Search

Background: In MR-guided in-bore percutaneous needle interventions, typically 2D interactive real-time imaging is used for navigating the needle into the target. Misaligned 2D imaging planes can result in losing visibility of the needle in the 2D images, which impedes successful targeting. Necessary iterative manual slice adjustment can prolong interventional workflows. Therefore, rapid automatic alignment of the imaging planes with the needle would be preferable to improve such workflows., Purpose: To investigate rapid 3D localization of needles in MR-guided interventions via a convolutional neural network (CNN)-based localization algorithm using an undersampled white-marker contrast acquisition for the purpose of automatic imaging slice alignment., Methods: A radial 3D rf-spoiled gradient echo MR pulse sequence with white-marker encoding was implemented and a CNN-based localization algorithm was employed to extract position and orientation of an aspiration needle from the undersampled white-marker images. The CNN was trained using porcine tissue phantoms (257 needle trajectories, four-fold data augmentation, 90%/10% split into training and validation dataset). Achievable localization times and accuracy were evaluated retrospectively in an ex vivo study (109 needle trajectories) for a range of needle orientations between 78° and 90° relative to the B 0 field. A proof-of-concept in vivo experiment was performed in two porcine animal models and feasibility of automatic imaging slice alignment was evaluated retrospectively., Results: Ex vivo needle localization was achieved with a median localization accuracy of 1.9 mm (distance needle tip to detected needle axis) and a median angular deviation of 2.6° for needle orientations between 86° and 90° to the B 0 field from fully sampled WM images (resolution of (4 mm) 3 , 6434 acquired radial k-space spokes, acquisition time of 80.4 s) in a field-of-view of (256 mm) 3 . Localization accuracy decreased with increasing undersampling and needle trajectory increasingly aligned with B 0 . For needle orientations between 86° and 90° to the B 0 field, a highly accelerated acquisition of only 32 k-space spokes (acquisition time of 0.4 s) yielded a median localization accuracy of 3.1 mm and a median angular deviation of 4.7°. For needle orientations between 78° and 82° to the B 0 field, a median accuracy and angular deviation of 3.5 mm and 6.8° could still be achieved with 64 sampled spokes (acquisition time of 0.8 s). In vivo, a localization accuracy of 1.4 mm and angular deviation of 3.4° was achieved sampling 32 k-space spokes (acquisition time of 0.48 s) with the needle oriented at 87.7° to the B 0 field. For a needle oriented at 77.6° to the B 0 field, localization accuracy of 5.3 mm and angular deviation of 6.8° were still achieved sampling 128 k-space spokes (acquisition time of 1.92 s), allowing for retrospective slice alignment., Conclusion: The investigated approach enables passive biopsy needle localization in 3D. Acceleration of the localization to real-time applicability is feasible for needle orientations approximately perpendicular to B 0 . The method can potentially facilitate MR-guided needle interventions by enabling automatic imaging slice alignment with the needle., (© 2024 Siemens Healthineers AG, Cook Advanced Technologies and The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Deep learning technology has made remarkable progress in pancreatic image segmentation tasks. However, annotating 3D medical images is time-consuming and requires expertise, and existing semi-supervised segmentation methods perform poorly in the segmentation task of organs with blurred edges in enhanced CT such as the pancreas., Purpose: To address the challenges of limited labeled data and indistinct boundaries of regions of interest (ROI)., Methods: We propose Edge-Biased Consistency Regularization (EBC-Net). 3D edge detection is employed to construct edge perturbations and integrate edge prior information into limited data, aiding the network in learning from unlabeled data. Additionally, due to the one-sidedness of a single perturbation space, we expand the dual-level perturbation space of both images and features to more efficiently focus the model's attention on the edges of the ROI. Finally, inspired by the clinical habits of doctors, we propose a 3D Anatomical Invariance Extraction Module and Anatomical Attention to capture anatomy-invariant features., Results: Extensive experiments have demonstrated that our method outperforms state-of-the-art methods in semi-supervised pancreas image segmentation. Moreover, it can better preserve the morphology of pancreatic organs and excel at edges region accuracy., Conclusions: Incorporated with edge prior knowledge, our method mixes disturbances in dual-perturbation space, which shifts the network's attention to the fuzzy edge region using a few labeled samples. These ideas have been verified on the pancreas segmentation dataset., (© 2024 American Association of Physicists in Medicine.)

Background: Recent advancements in anomaly detection have paved the way for novel radiological reading assistance tools that support the identification of findings, aimed at saving time. The clinical adoption of such applications requires a low rate of false positives while maintaining high sensitivity., Purpose: In light of recent interest and development in multi pathology identification, we present a novel method, based on a recent contrastive self-supervised approach, for multiple chest-related abnormality identification including low lung density area ("LLDA"), consolidation ("CONS"), nodules ("NOD") and interstitial pattern ("IP"). Our approach alerts radiologists about abnormal regions within a computed tomography (CT) scan by providing 3D localization., Methods: We introduce a new method for the classification and localization of multiple chest pathologies in 3D Chest CT scans. Our goal is to distinguish four common chest-related abnormalities: "LLDA", "CONS", "NOD", "IP" and "NORMAL". This method is based on a 3D patch-based classifier with a Resnet backbone encoder pretrained leveraging recent contrastive self supervised approach and a fine-tuned classification head. We leverage the SimCLR contrastive framework for pretraining on an unannotated dataset of randomly selected patches and we then fine-tune it on a labeled dataset. During inference, this classifier generates probability maps for each abnormality across the CT volume, which are aggregated to produce a multi-label patient-level prediction. We compare different training strategies, including random initialization, ImageNet weight initialization, frozen SimCLR pretrained weights and fine-tuned SimCLR pretrained weights. Each training strategy is evaluated on a validation set for hyperparameter selection and tested on a test set. Additionally, we explore the fine-tuned SimCLR pretrained classifier for 3D pathology localization and conduct qualitative evaluation., Results: Validated on 111 chest scans for hyperparameter selection and subsequently tested on 251 chest scans with multi-abnormalities, our method achieves an AUROC of 0.931 (95% confidence interval [CI]: [0.9034, 0.9557], p $ p$ -value < 0.001) and 0.963 (95% CI: [0.952, 0.976], p $ p$ -value < 0.001) in the multi-label and binary (i.e., normal versus abnormal) settings, respectively. Notably, our method surpasses the area under the receiver operating characteristic (AUROC) threshold of 0.9 for two abnormalities: IP (0.974) and LLDA (0.952), while achieving values of 0.853 and 0.791 for NOD and CONS, respectively. Furthermore, our results highlight the superiority of incorporating contrastive pretraining within the patch classifier, outperforming Imagenet pretraining weights and non-pretrained counterparts with uninitialized weights (F1 score = 0.943, 0.792, and 0.677 respectively). Qualitatively, the method achieved a satisfactory 88.8% completeness rate in localization and maintained an 88.3% accuracy rate against false positives., Conclusions: The proposed method integrates self-supervised learning algorithms for pretraining, utilizes a patch-based approach for 3D pathology localization and develops an aggregation method for multi-label prediction at patient-level. It shows promise in efficiently detecting and localizing multiple anomalies within a single scan., (© 2024 American Association of Physicists in Medicine.)

Background: Multi-organ segmentation is a critical task in medical imaging, with wide-ranging applications in both clinical practice and research. Accurate delineation of organs from high-resolution 3D medical images, such as CT scans, is essential for radiation therapy planning, enhancing treatment outcomes, and minimizing radiation toxicity risks. Additionally, it plays a pivotal role in quantitative image analysis, supporting various medical research studies. Despite its significance, manual segmentation of multiple organs from 3D images is labor-intensive and prone to low reproducibility due to high interoperator variability. Recent advancements in deep learning have led to several automated segmentation methods, yet many rely heavily on labeled data and human anatomy expertise., Purpose: In this study, our primary objective is to address the limitations of existing semi-supervised learning (SSL) methods for abdominal multi-organ segmentation. We aim to introduce a novel SSL approach that leverages unlabeled data to enhance the performance of deep neural networks in segmenting abdominal organs. Specifically, we propose a method that incorporates a redrawing network into the segmentation process to correct errors and improve accuracy., Methods: Our proposed method comprises three interconnected neural networks: a segmentation network for image segmentation, a teacher network for consistency regularization, and a redrawing network for object redrawing. During training, the segmentation network undergoes two rounds of optimization: basic training and readjustment. We adopt the Mean-Teacher model as our baseline SSL approach, utilizing labeled and unlabeled data. However, recognizing significant errors in abdominal multi-organ segmentation using this method alone, we introduce the redrawing network to generate redrawn images based on CT scans, preserving original anatomical information. Our approach is grounded in the generative process hypothesis, encompassing segmentation, drawing, and assembling stages. Correct segmentation is crucial for generating accurate images. In the basic training phase, the segmentation network is trained using both labeled and unlabeled data, incorporating consistency learning to ensure consistent predictions before and after perturbations. The readjustment phase focuses on reducing segmentation errors by optimizing the segmentation network parameters based on the differences between redrawn and original CT images., Results: We evaluated our method using two publicly available datasets: the beyond the cranial vault (BTCV) segmentation dataset (training: 44, validation: 6) and the abdominal multi-organ segmentation (AMOS) challenge 2022 dataset (training:138, validation:16). Our results were compared with state-of-the-art SSL methods, including MT and dual-task consistency (DTC), using the Dice similarity coefficient (DSC) as an accuracy metric. On both datasets, our proposed SSL method consistently outperformed other methods, including supervised learning, achieving superior segmentation performance for various abdominal organs. These findings demonstrate the effectiveness of our approach, even with a limited number of labeled data., Conclusions: Our novel semi-supervised learning approach for abdominal multi-organ segmentation addresses the challenges associated with this task. By integrating a redrawing network and leveraging unlabeled data, we achieve remarkable improvements in accuracy. Our method demonstrates superior performance compared to existing SSL and supervised learning methods. This approach holds great promise in enhancing the precision and efficiency of multi-organ segmentation in medical imaging applications., (© 2024 American Association of Physicists in Medicine.)

Background: Precise glioma segmentation from multi-parametric magnetic resonance (MR) images is essential for brain glioma diagnosis. However, due to the indistinct boundaries between tumor sub-regions and the heterogeneous appearances of gliomas in volumetric MR scans, designing a reliable and automated glioma segmentation method is still challenging. Although existing 3D Transformer-based or convolution-based segmentation networks have obtained promising results via multi-modal feature fusion strategies or contextual learning methods, they widely lack the capability of hierarchical interactions between different modalities and cannot effectively learn comprehensive feature representations related to all glioma sub-regions., Purpose: To overcome these problems, in this paper, we propose a 3D hierarchical cross-modality interaction network (HCMINet) using Transformers and convolutions for accurate multi-modal glioma segmentation, which leverages an effective hierarchical cross-modality interaction strategy to sufficiently learn modality-specific and modality-shared knowledge correlated to glioma sub-region segmentation from multi-parametric MR images., Methods: In the HCMINet, we first design a hierarchical cross-modality interaction Transformer (HCMITrans) encoder to hierarchically encode and fuse heterogeneous multi-modal features by Transformer-based intra-modal embeddings and inter-modal interactions in multiple encoding stages, which effectively captures complex cross-modality correlations while modeling global contexts. Then, we collaborate an HCMITrans encoder with a modality-shared convolutional encoder to construct the dual-encoder architecture in the encoding stage, which can learn the abundant contextual information from global and local perspectives. Finally, in the decoding stage, we present a progressive hybrid context fusion (PHCF) decoder to progressively fuse local and global features extracted by the dual-encoder architecture, which utilizes the local-global context fusion (LGCF) module to efficiently alleviate the contextual discrepancy among the decoding features., Results: Extensive experiments are conducted on two public and competitive glioma benchmark datasets, including the BraTS2020 dataset with 494 patients and the BraTS2021 dataset with 1251 patients. Results show that our proposed method outperforms existing Transformer-based and CNN-based methods using other multi-modal fusion strategies in our experiments. Specifically, the proposed HCMINet achieves state-of-the-art mean DSC values of 85.33% and 91.09% on the BraTS2020 online validation dataset and the BraTS2021 local testing dataset, respectively., Conclusions: Our proposed method can accurately and automatically segment glioma regions from multi-parametric MR images, which is beneficial for the quantitative analysis of brain gliomas and helpful for reducing the annotation burden of neuroradiologists., (© 2024 American Association of Physicists in Medicine.)

Background: Radiation delivery with ultra-high dose rate (FLASH) radiotherapy (RT) holds promise for improving treatment outcomes and reducing side effects but poses challenges in radiation delivery accuracy due to its ultra-high dose rates. This necessitates the development of novel imaging and verification technologies tailored to these conditions., Purpose: Our study explores the effectiveness of proton-induced acoustic imaging (PAI) in tracking the Bragg peak in three dimensions and in real time during FLASH proton irradiations, offering a method for volumetric beam imaging at both conventional and FLASH dose rates., Methods: We developed a three-dimensional (3D) PAI technique using a 256-element ultrasound detector array for FLASH dose rate proton beams. In the study, we tested protoacoustic signal with a beamline of a FLASH-capable synchrocyclotron, setting the distal 90% of the Bragg peak around 35 mm away from the ultrasound array. This configuration allowed us to assess various total proton radiation doses, maintaining a consistent beam output of 21 pC/pulse. We also explored a spectrum of dose rates, from 15 Gy/s up to a FLASH rate of 48 Gy/s, by administering a set number of pulses. Furthermore, we implemented a three-dot scanning beam approach to observe the distinct movements of individual Bragg peaks using PAI. All these procedures utilized a proton beam energy of 180 MeV to achieve the maximum possible dose rate., Results: Our findings indicate a strong linear relationship between protoacoustic signal amplitudes and delivered doses (R 2  = 0.9997), with a consistent fit across different dose rates. The technique successfully provided 3D renderings of Bragg peaks at FLASH rates, validated through absolute Gamma index values., Conclusions: The protoacoustic system demonstrates effectiveness in 3D visualization and tracking of the Bragg peak during FLASH proton therapy, representing a notable advancement in proton therapy quality assurance. This method promises enhancements in protoacoustic image guidance and real-time dosimetry, paving the way for more accurate and effective treatments in ultra-high dose rate therapy environments., (© 2024 American Association of Physicists in Medicine.)

Background: Protoacoustic (PA) imaging has the potential to provide real-time 3D dose verification of proton therapy. However, PA images are susceptible to severe distortion due to limited angle acquisition. Our previous studies showed the potential of using deep learning to enhance PA images. As the model was trained using a limited number of patients' data, its efficacy was limited when applied to individual patients., Purpose: In this study, we developed a patient-specific deep learning method for protoacoustic imaging to improve the reconstruction quality of protoacoustic imaging and the accuracy of dose verification for individual patients., Methods: Our method consists of two stages: in the first stage, a group model is trained from a diverse training set containing all patients, where a novel deep learning network is employed to directly reconstruct the initial pressure maps from the radiofrequency (RF) signals; in the second stage, we apply transfer learning on the pre-trained group model using patient-specific dataset derived from a novel data augmentation method to tune it into a patient-specific model. Raw PA signals were simulated based on computed tomography (CT) images and the pressure map derived from the planned dose. The reconstructed PA images were evaluated against the ground truth by using the root mean squared errors (RMSE), structural similarity index measure (SSIM) and gamma index on 10 specific prostate cancer patients. The significance level was evaluated by t-test with the p-value threshold of 0.05 compared with the results from the group model., Results: The patient-specific model achieved an average RMSE of 0.014 ( p < 0.05 ${{{p}}}&lt;{0.05}$ ), and an average SSIM of 0.981 ( p < 0.05 ${{{p}}}&lt;{0.05}$ ), out-performing the group model. Qualitative results also demonstrated that our patient-specific approach acquired better imaging quality with more details reconstructed when comparing with the group model. Dose verification achieved an average RMSE of 0.011 ( p < 0.05 ${{{p}}}&lt;{0.05}$ ), and an average SSIM of 0.995 ( p < 0.05 ${{{p}}}&lt;{0.05}$ ). Gamma index evaluation demonstrated a high agreement (97.4% [ p < 0.05 ${{{p}}}&lt;{0.05}$ ] and 97.9% [ p < 0.05 ${{{p}}}&lt;{0.05}$ ] for 1%/3  and 1%/5 mm) between the predicted and the ground truth dose maps. Our approach approximately took 6 s to reconstruct PA images for each patient, demonstrating its feasibility for online 3D dose verification for prostate proton therapy., Conclusions: Our method demonstrated the feasibility of achieving 3D high-precision PA-based dose verification using patient-specific deep-learning approaches, which can potentially be used to guide the treatment to mitigate the impact of range uncertainty and improve the precision. Further studies are needed to validate the clinical impact of the technique., (© 2024 American Association of Physicists in Medicine.)

Background: The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application., Purpose: In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images., Methods: A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results., Results: To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets., Conclusions: The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures., (© 2024 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Vessel-wall volume and localized three-dimensional ultrasound (3DUS) metrics are sensitive to the change of carotid atherosclerosis in response to medical/dietary interventions. Manual segmentation of the media-adventitia boundary (MAB) and lumen-intima boundary (LIB) required to obtain these metrics is time-consuming and prone to observer variability. Although supervised deep-learning segmentation models have been proposed, training of these models requires a sizeable manually segmented training set, making larger clinical studies prohibitive., Purpose: We aim to develop a method to optimize pre-trained segmentation models without requiring manual segmentation to supervise the fine-tuning process., Methods: We developed an adversarial framework called the unsupervised shape-and-texture generative adversarial network (USTGAN) to fine-tune a convolutional neural network (CNN) pre-trained on a source dataset for accurate segmentation of a target dataset. The network integrates a novel texture-based discriminator with a shape-based discriminator, which together provide feedback for the CNN to segment the target images in a similar way as the source images. The texture-based discriminator increases the accuracy of the CNN in locating the artery, thereby lowering the number of failed segmentations. Failed segmentation was further reduced by a self-checking mechanism to flag longitudinal discontinuity of the artery and by self-correction strategies involving surface interpolation followed by a case-specific tuning of the CNN. The U-Net was pre-trained by the source dataset involving 224 3DUS volumes with 136, 44, and 44 volumes in the training, validation and testing sets. The training of USTGAN involved the same training group of 136 volumes in the source dataset and 533 volumes in the target dataset. No segmented boundaries for the target cohort were available for training USTGAN. The validation and testing of USTGAN involved 118 and 104 volumes from the target cohort, respectively. The segmentation accuracy was quantified by Dice Similarity Coefficient (DSC), and incorrect localization rate (ILR). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference of DSCs between models and settings, where p ≤ 0.05 $p\,\le \,0.05$ was considered statistically significant., Results: USTGAN attained a DSC of 85.7 ± 13.0 $85.7\,\pm \,13.0$ % in LIB and 86.2 ± 10.6 ${86.2}\,\pm \,{10.6}$ % in MAB, improving from the baseline performance of 74.6 ± 30.7 ${74.6}\,\pm \,{30.7}$ % in LIB (p < 10 - 12 $&lt;10^{-12}$ ) and 75.7 ± 28.9 ${75.7}\,\pm \,{28.9}$ % in MAB (p < 10 - 12 $&lt;10^{-12}$ ). Our approach outperformed six state-of-the-art domain-adaptation models (MAB: p ≤ 3.63 × 10 - 7 $p \le 3.63\,\times \,10^{-7}$ , LIB: p ≤ 9.34 × 10 - 8 $p\,\le \,9.34\,\times \,10^{-8}$ ). The proposed USTGAN also had the lowest ILR among the methods compared (LIB: 2.5%, MAB: 1.7%)., Conclusion: Our framework improves segmentation generalizability, thereby facilitating efficient carotid disease monitoring in multicenter trials and in clinics with less expertise in 3DUS imaging., (© 2024 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Objectives: To analyze the three-dimensional stability and morphologic changes of tent space after the osteotome sinus floor elevation (OSFE) procedures without bone grafts., Materials and Methods: Forty-six implants placed using the OSFE technique with simultaneous implant placement without bone grafts were included in this retrospective study. Cone-beam computed tomography (CBCT) scans of the augmented sinuses were obtained pre- and postoperatively up to 48 months of follow-up. The maxillary sinus cavity profiles were outlined using three-dimensional virtual reconstruction and superimposition of CBCT scans. The three-dimensional changes in the tent space were measured. A generalized estimating equation (GEE) was used to explore potential factors., Results: The implant survival rate was 97.8%. The mean volume of remaining tent space immediately after surgery was 96.8 ± 70.5 mm 3 , shrinking to 31.0 ± 24.9 mm 3 after 48 months, while the mean percentage of remaining tent space volume decreased to 29.1 ± 20.7%. The tent space volume and the percentage of residual tent space volume only decreased significantly within 12 months after surgery (p = .008, .013). GEE results indicated positive correlations between the percentage of remaining tent space volume and implant protrusion length (p = .000) and apical height (p = .000), with a negative correlation between the sinus floor area immediately after surgery (p = .002) and the healing time (p = .022)., Conclusions: The volume of the tent space rapidly shrank after OSFE without bone grafts. Several factors might influence the tent space stability. Long-term clinical trials with larger sample sizes are necessary to further validate the results., (© 2024 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Background: Intensity modulation with dynamic multi-leaf collimator (MLC) and monitor unit (MU) changes across control points (CPs) characterizes volumetric modulated arc therapy (VMAT). The increased uncertainty in plan deliverability required patient-specific quality assurance (PSQA), which remained inefficient upon Quality Assurance (QA) failure. To prevent waste before QA, plan complexity metrics (PCMs) and machine learning models with the metrics were generated, which were lack of providing CP-specific information upon QA failures., Purpose: By generating 3D images from digital imaging and comminications in medicine in radiation therapy (DICOM RT) plan, we proposed a predictive model that can estimate the deliverability of VMAT plans and visualize CP-specific regions associated with plan deliverability., Methods: The patient cohort consisted of 259 and 190 cases for left- and right-breast VMAT treatments, which were split into 235 and 166 cases for training and 24 cases from each treatment for testing the networks. Three-channel 3D images generated from DICOM RT plans were fed into a DenseNet-based deep learning network. To reflect VMAT plan complexity as an image, the first two channels described MLC and MU variations between two consecutive CPs, while the last channel assigned the beam field size. The network output was defined as binary classified PSQA results, indicating deliverability. The predictive performance was assessed by accuracy, sensitivity, specificity, F1-score, and area under the curve (AUC). The gradient-weighted class activation map (Grad-CAM) highlighted the regions of CPs in VMAT plans associated with deliverability, compared against PCMs by Spearman correlation., Results: The DenseNet-based predictive model yielded AUCs of 92.2% and 93.8%, F1-scores of 97.0% and 93.8% and accuracies of 95.8% and 91.7% for the left- and right-breast VMAT cases. Additionally, the specificity of 87.5% for both cases indicated that the predictive model accurately detected QA failing cases. The activation maps significantly differentiated QA failing-labeled from passing-labeled classes for the non-deliverable cases. The PCM with the highest correlation to the Grad-CAM varied from patient cases, implying that plan deliverability would be considered patient-specific., Conclusion: This work demonstrated that the deep learning-based network based on visualization of dynamic VMAT plan information successfully predicted plan deliverability, which also provided control-point specific planning parameter information associated with plan deliverability in a patient-specific manner., (© 2024 American Association of Physicists in Medicine.)

Background: The image resolution of fetal brain magnetic resonance imaging (MRI) is a critical factor in brain development measures, which is mainly determined by the physical resolution configured in the MRI sequence. However, fetal brain MRI are commonly reconstructed to 3D images with a higher apparent resolution, compared to the original physical resolution., Purpose: This work is to demonstrate that accurate segmentation can be achieved based on the MRI physical resolution, and the high apparent resolution segmentation can be achieved by a simple deep learning module., Methods: This retrospective study included 150 adult and 80 fetal brain MRIs. The adult brain MRIs were acquired at a high physical resolution, which were downsampled to visualize and quantify its impacts on the segmentation accuracy. The physical resolution of fetal images was estimated based on MRI acquisition settings and the images were downsampled accordingly before segmentation and restored using multiple upsampling strategies. Segmentation accuracy of ConvNet models were evaluated on the original and downsampled images. Dice coefficients were calculated, and compared to the original data., Results: When the apparent resolution was higher than the physical resolution, the accuracy of fetal brain segmentation had negligible degradation (accuracy reduced by 0.26%, 1.1%, and 1.8% with downsampling factors of 4/3, 2, and 4 in each dimension, without significant differences from the original data). Using a downsampling factor of 4 in each dimension, the proposed method provided 7× smaller and 10× faster models., Conclusion: Efficient and accurate fetal brain segmentation models can be developed based on the physical resolution of MRI acquisitions., (© 2024 American Association of Physicists in Medicine.)

Background: Lung cancer is the most common type of cancer. Detection of lung cancer at an early stage can reduce mortality rates. Pulmonary nodules may represent early cancer and can be identified through computed tomography (CT) scans. Malignant risk can be estimated based on attributes like size, shape, location, and density., Purpose: Deep learning algorithms have achieved remarkable advancements in this domain compared to traditional machine learning methods. Nevertheless, many existing anchor-based deep learning algorithms exhibit sensitivity to predefined anchor-box configurations, necessitating manual adjustments to obtain optimal outcomes. Conversely, current anchor-free deep learning-based nodule detection methods normally adopt fixed-size nodule models like cubes or spheres., Methods: To address these technical challenges, we propose a multiscale 3D anchor-free deep learning network (M3N) for pulmonary nodule detection, leveraging adjustable nodule modeling (ANM). Within this framework, ANM empowers the representation of target objects in an anisotropic manner, with a novel point selection strategy (PSS) devised to accelerate the learning process of anisotropic representation. We further incorporate a composite loss function that combines the conventional L2 loss and cosine similarity loss, facilitating M3N to learn nodules' intensity distribution in three dimensions., Results: Experiment results show that the M3N achieves 90.6% competitive performance metrics (CPM) with seven predefined false positives per scan on the LUNA 16 dataset. This performance appears to exceed that of other state-of-the-art deep learning-based networks reported in their respective publications. Individual test results also demonstrate that M3N excels in providing more accurate, adaptive bounding boxes surrounding the contours of target nodules., Conclusions: The newly developed nodule detection system reduces reliance on prior knowledge, such as the general size of objects in the dataset, thus it should enhance overall robustness and versatility. Distinct from traditional nodule modeling techniques, the ANM approach aligns more closely with the morphological characteristics of nodules. Time consumption and detection results demonstrate promising efficiency and accuracy which should be validated in clinical settings., (© 2024 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Three-dimensional (3D) ultrasound (US) imaging has shown promise in non-invasive monitoring of changes in the lateral brain ventricles of neonates suffering from intraventricular hemorrhaging. Due to the poorly defined anatomical boundaries and low signal-to-noise ratio, fully supervised methods for segmentation of the lateral ventricles in 3D US images require a large dataset of annotated images by trained physicians, which is tedious, time-consuming, and expensive. Training fully supervised segmentation methods on a small dataset may lead to overfitting and hence reduce its generalizability. Semi-supervised learning (SSL) methods for 3D US segmentation may be able to address these challenges but most existing SSL methods have been developed for magnetic resonance or computed tomography (CT) images., Purpose: To develop a fast, lightweight, and accurate SSL method, specifically for 3D US images, that will use unlabeled data towards improving segmentation performance., Methods: We propose an SSL framework that leverages the shape-encoding ability of an autoencoder network to enforce complex shape and size constraints on a 3D U-Net segmentation model. The autoencoder created pseudo-labels, based on the 3D U-Net predicted segmentations, that enforces shape constraints. An adversarial discriminator network then determined whether images came from the labeled or unlabeled data distributions. We used 887 3D US images, of which 87 had manually annotated labels and 800 images were unlabeled. Training/validation/testing sets of 25/12/50, 25/12/25 and 50/12/25 images were used for model experimentation. The Dice similarity coefficient (DSC), mean absolute surface distance (MAD), and absolute volumetric difference (VD) were used as metrics for comparing to other benchmarks. The baseline benchmark was the fully supervised vanilla 3D U-Net while dual task consistency, shape-aware semi-supervised network, correlation-aware mutual learning, and 3D U-Net Ensemble models were used as state-of-the-art benchmarks with DSC, MAD, and VD as comparison metrics. The Wilcoxon signed-rank test was used to test statistical significance between algorithms for DSC and VD with the threshold being p < 0.05 and corrected to p < 0.01 using the Bonferroni correction. The random-access memory (RAM) trace and number of trainable parameters were used to compare the computing efficiency between models., Results: Relative to the baseline 3D U-Net model, our shape-encoding SSL method reported a mean DSC improvement of 6.5%, 7.7%, and 4.1% with a 95% confidence interval of 4.2%, 5.7%, and 2.1% using image data splits of 25/12/50, 25/12/25, and 50/12/25, respectively. Our method only used a 1GB increase in RAM compared to the baseline 3D U-Net and required less than half the RAM and trainable parameters compared to the 3D U-Net ensemble method., Conclusions: Based on our extensive literature survey, this is one of the first reported works to propose an SSL method designed for segmenting organs in 3D US images and specifically one that incorporates unlabeled data for segmenting neonatal cerebral lateral ventricles. When compared to the state-of-the-art SSL and fully supervised learning methods, our method yielded the highest DSC and lowest VD while being computationally efficient., (© 2024 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Accurate measurement of ureteral diameters plays a pivotal role in diagnosing and monitoring urinary tract obstruction (UTO). While three-dimensional magnetic resonance urography (3D MRU) represents a significant advancement in imaging, the traditional manual methods for assessing ureteral diameters are characterized by labor-intensive procedures and inherent variability. In the realm of medical image analysis, deep learning has led to a paradigm shift, yet the development of a comprehensive automated tool for the precise segmentation and measurement of ureters in MR images is an unaddressed challenge., Purpose: The ureter was quantitatively measured on 3D MRU images using a deep learning model., Methods: A retrospective cohort of 445 3D MRU scans (443 patients, 52 ± 18 years; 217 female patients) was collected and split into training, validation, and internal testing cohorts. A 3D V-Net model was trained for urinary tract segmentation, and a post-processing algorithm was developed for ureteral measurements. The accuracy of the segmentation was evaluated using the Dice similarity coefficient (DSC) and volume intraclass correlation coefficient (ICC), with ground truth segmentations provided by experienced radiologists. The external cohort comprised 50 scans (50 patients, 55 ± 21 years; 30 female patients), and the model-predicted ureteral diameter measurements were compared with manual measurements to assess system performance. The various diameter parameters of ureter among the different measurement methods (ground truth, auto-segmentation with automatic diameter extraction, and manual segmentation with automatic diameter extraction) were assessed with Friedman tests and post hoc Dunn test. The effectiveness of the UTO diagnosis was assessed by receiver operating characteristic (ROC) curves and their respective areas under the curve (AUC) between different methods., Results: In both the internal test and external cohorts, the mean DSC values for bilateral ureters exceeded 0.70. The ICCs for the bilateral ureter volume obtained by comparing the model and manual segmentation were all greater than 0.96 (p  <  0.05), except for the right ureter in the internal test cohort, for which the ICC was 0.773 (p  <  0.05). The mean DSCs for interobserver and intraobserver reliability were all above 0.97. The maximum diameter of the ureter exhibited no statistically significant differences either in the dilated (p = 0.08) or in the non-dilated (p = 0.32) ureters across the three measurement methods. The AUCs of ground truth, auto-segmentation with automatic diameter extraction, and manual segmentation with automatic diameter extraction in diagnosing UTO were 0.988 (95% CI: 0.934, 1.000), 0.961 (95% CI: 0.893, 0.991), and 0.979 (95% CI: 0.919, 0.998), respectively. There was no statistical difference between AUCs of the different methods (p > 0.05)., Conclusion: The proposed deep learning model and post-processing algorithm provide an effective means for the quantitative evaluation of urinary diseases using 3D MRU images., (© 2024 American Association of Physicists in Medicine.)

Objectives: This study aimed to develop a structured light scanning system with a planar mirror to enhance the digital full-arch implant impression accuracy and to compare it with photogrammetry and intraoral scanner methods., Materials and Methods: An edentulous maxillary stone cast with six scan bodies was scanned as the reference model using a laboratory scanner. Three scanning modalities were compared (n = 10): (1) self-developed structured light scanning with a mirror (SSLS); (2) intraoral scanner (IOS); and (3) photogrammetry system (PG). The scanners were stopped for 1 min after each scan. Six scan bodies were analysed within each scan model. Linear deviations between the scan bodies (1-2, 1-3, 1-4, 1-5, and 1-6) and 3D mucosal deviations were established. The overall deviation was calculated as the mean of all linear deviations. "Trueness" represented the discrepancy between the test and reference files, while "precision" denoted the consistency among the test files. Kruskal-Wallis and Mann-Whitney U tests were used for statistical analyses., Results: Significant overall linear discrepancies were noted among the SSLS, PG, and IOS groups (p < .001). SSLS showed the best overall trueness and precision (6.6, 5.7 μm), followed by PG (58.4, 6.8 μm) and IOS (214.6, 329.1 μm). For the 3D mucosal deviation, the trueness (p < .001) and precision (p < .001) of the SSLS group were significantly better than those of the IOS group., Conclusions: The SSLS exhibited higher accuracy in determining the implant positions than the PG and IOS. Additionally, it demonstrated better accuracy in capturing the mucosa than IOS., (© 2023 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Objectives: The purpose of this prospective study was to determine the inter- and intraindividual variability in virtual single-tooth implant positioning based on the level of expertise, specialty, total time spent, and the use of a prosthetic tooth setup., Materials and Methods: Virtual implant planning was performed on matched pre- and post-extraction intraoral scans (IOS), and cone-beam computed tomography scans of 15 patients. Twelve individual examiners, involving six novices and experts from oral surgery and prosthodontics positioned the implants, first based on anatomical landmarks utilizing only the post-extraction, and second with the use of the pre-extraction IOS as a setup. The time for implant positioning was recorded. After 1 month, all virtual plannings were performed again. The individual implant positions were superimposed to obtain 3D deviations using a software algorithm., Results: An interindividual variability with mean angular, crestal, and apical positional deviations of 3.8 ± 1.94°, 1.11 ± 0.55, and 1.54 ± 0.66 mm, respectively, was found. When assessing intraindividual variability, deviations of 3.28 ± 1.99°, 0.78 ± 0.46, and 1.12 ± 0.61 mm, respectively, were observed. Implants planned by experts exhibited statistically lower deviations compared to those planned by novices. Longer planning times resulted in lower deviations in the experts' group but not in the novices. Oral surgeons demonstrated lower crestal, but not angular and apical deviations than prosthodontists. The use of a setup only led to minor adjustments., Conclusions: Substantial inter- and intraindividual variability exists during implant positioning utilizing specialized software planning. The level of expertise and the time invested influenced the deviations of the implant position during the planning sequence., (© 2023 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Background: In laparoscopic liver surgery, accurately predicting the displacement of key intrahepatic anatomical structures is crucial for informing the doctor's intraoperative decision-making. However, due to the constrained surgical perspective, only a partial surface of the liver is typically visible. Consequently, the utilization of non-rigid volume to surface registration methods becomes essential. But traditional registration methods lack the necessary accuracy and cannot meet real-time requirements., Purpose: To achieve high-precision liver registration with only partial surface information and estimate the displacement of internal liver tissues in real-time., Methods: We propose a novel neural network architecture tailored for real-time non-rigid liver volume to surface registration. The network utilizes a voxel-based method, integrating sparse convolution with the newly proposed points of interest (POI) linear attention module. POI linear attention module specifically calculates attention on the previously extracted POI. Additionally, we identified the most suitable normalization method RMSINorm., Results: We evaluated our proposed network and other networks on a dataset generated from real liver models and two real datasets. Our method achieves an average error of 4.23 mm and a mean frame rate of 65.4 fps in the generation dataset. It also achieves an average error of 8.29 mm in the human breathing motion dataset., Conclusions: Our network outperforms CNN-based networks and other attention networks in terms of accuracy and inference speed., (© 2024 American Association of Physicists in Medicine.)

Objective: The purpose of the present study was to assess the influence of color temperature and illuminance of ambient light on the accuracy of different intraoral scanners (IOSs) in complete-arch implant scans., Methods: An edentulous model with six implants and scan bodies was digitized by using a laboratory scanner (DW-7-140; Dental Wings) to obtain a reference mesh. Fifteen scans were performed employing two intraoral scanners (Trios 4;3Shape A/S and i700; Medit Co) at two illuminances (500 and 1000 lux) and three color temperatures (3200, 4400, and 5600 K). Scanning accuracy was measured by using a 3D metrology software program (Geomagic Control X). Kruskal-Wallis, one-way ANOVA, and pairwise comparison tests were used to analyze the data (α = .05)., Results: Significant differences in trueness and precision values were found among the different IOSs under the same ambient lighting condition and among the different lighting conditions for a given IOS (p < .05) except for trueness in i700 groups (p > .05)., Conclusions: The influence on the accuracy of color temperature and illuminance varied depending on the intraoral scanner. An optimal ambient scanning light condition was not found; this should be adjusted based on the specific IOS system used. 3200 K of ambient light influences the precision of i700 when performed at 1000 lux, decreasing the accuracy. The variation of color temperature at the same illuminance does not affect the scanning accuracy of TRIOS 4, which obtained better accuracy in all scans at 1000 lux., (© 2023 The Authors. Clinical Oral Implants Research published by John Wiley & Sons Ltd.)

Aim: To introduce an objective method to evaluate the accuracy of implant position assessment in partially edentulous patients by comparing different techniques (conventional impression, intraoral scan, CBCT) to a reference 3D model obtained with an industrial scanner, the latter mimicking the clinical situation., Materials and Methods: Twenty-nine implants were placed in four human cadaver heads using a fully guided flapless protocol. Implant position was assessed using (a) a conventional impression, (b) an intraoral scan, and (c) CBCT and compared to an industrial scan. Three-dimensional models of intraoral scan body and implant were registered to the arch models and the deviation at implant shoulder, apex, and the angle of deviation were compared to each other as well as to the reference model., Results: The three assessment techniques showed statistically significant deviations (p < .01) from the industrial scan, for all measurements, with no difference between the techniques. The maximum deviation at the implant shoulder was 0.16 mm. At the implant apex this increased to 0.38 mm. The intraoral scan deviated significantly more than the CBCT (0.12 mm, p < .01) and the conventional impression (0.10 mm, p = .02). The maximum implant angle deviation was 1.0°. The intraoral scan deviated more than the conventional impression (0.3°, p = .02)., Conclusion: All assessment techniques deviated from the reference industrial scan, but the differences were relatively small. Intraoral scans were slightly less accurate than both conventional impressions and CBCT. Depending on the application, however, this inaccuracy may not be clinically relevant., (© 2023 The Authors. Clinical Oral Implants Research published by John Wiley & Sons Ltd.)

Background: Image-to-patient registration aligns preoperative images to intra-operative anatomical structures and it is a critical step in image-guided surgery (IGS). The accuracy and speed of this step significantly influence the performance of IGS systems. Rigid registration based on paired points has been widely used in IGS, but studies have shown its limitations in terms of cost, accuracy, and registration time. Therefore, rigid registration of point clouds representing the human anatomical surfaces has become an alternative way for image-to-patient registration in the IGS systems., Purpose: We propose a novel correspondence-based rigid point cloud registration method that can achieve global registration without the need for pose initialization. The proposed method is less sensitive to outliers compared to the widely used RANSAC-based registration methods and it achieves high accuracy at a high speed, which is particularly suitable for the image-to-patient registration in IGS., Methods: We use the rotation axis and angle to represent the rigid spatial transformation between two coordinate systems. Given a set of correspondences between two point clouds in two coordinate systems, we first construct a 3D correspondence cloud (CC) from the inlier correspondences and prove that the CC distributes on a plane, whose normal is the rotation axis between the two point clouds. Thus, the rotation axis can be estimated by fitting the CP. Then, we further show that when projecting the normals of a pair of corresponding points onto the CP, the angle between the projected normal pairs is equal to the rotation angle. Therefore, the rotation angle can be estimated from the angle histogram. Besides, this two-stage estimation also produces a high-quality correspondence subset with high inlier rate. With the estimated rotation axis, rotation angle, and the correspondence subset, the spatial transformation can be computed directly, or be estimated using RANSAC in a fast and robust way within only 100 iterations., Results: To validate the performance of the proposed registration method, we conducted experiments on the CT-Skull dataset. We first conducted a simulation experiment by controlling the initial inlier rate of the correspondence set, and the results showed that the proposed method can effectively obtain a correspondence subset with much higher inlier rate. We then compared our method with traditional approaches such as ICP, Go-ICP, and RANSAC, as well as recently proposed methods like TEASER, SC2-PCR, and MAC. Our method outperformed all traditional methods in terms of registration accuracy and speed. While achieving a registration accuracy comparable to the recently proposed methods, our method demonstrated superior speed, being almost three times faster than TEASER., Conclusions: Experiments on the CT-Skull dataset demonstrate that the proposed method can effectively obtain a high-quality correspondence subset with high inlier rate, and a tiny RANSAC with 100 iterations is sufficient to estimate the optimal transformation for point cloud registration. Our method achieves higher registration accuracy and faster speed than existing widely used methods, demonstrating great potential for the image-to-patient registration, where a rigid spatial transformation is needed to align preoperative images to intra-operative patient anatomy., (© 2024 American Association of Physicists in Medicine.)

Background: Proton therapy is a form of radiotherapy commonly used to treat various cancers. Due to its high conformality, minor variations in patient anatomy can lead to significant alterations in dose distribution, making adaptation crucial. While cone-beam computed tomography (CBCT) is a well-established technique for adaptive radiation therapy (ART), it cannot be directly used for adaptive proton therapy (APT) treatments because the stopping power ratio (SPR) cannot be estimated from CBCT images., Purpose: To address this limitation, Deep Learning methods have been suggested for converting pseudo-CT (pCT) images from CBCT images. In spite of convolutional neural networks (CNNs) have shown consistent improvement in pCT literature, there is still a need for further enhancements to make them suitable for clinical applications., Methods: The authors introduce the 3D vision transformer (ViT) block, studying its performance at various stages of the proposed architectures. Additionally, they conduct a retrospective analysis of a dataset that includes 259 image pairs from 59 patients who underwent treatment for head and neck cancer. The dataset is partitioned into 80% for training, 10% for validation, and 10% for testing purposes., Results: The SPR maps obtained from the pCT using the proposed method present an absolute relative error of less than 5% from those computed from the planning CT, thus improving the results of CBCT., Conclusions: We introduce an enhanced ViT3D architecture for pCT image generation from CBCT images, reducing SPR error within clinical margins for APT workflows. The new method minimizes bias compared to CT-based SPR estimation and dose calculation, signaling a promising direction for future research in this field. However, further research is needed to assess the robustness and generalizability across different medical imaging applications., (© 2024 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Prostate cancer (PCa) is the most common cancer in men and the second leading cause of male cancer-related death. Gleason score (GS) is the primary driver of PCa risk-stratification and medical decision-making, but can only be assessed at present via biopsy under anesthesia. Magnetic resonance imaging (MRI) is a promising non-invasive method to further characterize PCa, providing additional anatomical and functional information. Meanwhile, the diagnostic power of MRI is limited by qualitative or, at best, semi-quantitative interpretation criteria, leading to inter-reader variability., Purposes: Computer-aided diagnosis employing quantitative MRI analysis has yielded promising results in non-invasive prediction of GS. However, convolutional neural networks (CNNs) do not implicitly impose a frame of reference to the objects. Thus, CNNs do not encode the positional information properly, limiting method robustness against simple image variations such as flipping, scaling, or rotation. Capsule network (CapsNet) has been proposed to address this limitation and achieves promising results in this domain. In this study, we develop a 3D Efficient CapsNet to stratify GS-derived PCa risk using T2-weighted (T2W) MRI images., Methods: In our method, we used 3D CNN modules to extract spatial features and primary capsule layers to encode vector features. We then propose to integrate fully-connected capsule layers (FC Caps) to create a deeper hierarchy for PCa grading prediction. FC Caps comprises a secondary capsule layer which routes active primary capsules and a final capsule layer which outputs PCa risk. To account for data imbalance, we propose a novel dynamic weighted margin loss. We evaluate our method on a public PCa T2W MRI dataset from the Cancer Imaging Archive containing data from 976 patients., Results: Two groups of experiments were performed: (1) we first identified high-risk disease by classifying low + medium risk versus high risk; (2) we then stratified disease in one-versus-one fashion: low versus high risk, medium versus high risk, and low versus medium risk. Five-fold cross validation was performed. Our model achieved an area under receiver operating characteristic curve (AUC) of 0.83 and 0.64 F1-score for low versus high grade, 0.79 AUC and 0.75 F1-score for low + medium versus high grade, 0.75 AUC and 0.69 F1-score for medium versus high grade and 0.59 AUC and 0.57 F1-score for low versus medium grade. Our method outperformed state-of-the-art radiomics-based classification and deep learning methods with the highest metrics for each experiment. Our divide-and-conquer strategy achieved weighted Cohen's Kappa score of 0.41, suggesting moderate agreement with ground truth PCa risks., Conclusions: In this study, we proposed a novel 3D Efficient CapsNet for PCa risk stratification and demonstrated its feasibility. This developed tool provided a non-invasive approach to assess PCa risk from T2W MR images, which might have potential to personalize the treatment of PCa and reduce the number of unnecessary biopsies., (© 2024 American Association of Physicists in Medicine.)

Background: Dynamic contrast-enhanced ultrasound (DCE-US) is highly susceptible to motion artifacts arising from patient movement, respiration, and operator handling and experience. Motion artifacts can be especially problematic in the context of perfusion quantification. In conventional 2D DCE-US, motion correction (MC) algorithms take advantage of accompanying side-by-side anatomical B-Mode images that contain time-stable features. However, current commercial models of 3D DCE-US do not provide side-by-side B-Mode images, which makes MC challenging., Purpose: This work introduces a novel MC algorithm for 3D DCE-US and assesses its efficacy when handling clinical data sets., Methods: In brief, the algorithm uses a pyramidal approach whereby short temporal windows consisting of three consecutive frames are created to perform local registrations, which are then registered to a master reference derived from a weighted average of all frames. We applied the algorithm to imaging studies from eight patients with metastatic lesions in the liver and assessed improvements in original versus motion corrected 3D DCE-US cine using: (i) frame-to-frame volumetric overlap of segmented lesions, (ii) normalized correlation coefficient (NCC) between frames (similarity analysis), and (iii) sum of squared errors (SSE), root-mean-squared error (RMSE), and r-squared (R 2 ) quality-of-fit from fitted time-intensity curves (TIC) extracted from a segmented lesion., Results: We noted improvements in frame-to-frame lesion overlap across all patients, from 68% ± 13% without correction to 83% ± 3% with MC (p = 0.023). Frame-to-frame similarity as assessed by NCC also improved on two different sets of time points from 0.694 ± 0.057 (original cine) to 0.862 ± 0.049 (corresponding MC cine) and 0.723 ± 0.066 to 0.886 ± 0.036 (p ≤ 0.001 for both). TIC analysis displayed a significant decrease in RMSE (p = 0.018) and a significant increase in R 2 goodness-of-fit (p = 0.029) for the patient cohort., Conclusions: Overall, results suggest decreases in 3D DCE-US motion after applying the proposed algorithm., (© 2024 American Association of Physicists in Medicine.)

Background: Time-resolved magnetic resonance fingerprinting (MRF), or 4D-MRF, has been demonstrated its feasibility in motion management in radiotherapy (RT). However, the prohibitive long acquisition time is one of challenges of the clinical implementation of 4D-MRF. The shortening of acquisition time causes data insufficiency in each respiratory phase, leading to poor accuracies and consistencies of the predicted tissues' properties of each phase., Purpose: To develop a technique for the reconstruction of multi-phase parametric maps in four-dimensional magnetic resonance fingerprinting (4D-MRF) through the optimization of local T1 and T2 sensitivities., Methods: The proposed technique employed an iterative optimization to tailor the data arrangement of each phase by manipulation of inter-phase frames, such that the T1 and T2 sensitivities, which were quantified by the modified Minkowski distance, of the truncated signal evolution curve was maximized. The multi-phase signal evolution curves were modified by sliding window reconstruction and inter-phase frame sharing (SWIFS). Motion correction (MC) and dot product matching were sequentially performed on the modified signal evolution and dictionary to reconstruct the multi-parametric maps. The proposed technique was evaluated by numerical simulations using the extended cardiac-torso (XCAT) phantom with regular and irregular breathing patterns, and by in vivo MRF data of three health volunteers and six liver cancer patients acquired at a 3.0 T scanner., Results: In simulation study, the proposed SWIFS approach achieved the overall mean absolute percentage error (MAPE) of 8.62% ± 1.59% and 16.2% ± 3.88% for the eight-phases T1 and T2 maps, respectively, in the sagittal view with irregular breathing patterns. In contrast, the overall MAPE of T1 and T2 maps generated by the conventional approach with multiple MRF repetitions were 22.1% ± 11.0% and 30.8% ± 14.9%, respectively. For in-vivo study, the predicted mean T1 and T2 of liver by the proposed SWIFS approach were 795 ms ± 38.9 ms and 58.3 ms ± 11.7 ms, respectively., Conclusions: Both simulation and in vivo results showed that the approach empowered by T1 and T2 sensitivities optimization and sliding window under the shortened acquisition of MRF had superior performance in the estimation of multi-phase T1 and T2 maps as compared to the conventional approach with oversampling of MRF data., (© 2024 American Association of Physicists in Medicine.)

Objective: This in-vitro study assessed the influence of two intraoral scanning (IOS) protocols on the accuracy (trueness and precision) of digital scans performed in edentulous arches., Methods: Twenty-two abutment-level master casts of edentulous arches with at least four implants were scanned repeatedly five times, each with two different scanning protocols. Protocol A (IOS-A) consisted of scanning the edentulous arch before inserting the implant scan bodies, followed by their insertion and its subsequent digital acquisition. Protocol B (IOS-B) consisted of scanning the edentulous arch with the scan bodies inserted from the outset. A reference scan from each edentulous cast was obtained using a laboratory scanner. Trueness and precision were calculated using the spatial fit analysis, cross-arch distance, and virtual Sheffield test. Statistical analysis was performed using generalized estimating equations (GEEs). Statistical significance was set at α = .05., Results: In the spatial fit test, the precision of average 3D distances was 45 μm (±23 μm) with protocol IOS-A and 25 μm (±10 μm) for IOS-B (p < .001), and the trueness of average 3D distances was 44 μm (±24 μm) with protocol IOS-A and 24 μm (±7 μm) for IOS-B (p < .001). Cross-arch distance precision was 59 μm (±53 μm) for IOS-A and 41 μm (±43 μm) for IOS-B (p = .0035), and trueness was 64 μm (±47 μm) for IOS-A and 50 μm (±40 μm) for IOS-B (p = .0021). Virtual Sheffield precision was 286 μm (±198 μm) for IOS-A and 146 μm (±92 μm) for IOS-B (p < .001), and trueness was 228 μm (±171 μm) for IOS-A and 139 μm (±92 μm) for IOS-B (p < .001)., Conclusions: The IOS-B protocol demonstrated significantly superior accuracy. Placement of scan bodies before scanning the edentulous arch is recommended to improve the accuracy of complete-arch intraoral scanning., (© 2024 The Authors. Clinical Oral Implants Research published by John Wiley & Sons Ltd.)

Objectives: The purpose of this in vitro study was to compare the trueness and precision of complete arch implant impressions using conventional impression, intraoral scanning with and without splinting, and stereophotogrammetry., Materials and Methods: An edentulous model with six implants was used in this study. Four implant impression techniques were compared: the conventional impression (CI), intraoral scanning (IOS) without splinting, intraoral scanning with splinting (MIOS), and stereophotogrammetry (SPG). An industrial blue light scanner was used to generate the baseline scan from the model. The CI was captured with a laboratory scanner. The reference best-fit method was then applied in the computer-aided design (CAD) software to compute the three-dimensional, angular, and linear discrepancies among the four impression techniques. The root mean square (RMS) 3D discrepancies in trueness and precision between the four impression groups were analyzed with a Kruskal-Wallis test. Trueness and precision between single analogs were assessed using generalized estimating equations., Results: Significant differences in the overall trueness (p = .017) and precision (p < .001) were observed across four impression groups. The SPG group exhibited significantly smaller RMS 3D deviations than the CI, IOS, and MIOS groups (p < .05), with no significant difference detected among the latter three groups (p > .05)., Conclusions: Stereophotogrammetry showed superior trueness and precision, meeting misfit thresholds for implant-supported complete arch prostheses. Intraoral scanning, while accurate like conventional impressions, exhibited cross-arch angular and linear deviations. Adding a splint to the scan body did not improve intraoral scanning accuracy., (© 2024 The Authors. Clinical Oral Implants Research published by John Wiley & Sons Ltd.)

Background: Misalignment or double-contouring artifacts can appear in high-resolution 3D cone beam computed tomography (CBCT) images, potentially indicating geometric accuracy issues in the projection data. Such artifacts may go unnoticed in low-resolution images and could be associated with changes in the focal spot (FS) position., Purpose: High-resolution 3D-CBCT imaging by a mobile imaging device with a large gantry clearance offers more versatility for clinical workflows in image-guided brachytherapy (IGBT), intraoperative radiation therapy (IORT), and spinal, as well as maxillofacial surgery. However, misalignment or double-contouring artifacts hinder workflow advancements in these domains. This paper introduces intrinsic calibration and geometrical correction methods as extensions to a well-established technique for addressing geometrical deviations resulting from factors such as gravity or mechanical inconsistencies. These extensions cover shifts and drifts of the FS depending on FS size selection, temperature, tube current, and tube potential. The proposed methods effectively mitigate artifacts in high-resolution CBCT images stemming from geometrical inaccuracies in projection data, without requiring additional equipment like a pinhole device., Methods: Geometrical offsets and drifts of the x-ray tube FS were characterized on a mobile multi-purpose imaging system, the ImagingRing-m. A pinhole-like experiment was simulated by adjusting the movable collimation unit to a small rectangular aperture within the FS size range. The influence of filament selection, that is, FS size, temperature, the relatively low tube currents, as well as tube potential settings have been studied on two different monobloc types sharing the same x-ray tube insert. The Catphan 504 and an Alderson head phantom were used to assess resulting image artifacts., Results: Switching the FS size to one different from what was used for geometrical (gravitation, mechanical variations) calibration induced the most notable position changes of the x-ray FS, resulting in double-contouring artifacts and blurring of high-resolution 3D-CBCT images. Incorporating these shifts into a geometrical correction method effectively minimized these artifacts. Thermal drifts exhibited the second largest geometrical changes, comparable to FS size shifts across the thermal operating conditions of the x-ray system. The proposed thermal drift compensation markedly reduced thermal drift effects. Tube current and potential had little impact within the range of available tube currents, eliminating the need for compensation in current applications., Conclusions: Augmenting the geometrical calibration pipeline with proposed FS drift compensations yielded significant enhancements in image quality for high-resolution reconstructions. While compensation for thermal effects posed challenges, it proved achievable. The roles of tube current and potential were found to be negligible., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Cone-beam CT (CBCT) with non-circular scanning orbits can improve image quality for 3D intraoperative image guidance. However, geometric calibration of such scans can be challenging. Existing methods typically require a prior image, specialized phantoms, presumed repeatable orbits, or long computation time., Purpose: We propose a novel fully automatic online geometric calibration algorithm that does not require prior knowledge of fiducial configuration. The algorithm is fast, accurate, and can accommodate arbitrary scanning orbits and fiducial configurations., Methods: The algorithm uses an automatic initialization process to eliminate human intervention in fiducial localization and an iterative refinement process to ensure robustness and accuracy. We provide a detailed explanation and implementation of the proposed algorithm. Physical experiments on a lab test bench and a clinical robotic C-arm scanner were conducted to evaluate spatial resolution performance and robustness under realistic constraints., Results: Qualitative and quantitative results from the physical experiments demonstrate high accuracy, efficiency, and robustness of the proposed method. The spatial resolution performance matched that of our existing benchmark method, which used a 3D-2D registration-based geometric calibration algorithm., Conclusions: We have demonstrated an automatic online geometric calibration method that delivers high spatial resolution and robustness performance. This methodology enables arbitrary scan trajectories and should facilitate translation of such acquisition methods in a clinical setting., (© 2024 American Association of Physicists in Medicine.)

Background: Cine magnetic resonance (MR) images have been used for real-time MR guided radiation therapy (MRgRT). However, the onboard MR systems with low-field strength face the problem of limited image quality., Purpose: To improve the quality of cine MR images in MRgRT using prior image information provided by the patient planning and positioning MR images., Methods: This study employed MR images from 18 pancreatic cancer patients who received MR-guided stereotactic body radiation therapy. Planning 3D MR images were acquired during the patient simulation, and positioning 3D MR images and 2D sagittal cine MR images were acquired before and during the beam delivery, respectively. A deep learning-based framework consisting of two cycle generative adversarial networks (CycleGAN), Denoising CycleGAN and Enhancement CycleGAN, was developed to establish the mapping between the 3D and 2D MR images. The Denoising CycleGAN was trained to first denoise the cine images using the time domain cine image series, and the Enhancement CycleGAN was trained to enhance the spatial resolution and contrast by taking advantage of the prior image information from the planning and positioning images. The denoising performance was assessed by signal-to-noise ratio (SNR), structural similarity index measure, peak SNR, blind/reference-less image spatial quality evaluator (BRISQUE), natural image quality evaluator, and perception-based image quality evaluator scores. The quality enhancement performance was assessed by the BRISQUE and physician visual scores. In addition, the target contouring was evaluated on the original and processed images., Results: Significant differences were found for all evaluation metrics after Denoising CycleGAN processing. The BRISQUE and visual scores were also significantly improved after sequential Denoising and Enhancement CycleGAN processing. In target contouring evaluation, Dice similarity coefficient, centroid distance, Hausdorff distance, and average surface distance values were significantly improved on the enhanced images. The whole processing time was within 20 ms for a typical input image size of 512 × 512., Conclusion: Taking advantage of the prior high-quality positioning and planning MR images, the deep learning-based framework enhanced the cine MR image quality significantly, leading to improved accuracy in automatic target contouring. With the merits of both high computational efficiency and considerable image quality enhancement, the proposed method may hold important clinical implication for real-time MRgRT., (© 2023 American Association of Physicists in Medicine.)

Background: Minimally invasive procedures usually require navigating a microcatheter and guidewire through endoluminal structures such as blood vessels and airways to sites of the disease. For numerous clinical applications, two-dimensional (2D) fluoroscopy is the primary modality used for real-time image guidance during navigation. However, 2D imaging can pose challenges for navigation in complex structures. Real-time 3D visualization of devices within the anatomic context could provide considerable benefits for these procedures. Continuous-sweep limited angle (CLA) fluoroscopy has recently been proposed to provide a compromise between conventional rotational 3D acquisitions and real-time fluoroscopy., Purpose: The purpose of this work was to develop and evaluate a noniterative 3D device reconstruction approach for CLA fluoroscopy acquisitions, which takes into account endoluminal topology to avoid impossible paths between disconnected branches., Methods: The algorithm relies on a static 3D roadmap (RM) of vessels or airways, which may be generated from conventional cone beam CT (CBCT) acquisitions prior to navigation. The RM is converted to a graph representation describing its topology. During catheter navigation, the device is segmented from the live 2D projection images using a deep learning approach from which the centerlines are extracted. Rays from the focal spot to detector pixels representing 2D device points are identified and intersections with the RM are computed. Based on the RM graph, a subset of line segments is selected as candidates to exclude device paths through disconnected branches of the RM. Depth localization for each point along the device is then performed by finding the point closest to the previous 3D reconstruction along the candidate segments. This process is repeated as the projection angle changes for each CLA image frame. The approach was evaluated in a phantom study in which a catheter and guidewire were navigated along five pathways within a complex vessel phantom. The result was compared to static cCBCT acquisitions of the device in the final position., Results: The average root mean squared 3D distance between CLA reconstruction and reference centerline was 1.87 ± 0.30 $1.87 \pm 0.30$ mm. The Euclidean distance at the device tip was 2.92 ± 2.35 $2.92 \pm 2.35$ mm. The correct pathway was identified during reconstruction in 100 % $100\%$ of frames ( n = 1475 $n=1475$ ). The percentage of 3D device points reconstructed inside the 3D roadmap was 91.83 ± 2.52 % $91.83 \pm 2.52\%$ with an average distance of 0.62 ± 0.30 $0.62 \pm 0.30$ mm between the device points outside the roadmap and the nearest point within the roadmap., Conclusions: This study demonstrates the feasibility of reconstructing curvilinear devices such as catheters and guidewires during endoluminal procedures including intravascular and transbronchial interventions using a noniterative reconstruction approach for CLA fluoroscopy. This approach could improve device navigation in cases where the structure of vessels or airways is complex and includes overlapping branches., (© 2024 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: High-resolution magnetic resonance imaging (MRI) with excellent soft-tissue contrast is a valuable tool utilized for diagnosis and prognosis. However, MRI sequences with long acquisition time are susceptible to motion artifacts, which can adversely affect the accuracy of post-processing algorithms., Purpose: This study proposes a novel retrospective motion correction method named "motion artifact reduction using conditional diffusion probabilistic model" (MAR-CDPM). The MAR-CDPM aimed to remove motion artifacts from multicenter three-dimensional contrast-enhanced T1 magnetization-prepared rapid acquisition gradient echo (3D ceT1 MPRAGE) brain dataset with different brain tumor types., Materials and Methods: This study employed two publicly accessible MRI datasets: one containing 3D ceT1 MPRAGE and 2D T2-fluid attenuated inversion recovery (FLAIR) images from 230 patients with diverse brain tumors, and the other comprising 3D T1-weighted (T1W) MRI images of 148 healthy volunteers, which included real motion artifacts. The former was used to train and evaluate the model using the in silico data, and the latter was used to evaluate the model performance to remove real motion artifacts. A motion simulation was performed in k-space domain to generate an in silico dataset with minor, moderate, and heavy distortion levels. The diffusion process of the MAR-CDPM was then implemented in k-space to convert structure data into Gaussian noise by gradually increasing motion artifact levels. A conditional network with a Unet backbone was trained to reverse the diffusion process to convert the distorted images to structured data. The MAR-CDPM was trained in two scenarios: one conditioning on the time step t $t$ of the diffusion process, and the other conditioning on both t $t$ and T2-FLAIR images. The MAR-CDPM was quantitatively and qualitatively compared with supervised Unet, Unet conditioned on T2-FLAIR, CycleGAN, Pix2pix, and Pix2pix conditioned on T2-FLAIR models. To quantify the spatial distortions and the level of remaining motion artifacts after applying the models, quantitative metrics were reported including normalized mean squared error (NMSE), structural similarity index (SSIM), multiscale structural similarity index (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multiscale gradient magnitude similarity deviation (MS-GMSD). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference between the models where p-value  < 0.05 $ &lt; 0.05$ was considered statistically significant., Results: Qualitatively, MAR-CDPM outperformed these methods in preserving soft-tissue contrast and different brain regions. It also successfully preserved tumor boundaries for heavy motion artifacts, like the supervised method. Our MAR-CDPM recovered motion-free in silico images with the highest PSNR and VIF for all distortion levels where the differences were statistically significant (p-values < 0.05 $&lt; 0.05$ ). In addition, our method conditioned on t and T2-FLAIR outperformed (p-values < 0.05 $&lt; 0.05$ ) other methods to remove motion artifacts from the in silico dataset in terms of NMSE, MS-SSIM, SSIM, and MS-GMSD. Moreover, our method conditioned on only t outperformed generative models (p-values < 0.05 $&lt; 0.05$ ) and had comparable performances compared with the supervised model (p-values > 0.05 $&gt; 0.05$ ) to remove real motion artifacts., Conclusions: The MAR-CDPM could successfully remove motion artifacts from 3D ceT1 MPRAGE. It is particularly beneficial for elderly who may experience involuntary movements during high-resolution MRI imaging with long acquisition times., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: 2D angiographic parametric imaging (API) quantitatively extracts imaging biomarkers related to contrast flow and is conventionally applied to 2D digitally subtracted angiograms (DSA's). In the interventional suite, API is typically performed using 1-2 projection views and is limited by vessel overlap, foreshortening, and depth-integration of contrast motion., Purpose: This work explores the use of a pathlength-correction metric to overcome the limitations of 2D-API: the primary objective was to study the effect of converting 3D contrast flow to projected contrast flow using a simulated angiographic framework created with computational fluid dynamics (CFD) simulations, thereby removing acquisition variability., Methods: The pathlength-correction framework was applied to in-silico angiograms, generating a reference (i.e., ground-truth) volumetric contrast distribution in four patient-specific intracranial aneurysm geometries. Biplane projections of contrast flow were created from the reference volumetric contrast distributions, assuming a cone-beam geometry. A Parker-weighted reconstruction was performed to obtain a binary representation of the vessel structure in 3D. Standard ray tracing techniques were then used to track the intersection of a ray from the focal spot with each voxel of the reconstructed vessel wall to a pixel in the detector plane. The lengths of each ray through the 3D vessel lumen were then projected along each ray-path to create a pathlength-correction map, where the pixel intensity in the detector plane corresponds to the vessel width along each source-detector ray. By dividing the projection sequences with this correction map, 2D pathlength-corrected in-silico angiograms were obtained. We then performed voxel-wise (3D) API on the ground-truth contrast distribution and compared it to pixel-wise (2D) API, both with and without pathlength correction for each biplane view. The percentage difference (PD) between the resultant API biomarkers in each dataset were calculated within the aneurysm region of interest (ROI)., Results: Intensity-based API parameters, such as the area under the curve (AUC) and peak height (PH), exhibited notable changes in magnitude and spatial distribution following pathlength correction: these now accurately represent conservation of mass of injected contrast media within each arterial geometry and accurately reflect regions of stagnation and recirculation in each aneurysm ROI. Improved agreement was observed between these biomarkers in the pathlength-corrected biplane maps: the maximum PD within the aneurysm ROI is 3.3% with pathlength correction and 47.7% without pathlength correction. As expected, improved agreement with ROI-averaged ground-truth 3D counterparts was observed for all aneurysm geometries, particularly large aneurysms: the maximum PD for both AUC and PH was 5.8%. Temporal parameters (mean transit time, MTT, time-to-peak, TTP, time-to-arrival, TTA) remained unaffected after pathlength correction., Conclusions: This study indicates that the values of intensity-based API parameters obtained with conventional 2D-API, without pathlength correction, are highly dependent on the projection orientation, and uncorrected API should be avoided for hemodynamic analysis. The proposed metric can standardize 2D API-derived biomarkers independent of projection orientation, potentially improving the diagnostic value of all acquired 2D-DSA's. Integration of a pathlength correction map into the imaging process can allow for improved interpretation of biomarkers in 2D space, which may lead to improved diagnostic accuracy during procedures involving the cerebral vasculature., (© 2023 American Association of Physicists in Medicine.)

Objectives: To compare the accuracy of immediate implant placement of cylindrical implants (CI) and tapered implants (TI) of different lengths using a robotic dental implant system., Materials and Methods: CI and TI of three lengths (8, 10, and 12 mm) each were digitally planned and placed in a three-dimensional printed extraction socket model under robotic guidance. There were six groups with three samples in each group, resulting in a total of 18 samples. Implant angular deviation, platform point deviation (total, lateral, depth), and implant apical point deviation (total, lateral, depth) were recorded and compared between the different groups., Results: The angular deviations for CI 8 mm, CI 10 mm, CI 12 mm, TI 8 mm, TI 10 mm, and TI 12 mm were 1.32° ± 0.19°, 1.03° ± 0.56°, 1.31° ± 0.38°, 1.27° ± 0.64°, 1.10° ± 0.43° and 1.05° ± 0.45°, respectively. The total deviations of platform and apical points for CI 8 mm, CI 10 mm, CI 12 mm, TI 8 mm, TI 10 mm, and TI 12 mm were 0.79 ± 0.18 mm, 0.77 ± 0.33 mm; 0.64 ± 0.21 mm, 0.55 ± 0.17 mm; 0.64 ± 0.37 mm, 0.65 ± 0.34 mm; 0.68 ± 0.26 mm, 0.71 ± 0.20 mm; 0.70 ± 0.12 mm, 0.66 ± 0.23 mm; and 0.71 ± 0.15 mm, 0.77 ± 0.29 mm, respectively, and had no significant differences., Conclusions: Within the limitation of this study, acceptable accuracy can be achieved for both TI and CI using robotic systems. Our study demonstrated that the implant shape and length did not affect the accuracy of immediate implant placement under robotic guidance in vitro. However, further trials are required to confirm their efficacy in clinical practice., (© 2024 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Background: The distension properties of the vagina are critical to its function including support of surrounding organs, childbirth, and intercourse. It could be altered by many pathophysiological processes like pregnancy, radiotherapy, and reconstruction surgery. However, there are no clinically available diagnostic tools capable of quantifying the distension properties of the vagina., Purpose: A proof-of-concept study was designed to assess the feasibility of a novel three-dimensional (3D) ultrasound imaging technique that allows quantitative evaluation of the vagina under distension., Methods: Patients with symptomatic pelvic organ prolapse (POP) were recruited for the study. An ultrathin, oversized bag was inserted into the vagina and filled with water using a modified urodynamics system. The instilled water volume and intravaginal pressure were continuously recorded. At maximum vaginal capacity, 3D transintroital ultrasound of the distended vagina and surrounding pelvic structures was performed. Exams were performed in duplicate for each patient, two hours apart (round A and round B). Following the development of a 3D surface model of the distended vagina from each scan, several measurements were obtained, including cross-sectional area, anteroposterior (AP) length and lateral width in the plane of minimum hiatal dimensions (PMHD), AP and lateral diameter at the pubic symphysis (PS) level, maximum and minimum diameter, and maximum vertical length. To assess repeatability between measurements in two rounds, the coefficient of variation (CV) and the intraclass correlation coefficient (ICC) were calculated for each measurement. Correlations between physical measurements including the pelvic organ prolapse quantification (POP-Q) system and vaginal diameter measurements, and obtained metrics were also assessed., Results: Sixteen patients with POP (average age 69 years) completed both rounds of imaging. There was sufficient echogenicity on 3D transintroital ultrasound of the distended vaginal wall to establish boundaries for 3D surface models of the vagina. Overall, all metrics had good or excellent reliability (ICC = 0.77-0.93, p < 0.05; CV = 3%-18%) except maximum diameter, which demonstrated only moderate reliability (ICC = 0.67, p = 0.092). Strong correlations were found between physical exam measurements including D point of POP-Q, introitus diameter and lateral diameter at apex, and maximum vaginal capacity, maximum vertical length, lateral diameter at PS, minimum diameter, and distended PMHD measurements. The results demonstrated that this system could generate 3D models of the shape of the distended vagina and provide multiple metrics that could be reliably calculated from automated analyses of the models., Conclusions: A novel system for evaluation of the distension properties of the vagina was developed and preliminary evaluation was performed. This system may represent a technique for evaluation of the biomechanical and structural properties of the vagina., (© 2023 American Association of Physicists in Medicine.)

Background: High resolution imaging of the microvasculature plays an important role in both diagnostic and therapeutic applications in the brain. However, ultrasound pulse-echo sonography imaging the brain vasculatures has been limited to narrow acoustic windows and low frequencies due to the distortion of the skull bone, which sacrifices axial resolution since it is pulse length dependent., Purpose: To overcome the detect limit, a large aperture 256-module sparse hemispherical transmit/receive array was used to visualize the acoustic emissions of ultrasound-vaporized lipid-coated decafluorobutane nanodroplets flowing through tube phantoms and within rabbit cerebral vasculature in vivo via passive acoustic mapping and super resolution techniques., Methods: Nanodroplets were vaporized with 55 kHz burst-mode ultrasound (burst length = 145 μs, burst repetition frequency = 9-45 Hz, peak negative acoustic pressure = 0.10-0.22 MPa), which propagates through overlying tissues well without suffering from severe distortions. The resulting emissions were received at a higher frequency (612 or 1224 kHz subarray) to improve the resulting spatial resolution during passive beamforming. Normal resolution three-dimensional images were formed using a delay, sum, and integrate beamforming algorithm, and super-resolved images were extracted via Gaussian fitting of the estimated point-spread-function to the normal resolution data., Results: With super resolution techniques, the mean lateral (axial) full-width-at-half-maximum image intensity was 16 ± 3 (32 ± 6) μm, and 7 ± 1 (15 ± 2) μm corresponding to ∼1/67 of the normal resolution at 612 and 1224 kHz, respectively. The mean positional uncertainties were ∼1/350 (lateral) and ∼1/180 (axial) of the receive wavelength in water. In addition, a temporal correlation between nanodroplet vaporization and the transmit waveform shape was observed, which may provide the opportunity to enhance the signal-to-noise ratio in future studies., Conclusions: Here, we demonstrate the feasibility of vaporizing nanodroplets via low frequency ultrasound and simultaneously performing spatial mapping via passive beamforming at higher frequencies to improve the resulting spatial resolution of super resolution imaging techniques. This method may enable complete four-dimensional vascular mapping in organs where a hemispherical array could be positioned to surround the target, such as the brain, breast, or testicles., (© 2023 American Association of Physicists in Medicine.)

Background: The use of iodine-based contrast agent for better delineation of tumors in breast CT (bCT) has been shown to be compelling, similar to the tumor enhancement in contrast-enhanced breast MRI. Contrast-enhanced bCT (CE-bCT) is a relatively new tool, and a structured evaluation of different imaging parameters at play has yet to be conducted. In this investigation, data sets of acquired bCT images from 253 patients imaged at our institution were used in concert with simulated mathematically inserted spherical contrast-enhanced lesions to study the role of contrast enhancement on detectability., Purpose: To quantitatively evaluate the improvement in lesion detectability due to contrast enhancement across lesion diameter, section thickness, view plane, and breast density using a pre-whitened matched filter (PWMF) model observer., Methods: The relationship between iodine concentration and Hounsfield units (HU) was measured using spectral modeling. The lesion enhancement from clinical CE-bCT images in 22 patients was evaluated, and the average contrast enhancement (ΔHU) was determined. Mathematically generated spherical mass lesions of varying diameters (1, 3, 5, 9, 11, 15 mm) and contrast enhancement levels (0, 0.25, 0.50, 0.75, 1) were inserted at random locations in 253 actual patient bCT datasets. Images with varying thicknesses (0.4-19.8 mm) were generated by slice averaging, and the role of view plane (coronal and axial planes) was studied. A PWMF was used to generate receiver operating characteristic (ROC) curves across parameters of lesion diameter, contrast enhancement, section thickness, view plane, and breast density. The area under the ROC curve (AUC) was used as the primary performance metric, generated from over 90,000 simulated lesions., Results: An average 20% improvement (ΔAUC = 0.1) in lesion detectability due to contrast enhancement was observed across lesion diameter, section thickness, breast density, and view plane. A larger improvement was observed when stratifying patients based on breast density. For patients with VGF ≤ 40%, detection performance improved up to 20% (until AUC →1), and for patients with denser breasts (VGF > 40%), detection performance improved more drastically, ranging from 20% to 80% for 1- and 5-mm lesions. For the 1 mm lesion, detection performance raised slightly at the 1.2 mm section thickness before falling off as thickness increased. For larger lesions, detection performance was generally unaffected as section thickness increased up until it reached 5.8 mm, where performance began to decline. Detection performance was higher in the axial plane compared to the coronal plane for smaller lesions and thicker sections., Conclusions: For emerging diagnostic tools like CE-bCT, it is important to optimize imaging protocols for lesion detection. In this study, we found that intravenous contrast can be used to detect small lesions in dense breasts. Optimal section thickness for detectability has dependencies on breast density and lesion size, therefore, display thickness should be adjusted in real-time using display software. These findings may be useful for the development of CE-bCT as well as other x-ray-based breast imaging modalities., (© 2023 American Association of Physicists in Medicine.)

Background: MRI has a rapidly growing role in radiation therapy (RT) for treatment planning, real-time image guidance, and beam gating (e.g., MRI-Linac). Free-breathing 4D-MRI is desirable in respiratory motion management for therapy. Moreover, high-quality 3D-MRIs without motion artifacts are needed to delineate lesions. Existing MRI methods require multiple scans with lengthy acquisition times or are limited by low spatial resolution, contrast, and signal-to-noise ratio., Purpose: We developed a novel method to obtain motion-resolved 4D-MRIs and motion-integrated 3D-MRI reconstruction using a single rapid (35-45 s scan on a 0.35 T MRI-Linac., Methods: Golden-angle radial stack-of-stars MRI scans were acquired from a respiratory motion phantom and 12 healthy volunteers (n = 12) on a 0.35 T MRI-Linac. A self-navigated method was employed to detect respiratory motion using 2000 (acquisition time = 5-7 min) and the first 200 spokes (acquisition time = 35-45 s). Multi-coil non-uniform fast Fourier transform (MCNUFFT), compressed sensing (CS), and deep-learning Phase2Phase (P2P) methods were employed to reconstruct motion-resolved 4D-MRI using 2000 spokes (MCNUFFT2000) and 200 spokes (CS200 and P2P200). Deformable motion vector fields (MVFs) were computed from the 4D-MRIs and used to reconstruct motion-corrected 3D-MRIs with the MOtion Transformation Integrated forward-Fourier (MOTIF) method. Image quality was evaluated quantitatively using the structural similarity index measure (SSIM) and the root mean square error (RMSE), and qualitatively in a blinded radiological review., Results: Evaluation using the respiratory motion phantom experiment showed that the proposed method reversed the effects of motion blurring and restored edge sharpness. In the human study, P2P200 had smaller inaccuracy in MVFs estimation than CS200. P2P200 had significantly greater SSIMs (p < 0.0001) and smaller RMSEs (p < 0.001) than CS200 in motion-resolved 4D-MRI and motion-corrected 3D-MRI. The radiological review found that MOTIF 3D-MRIs using MCNUFFT2000 exhibited the highest image quality (scoring > 8 out of 10), followed by P2P200 (scoring > 5 out of 10), and then motion-uncorrected (scoring < 3 out of 10) in sharpness, contrast, and artifact-freeness., Conclusions: We have successfully demonstrated a method for respiratory motion management for MRI-guided RT. The method integrated self-navigated respiratory motion detection, deep-learning P2P 4D-MRI reconstruction, and a motion integrated reconstruction (MOTIF) for 3D-MRI using a single rapid MRI scan (35-45 s) on a 0.35 T MRI-Linac system., (© 2023 American Association of Physicists in Medicine.)

Background: As an emerging hybrid imaging modality, microwave-induced thermoacoustic imaging (MITAI) provides high contrast and deep tissue penetration, and has been extensively applied in cancer diagnosis, arthritis detection, and brain research. However, the previous studies had a limited spatial resolution of about 0.45-1.5 mm., Purpose: Here, we describe a microwave-induced thermoacoustic microscopy (MITAM) system to help overcome the resolution limitation of current MITAI to image more subtle tissue features. On this basis, this paper applies MITAM to the thin skin and to demonstrate the potential of MITAM in detecting scleroderma., Methods: To achieve high resolution, short pulse width microwave (pulse width: 70 ns) and high-frequency ultrasonic point-focused transducer (center frequency: 25 MHz) were used to build the MITAM system. Two parallel copper wires with a diameter of 90 μm in the X/Y plane and Y/Z plane were imaged to estimate X/Y/Z resolution. Nine Balb/c mice were randomly divided into three groups and injected with different concentrations of bleomycin to induce scleroderma models. Their ex vivo skins were then imaged by our MITAM system. Visual observations were performed on the 3-dimensional skins MITAM images. And the mean value, Standard deviation, quartile distance, and signal-to-noise ratio were calculated to verify the results of the qualitative observations. Hematoxylin-Eosin (HE) and Masson staining were used to validate the findings of the MITAM., Results: The thickness of each imaged skin was measured to be about 450 μm. As an organ composed of multiple layers of tissues, the skin needs to be imaged at high resolution for the detection of related diseases. The results obtained showed that the improved resolution (68 μm in the Z-axis and 135 μm in the X-axis/Y-axis) of MITAM over conventional MITAI allowed us to differentiate scleroderma skins from normal skins and to identify the severity of scleroderma skins, consistent with the pathological findings of these skins., Conclusions: The preliminary results obtained indicate that the MITAM can relieve the resolution limitation of traditional MITAI and has the potential to detection scleroderma. However, the transmission-type MITAM mentioned in this paper is difficult to image in vivo due to the narrow area between the antenna and the transducer. In the future, a reflective scanning MITAM will be constructed to detect scleroderma in vivo., (© 2023 American Association of Physicists in Medicine.)

Background: The absence of coronary artery calcium (CAC) measured via CT is associated with very favorable prognosis, and current guidelines recommend low-density lipoprotein cholesterol (LDL-c) lowering therapy for individuals with any CAC. This motivates early detection of small granules of CAC; however, calcium scan sensitivity for detecting very low levels of calcium has not been quantified., Purpose: In this work, the size limit of detectability of small calcium hydroxyapatite (CaHA) granules with clinical CAC scanning was assessed using validated simulations., Methods: CT projections of digital 3D mathematical phantoms containing small CaHA granules were simulated analytically; images were reconstructed using a filter designed to reproduce the point spread function of a specific commercial scanner, and a relationship of HU number versus diameter was derived. These simulation results were validated with experimental measurements of HU versus diameter from phantoms containing small granules of CaHA on a GE Revolution CT scanner in the clinic; ground truth measurements of the CaHA granule diameters were obtained using a Zeiss Xradia 510 Versa high-resolution 3D micro-CT imaging system. Using experimental measurements on the clinical CT scanner, detectability was quantified with a detectability index (d') using a non-prewhitened matched filter. The effect of changes to reconstruction slice thickness and reconstruction kernel on granule detectability was evaluated., Results: Under typical clinical calcium scanning and reconstruction conditions, the minimum detectable diameter of a simulated spherical calcium granule with a clinically relevant CaHA density was 0.76 mm. The minimum detectable volume was 2.4 times smaller on images reconstructed at a slice thickness of 0.625 mm compared to 2.5 mm. The detectability index d' increased by a factor of 1.7 when images were reconstructed with 0.625 mm slices compared to 2.5 mm slices. d' did not change when images were reconstructed with the high-resolution BONE filter compared to the less sharp STANDARD resolution filter on the GE Revolution CT., Conclusions: We have quantified detectability versus size of small calcium granules at the resolution limit of a widely available clinical CT scanner. Detectability increased significantly with reduced slice thickness and did not change with a sharper reconstruction kernel. The simulation can be used to calculate the trade-off between dose and CAC detectability., (© 2023 American Association of Physicists in Medicine.)

Background: The fusion of computed tomography (CT) and ultrasound (US) image can enhance lesion detection ability and improve the success rate of liver interventional radiology. The image-based fusion methods encounter the challenge of registration initialization due to the random scanning pose and limited field of view of US. Existing automatic methods those used vessel geometric information and intensity-based metric are sensitive to parameters and have low success rate. The learning-based methods require a large number of registered datasets for training., Purpose: The aim of this study is to provide a fully automatic and robust US-3D CT registration method without registered training data and user-specified parameters assisted by the revolutionary deep learning-based segmentation, which can further be used for preparing training samples for the study of learning-based methods., Methods: We propose a fully automatic CT-3D US registration method by two improved registration metrics. We propose to use 3D U-Net-based multi-organ segmentation of US and CT to assist the conventional registration. The rigid transform is searched in the space of any paired vessel bifurcation planes where the best transform is decided by a segmentation overlap metric, which is more related to the segmentation precision than Dice coefficient. In nonrigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy US voxels to guide the B-spline transform registration. We evaluate our method on 42 paired CT-3D US datasets scanned with two different US devices from two hospitals. We compared our methods with other exsiting methods with both quantitative measures of target registration error (TRE) and the Jacobian determinent with paired t-test and qualitative registration imaging results., Results: The results show that our method achieves fully automatic rigid registration TRE of 4.895 mm, deformable registration TRE of 2.995 mm in average, which outperforms state-of-the-art automatic linear methods and nonlinear registration metrics with paired t-test's p value less than 0.05. The proposed overlap metric achieves better results than self similarity description (SSD), edge matching (EM), and block matching (BM) with p values of 1.624E-10, 4.235E-9, and 0.002, respectively. The proposed hybrid edge and context-based metric outperforms context-only, edge-only, and intensity statistics-only-based metrics with p values of 0.023, 3.81E-5, and 1.38E-15, respectively. The 3D US segmentation has achieved mean Dice similarity coefficient (DSC) of 0.799, 0.724, 0.788, and precision of 0.871, 0.769, 0.862 for gallbladder, vessel, and branch vessel, respectively., Conclusions: The deep learning-based US segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient-based metrics, hybrid context, and edge image similarity metric contribute to robust and accurate registration., (© 2023 American Association of Physicists in Medicine.)

Background: Transperineal ultrasound (TPUS) is a valuable imaging tool for evaluating patients with pelvic floor disorders, including pelvic organ prolapse (POP). Currently, measurements of anatomical structures in the mid-sagittal plane of 2D and 3D US volumes are obtained manually, which is time-consuming, has high intra-rater variability, and requires an expert in pelvic floor US interpretation. Manual segmentation and biometric measurement can take 15 min per 2D mid-sagittal image by an expert operator. An automated segmentation method would provide quantitative data relevant to pelvic floor disorders and improve the efficiency and reproducibility of segmentation-based biometric methods., Purpose: Develop a fast, reproducible, and automated method of acquiring biometric measurements and organ segmentations from the mid-sagittal plane of female 3D TPUS volumes., Methods: Our method used a nnU-Net segmentation model to segment the pubis symphysis, urethra, bladder, rectum, rectal ampulla, and anorectal angle in the mid-sagittal plane of female 3D TPUS volumes. We developed an algorithm to extract relevant biometrics from the segmentations. Our dataset included 248 3D TPUS volumes, 126/122 rest/Valsalva split, from 135 patients. System performance was assessed by comparing the automated results with manual ground truth data using the Dice similarity coefficient (DSC) and average absolute difference (AD). Intra-class correlation coefficient (ICC) and time difference were used to compare reproducibility and efficiency between manual and automated methods respectively. High ICC, low AD and reduction in time indicated an accurate and reliable automated system, making TPUS an efficient alternative for POP assessment. Paired t-test and non-parametric Wilcoxon signed-rank test were conducted, with p < 0.05 determining significance., Results: The nnU-Net segmentation model reported average DSC and p values (in brackets), compared to the next best tested model, of 87.4% (<0.0001), 68.5% (<0.0001), 61.0% (0.1), 54.6% (0.04), 49.2% (<0.0001) and 33.7% (0.02) for bladder, rectum, urethra, pubic symphysis, anorectal angle, and rectal ampulla respectively. The average ADs for the bladder neck position, bladder descent, rectal ampulla descent and retrovesical angle were 3.2 mm, 4.5 mm, 5.3 mm and 27.3°, respectively. The biometric algorithm had an ICC > 0.80 for the bladder neck position, bladder descent and rectal ampulla descent when compared to manual measurements, indicating high reproducibility. The proposed algorithms required approximately 1.27 s to analyze one image. The manual ground truths were performed by a single expert operator. In addition, due to high operator dependency for TPUS image collection, we would need to pursue further studies with images collected from multiple operators., Conclusions: Based on our search in scientific databases (i.e., Web of Science, IEEE Xplore Digital Library, Elsevier ScienceDirect and PubMed), this is the first reported work of an automated segmentation and biometric measurement system for the mid-sagittal plane of 3D TPUS volumes. The proposed algorithm pipeline can improve the efficiency (1.27 s compared to 15 min manually) and has high reproducibility (high ICC values) compared to manual TPUS analysis for pelvic floor disorder diagnosis. Further studies are needed to verify this system's viability using multiple TPUS operators and multiple experts for performing manual segmentation and extracting biometrics from the images., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Vascular diseases are often treated minimally invasively. The interventional material (stents, guidewires, etc.) used during such percutaneous interventions are visualized by some form of image guidance. Today, this image guidance is usually provided by 2D X-ray fluoroscopy, that is, a live 2D image. 3D X-ray fluoroscopy, that is, a live 3D image, could accelerate existing and enable new interventions. However, existing algorithms for the 3D reconstruction of interventional material require either too many X-ray projections and therefore dose, or are only capable of reconstructing single, curvilinear structures., Purpose: Using only two new X-ray projections per 3D reconstruction, we aim to reconstruct more complex arrangements of interventional material than was previously possible., Methods: This is achieved by improving a previously presented deep learning-based reconstruction pipeline, which assumes that the X-ray images are acquired by a continuously rotating biplane system, in two ways: (a) separation of the reconstruction of different object types, (b) motion compensation using spatial transformer networks., Results: Our pipeline achieves submillimeter accuracy on measured data of a stent and two guidewires inside an anthropomorphic phantom with respiratory motion. In an ablation study, we find that the aforementioned algorithmic changes improve our two figures of merit by 75 % (1.76 mm → 0.44 mm) and 59 % (1.15 mm → 0.47 mm) respectively. A comparison of our measured dose area product (DAP) rate to DAP rates of 2D fluoroscopy indicates a roughly similar dose burden., Conclusions: This dose efficiency combined with the ability to reconstruct complex arrangements of interventional material makes the presented algorithm a promising candidate to enable 3D fluoroscopy., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Respiratory-resolved four-dimensional magnetic resonance imaging (4D-MRI) provides essential motion information for accurate radiation treatments of mobile tumors. However, obtaining high-quality 4D-MRI suffers from long acquisition and reconstruction times., Purpose: To develop a deep learning architecture to quickly acquire and reconstruct high-quality 4D-MRI, enabling accurate motion quantification for MRI-guided radiotherapy (MRIgRT)., Methods: A small convolutional neural network called MODEST is proposed to reconstruct 4D-MRI by performing a spatial and temporal decomposition, omitting the need for 4D convolutions to use all the spatio-temporal information present in 4D-MRI. This network is trained on undersampled 4D-MRI after respiratory binning to reconstruct high-quality 4D-MRI obtained by compressed sensing reconstruction. The network is trained, validated, and tested on 4D-MRI of 28 lung cancer patients acquired with a T1-weighted golden-angle radial stack-of-stars (GA-SOS) sequence. The 4D-MRI of 18, 5, and 5 patients were used for training, validation, and testing. Network performances are evaluated on image quality measured by the structural similarity index (SSIM) and motion consistency by comparing the position of the lung-liver interface on undersampled 4D-MRI before and after respiratory binning. The network is compared to conventional architectures such as a U-Net, which has 30 times more trainable parameters., Results: MODEST can reconstruct high-quality 4D-MRI with higher image quality than a U-Net, despite a thirty-fold reduction in trainable parameters. High-quality 4D-MRI can be obtained using MODEST in approximately 2.5 min, including acquisition, processing, and reconstruction., Conclusion: High-quality accelerated 4D-MRI can be obtained using MODEST, which is particularly interesting for MRIgRT., (© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Background: Accurate segmentation of organs has a great significance for clinical diagnosis, but it is still hard work due to the obscure imaging boundaries caused by tissue adhesion on medical images. Based on the image continuity in medical image volumes, segmentation on these slices could be inferred from adjacent slices with a clear organ boundary. Radiologists can delineate a clear organ boundary by observing adjacent slices., Purpose: Inspired by the radiologists' delineating procedure, we design an organ segmentation model based on boundary information of adjacent slices and a human-machine interactive learning strategy to introduce clinical experience., Methods: We propose an interactive organ segmentation method for medical image volume based on Graph Convolution Network (GCN) called Surface-GCN. First, we propose a Surface Feature Extraction Network (SFE-Net) to capture surface features of a target organ, and supervise it by a Mini-batch Adaptive Surface Matching (MBASM) module. Then, to predict organ boundaries precisely, we design an automatic segmentation module based on a Surface Convolution Unit (SCU), which propagates information on organ surfaces to refine the generated boundaries. In addition, an interactive segmentation module is proposed to learn radiologists' experience of interactive corrections on organ surfaces to reduce interaction clicks., Results: We evaluate the proposed method on one prostate MR image dataset and two abdominal multi-organ CT datasets. The experimental results show that our method outperforms other state-of-the-art methods. For prostate segmentation, the proposed method conducts a DSC score of 94.49% on PROMISE12 test dataset. For abdominal multi-organ segmentation, the proposed method achieves DSC scores of 95, 91, 95, and 88% for the left kidney, gallbladder, spleen, and esophagus, respectively. For interactive segmentation, the proposed method reduces 5-10 interaction clicks to reach the same accuracy., Conclusions: To overcome the medical organ segmentation challenge, we propose a Graph Convolutional Network called Surface-GCN by imitating radiologist interactions and learning clinical experience. On single and multiple organ segmentation tasks, the proposed method could obtain more accurate segmentation boundaries compared with other state-of-the-art methods., (© 2023 American Association of Physicists in Medicine.)

Background: In the brain tumor magnetic resonance image (MRI) segmentation, although the 3D convolution networks (CNNs) has achieved state-of-the-art results, the class and hard-voxel imbalances in the 3D images have not been well addressed. Voxel independent losses are dependent on the setting of class weights for the class imbalance issue, and are hard to assign each class equally. Region-related losses cannot correctly focus on hard voxels dynamically and not be robust to misclassification of small structures. Meanwhile, repeatedly training on the additional hard samples augmented by existing methods would bring more class imbalance, overfitting and incorrect knowledge learning to the model., Purpose: A novel region-related loss with balanced dynamic weighting while alleviating the sensitivity to small structures is necessary. In addition, we need to increase the diversity of hard samples in the training to improve the performance of model., Methods: The proposed Region-related Focal Loss (RFL) reshapes standard Dice Loss (DL) by up-weighting the loss assigned to hard-classified voxels. Compared to DL, RFL adaptively modulate its gradient with an invariant focalized point that voxels with lower-confidence than it would achieve a larger gradient, and higher-confidence voxels would get a smaller gradient. Meanwhile, RFL can adjust the parameters to set where and how much the network is focused. In addition, an Intra-classly Transformed Augmentation network (ITA-NET) is proposed to increase the diversity of hard samples, in which the 3D registration network and intra-class transfer layer are used to transform the shape and intensity respectively. A selective hard sample mining(SHSM) strategy is used to train the ITA-NET for avoiding excessive class imbalance. Source code (in Tensorflow) is available at: https://github.com/lb-whu/RFL&#95;ITA., Results: The experiments are carried out on public data set: Brain Tumor Segmentation Challenge 2020 (BratS2020). Experiments with BraTS2020 online validation set show that proposed methods achieve an average Dice scores of 0.905, 0.821, and 0.806 for whole tumor (WT), tumor core (TC) and enhancing tumor (ET), respectively. Compared with DL (baseline), the proposed RFL significantly improves the Dice scores by an average of 1%, and for the small region ET it can even increase by 3%. And the proposed method combined with ITA-NET improves the Dice scores of ET and TC by 5% and 3% respectively., Conclusions: The proposed RFL can converge with a invariant focalized point in the training of segmentation network, thus effectively alleviating the hard-voxel imbalance in brain tumor MRI segmentation. The negative region term of RFL can effectively reduce the sensitivity of the segmentation model to the misclassification of small structures. The proposed ITA-NET can increase the diversity of hard samples by transforming their shape and transfer their intra-class intensity, thereby effectively improving the robustness of the segmentation network to hard samples., (© 2023 American Association of Physicists in Medicine.)

Image quality models based on cascaded systems analysis and task-based imaging performance were an important aspect of the emergence of 2D and 3D digital x-ray systems over the last 25 years. This perspective vignette offers cursory review of such developments and personal insights that may not be obvious within previously published scientific literature. The vignette traces such models to the mid-1990s, when flat-panel x-ray detectors were emerging as a new base technology for digital radiography and benefited from the rigorous, objective characterization of imaging performance gained from such models. The connection of models for spatial resolution and noise to spatial-frequency-dependent descriptors of imaging task provided a useful framework for system optimization that helped to accelerate the development of new technologies to first clinical use. Extension of the models to new technologies and applications is also described, including dual-energy imaging, photon-counting detectors, phase contrast imaging, tomosynthesis, cone-beam CT, 3D image reconstruction, and image registration., (© 2022 American Association of Physicists in Medicine.)

Purpose: Respiration has a major impact on the accuracy of radiation treatment for thorax and abdominal tumours. Instantaneous volumetric imaging could provide precise knowledge of tumour and normal organs' three-dimensional (3D) movement, which is the key to reducing the negative effect of breathing motion. Therefore, this study proposed a real-time 3D MRI reconstruction method from cine-MRI using an unsupervised network., Methods and Materials: Cine-MRI and setup 3D-MRI from eight patients with liver cancer were utilized to establish and validate the deep learning network for 3D-MRI reconstruction. Unlike previous methods that required 4D-MRI for network training, the proposed method utilized a reference 3D-MRI and cine-MRI to generate the training data. Then, a network was trained in an unsupervised manner to estimate the relationship between the cine-MRI acquired on coronal plane and deformation vector field (DVF) that describes the patient's breathing motion. After the training process, the coronal cine-MRI were inputted into the network, and the corresponding DVF was obtained. By wrapping the reference 3D-MRI with the generated DVF, the 3D-MRI could be reconstructed., Results: The reconstructed 3D-MRI slices were compared with the corresponding phase-sorted cine-MRI using dice similarity coefficients (DSCs) of liver contours and blood vessel localization error. In all patients, the liver DSC had mean value >96.1% and standard deviation < 1.3%; the blood vessel localization error had mean value <2.6 mm, and standard deviation was <2.0 mm. Moreover, the time for 3D-MRI reconstruction was approximately 100 ms. These results indicated that the proposed method could accurately reconstruct the 3D-MRI in real time., Conclusions: The proposed method could accurately reconstruct the 3D-MRI from cine-MRI in real time. This method has great potential in improving the accuracy of radiotherapy for moving tumours., (© 2022 American Association of Physicists in Medicine.)

Background: Magnetic particle imaging (MPI) is a novel tomographic imaging modality that scans the distribution of superparamagnetic iron oxide nanoparticles. However, it is time-consuming to scan multiview two-dimensional (2D) projections for three-dimensional (3D) reconstruction in projection MPI, such as computed tomography (CT). An intuitive idea is to use the sparse-view projections for reconstruction to improve the temporal resolution. Tremendous progress has been made toward addressing the sparse-view problem in CT, because of the availability of large data sets. For the novel tomography of MPI, to the best of our knowledge, studies on the sparse-view problem have not yet been reported., Purpose: The acquisition of multiview projections for 3D MPI imaging is time-consuming. Our goal is to only acquire sparse-view projections for reconstruction to improve the 3D imaging temporal resolution of projection MPI., Methods: We propose to address the sparse-view problem in projection MPI by generating novel projections. The data set we constructed consists of three parts: simulation data set (including 3000 3D data), four phantoms data, and an in vivo mouse data. The simulation data set is used to train and validate the network, and the phantoms and in vivo mouse data are used to test the network. When the number of novel generated projections meets the requirements of filtered back projection, the streaking artifacts will be absent from MPI tomographic imaging. Specifically, we propose a projection generative network (PGNet), that combines an attention mechanism, adversarial training strategy, and a fusion loss function and can generate novel projections based on sparse-view real projections. To the best of our knowledge, we are the first to propose a deep learning method to attempt to overcome the sparse-view problem in projection MPI., Results: We compare our method with several sparse-view methods on phantoms and in vivo mouse data and validate the advantages and effectiveness of our proposed PGNet. Our proposed PGNet enables the 3D imaging temporal resolution of projection MPI to be improved by 6.6 times, while significantly suppressing the streaking artifacts., Conclusion: We proposed a deep learning method operated in projection domain to address the sparse-view reconstruction of MPI, and the data scarcity problem in projection MPI reconstruction is alleviated by constructing a sparse-dense simulated projection data set. By our proposed method, the number of acquisitions of real projections can be reduced. The advantage of our method is that it prevents the generation of streaking artifacts at the source. Our proposed sparse-view reconstruction method has great potential for application to time-sensitive in vivo 3D MPI imaging., (© 2022 American Association of Physicists in Medicine.)

Purpose: Early screening is crucial to improve the survival rate and recovery rate of lung cancer patients. Computer-aided diagnosis system (CAD) is a powerful tool to assist clinicians in early diagnosis. Lung nodules are characterized by spatial heterogeneity. However, many attempts use the two-dimensional multi-view (MV) framework to learn and simply integrate multiple view features. These methods suffer from the problems of not capturing the spatial characteristics effectively and ignoring the variability of multiple views. In this paper, we propose a three-dimensional MV convolutional neural network (3D MVCNN) framework and embed the squeeze-and-excitation (SE) module in it to further address the variability of each view in the MV framework., Methods: First, the 3D multiple view samples of lung nodules are extracted by the spatial sampling method, and a 3D CNN is established to extract 3D abstract features. Second, build a 3D MVCNN framework according to the 3D multiple view samples and 3D CNN. This framework can learn more features of different views of lung nodules, taking into account the characteristics of spatial heterogeneity of lung nodules. Finally, to further address the variability of each view in the MV framework, a 3D MVSECNN model is constructed by introducing a SE module in the feature fusion stage. For training and testing purposes we used independent subsets of the public LIDC-IDRI dataset., Results: For the LIDC-IDRI dataset, this study achieved 96.04% accuracy and 98.59% sensitivity in the binary classification, and 87.76% accuracy in the ternary classification, which was higher than other state-of-the-art studies. The consistency score of 0.948 between the model predictions and pathological diagnosis was significantly higher than that between the clinician's annotations and pathological diagnosis., Conclusions: The results show that our proposed method can effectively learn the spatial heterogeneity of nodules and solve the problem of multiple view variability. Moreover, the consistency analysis indicates that our method can provide clinicians with more accurate results of benign-malignant lung nodule classification for auxiliary diagnosis, which is important for assisting clinicians in clinical diagnosis., (© 2023 American Association of Physicists in Medicine.)