Search

Objective. The percutaneous puncture lung mass biopsy procedure, which relies on preoperative CT (Computed Tomography) images, is considered the gold standard for determining the benign or malignant nature of lung masses. However, the traditional lung puncture procedure has several issues, including long operation times, a high probability of complications, and high exposure to CT radiation for the patient, as it relies heavily on the surgeon's clinical experience. Approach. To address these problems, a multi-constrained objective optimization model based on clinical criteria for the percutaneous puncture lung mass biopsy procedure has been proposed. Additionally, based on fuzzy optimization, a multidimensional spatial Pareto front algorithm has been developed for optimal path selection. The algorithm finds optimal paths, which are displayed on 3D images, and provides reference points for clinicians' surgical path planning. Main results. To evaluate the algorithm's performance, 25 data sets collected from the Second People's Hospital of Zigong were used for prospective and retrospective experiments. The results demonstrate that 92% of the optimal paths generated by the algorithm meet the clinicians' surgical needs. Significance. The algorithm proposed in this paper is innovative in the selection of mass target point, the integration of constraints based on clinical standards, and the utilization of multi-objective optimization algorithm. Comparison experiments have validated the better performance of the proposed algorithm. From a clinical standpoint, the algorithm proposed in this paper has a higher clinical feasibility of the proposed pathway than related studies, which reduces the dependency of the physician's expertise and clinical experience on pathway planning during the percutaneous puncture lung mass biopsy procedure. [ABSTRACT FROM AUTHOR]

Objective. Multi-energy CT conducted by photon-counting detector has a wide range of applications, especially in multiple contrast agents imaging. However, static multi-energy (SME) CT imaging suffers from higher statistical noise because of increased energy bins with static energy thresholds. Our team has proposed a dynamic dual-energy (DDE) CT detector model and the corresponding iterative reconstruction algorithm to solve this problem. However, rigorous and detailed analysis of the statistical noise characterization in this DDE CT was lacked. Approach. Starting from the properties of the Poisson random variable, this paper analyzes the noise characterization of the DDE CT and compares it with the SME CT. It is proved that the multi-energy CT projections and reconstruction images calculated from the proposed DDE CT algorithm have less statistical noise than that of the SME CT. Main results. Simulations and experiments verify that the expectations of the multi-energy CT projections calculated from DDE CT are the same as those of the SME projections. Still, the variance of the former is smaller. We further analyze the convergence of the iterative DDE CT algorithm through simulations and prove that the derived noise characterization can be realized under different CT imaging configurations. Significance. The low statistical noise characteristics demonstrate the value of DDE CT imaging technology. [ABSTRACT FROM AUTHOR]

Reducing the radiation dose leads to the x-ray computed tomography (CT) images suffering from heavy noise and artifacts, which inevitably interferes with the subsequent clinic diagnostic and analysis. Leading works have explored diffusion models for low-dose CT imaging to avoid the structure degeneration and blurring effects of previous deep denoising models. However, most of them always begin their generative processes with Gaussian noise, which has little or no structure priors of the clean data distribution, thereby leading to long-time inference and unpleasant reconstruction quality. To alleviate these problems, this paper presents a Structure-Aware Diffusion model (SAD), an end-to-end self-guided learning framework for high-fidelity CT image reconstruction. First, SAD builds a nonlinear diffusion bridge between clean and degraded data distributions, which could directly learn the implicit physical degradation prior from observed measurements. Second, SAD integrates the prompt learning mechanism and implicit neural representation into the diffusion process, where rich and diverse structure representations extracted by degraded inputs are exploited as prompts, which provides global and local structure priors, to guide CT image reconstruction. Finally, we devise an efficient self-guided diffusion architecture using an iterative updated strategy, which further refines structural prompts during each generative step to drive finer image reconstruction. Extensive experiments on AAPM-Mayo and LoDoPaB-CT datasets demonstrate that our SAD could achieve superior performance in terms of noise removal, structure preservation, and blind-dose generalization, with few generative steps, even one step only. [ABSTRACT FROM AUTHOR]

Objective. Metal artifact reduction (MAR) has been a key issue in CT imaging. Recently, MAR methods based on deep learning have achieved promising results. However, when deploying deep learning-based MAR in real-world clinical scenarios, two prominent challenges arise. One limitation is the lack of paired training data in real applications, which limits the practicality of supervised methods. Another limitation is that image-domain methods suitable for more application scenarios are inadequate in performance while end-to-end approaches with better performance are only applicable to fan-beam CT due to large memory consumption. Approach. We propose a novel image-domain MAR method based on the generative adversarial network with variable constraints (MARGANVAC) to improve MAR performance. The proposed variable constraint is a kind of time-varying cost function that can relax the fidelity constraint at the beginning and gradually strengthen the fidelity constraint as the training progresses. To better deploy our image-domain supervised method into practical scenarios, we develop a transfer method to mimic the real metal artifacts by first extracting the real metal traces and then adding them to artifact-free images to generate paired training data. Main results. The effectiveness of the proposed method is validated in simulated fan-beam experiments and real cone-beam experiments. All quantitative and qualitative results demonstrate that the proposed method achieves superior performance compared with the competing methods. Significance. The MARGANVAC model proposed in this paper is an image-domain model that can be conveniently applied to various scenarios such as fan beam and cone beam CT. At the same time, its performance is on par with the cutting-edge dual-domain MAR approaches. In addition, the metal artifact transfer method proposed in this paper can easily generate paired data with real artifact features, which can be better used for model training in real scenarios. [ABSTRACT FROM AUTHOR]

Objective. Incorporating computed tomography (CT) reconstruction operators into differentiable pipelines has proven beneficial in many applications. Such approaches usually focus on the projection data and keep the acquisition geometry fixed. However, precise knowledge of the acquisition geometry is essential for high quality reconstruction results. In this paper, the differentiable formulation of fan-beam CT reconstruction is extended to the acquisition geometry. Approach. The CT fan-beam reconstruction is analytically derived with respect to the acquisition geometry. This allows to propagate gradient information from a loss function on the reconstructed image into the geometry parameters. As a proof-of-concept experiment, this idea is applied to rigid motion compensation. The cost function is parameterized by a trained neural network which regresses an image quality metric from the motion-affected reconstruction alone. Main results. The algorithm improves the structural similarity index measure (SSIM) from 0.848 for the initial motion-affected reconstruction to 0.946 after compensation. It also generalizes to real fan-beam sinograms which are rebinned from a helical trajectory where the SSIM increases from 0.639 to 0.742. Significance. Using the proposed method, we are the first to optimize an autofocus-inspired algorithm based on analytical gradients. Next to motion compensation, we see further use cases of our differentiable method for scanner calibration or hybrid techniques employing deep models. [ABSTRACT FROM AUTHOR]

Objective. Low-dose CT (LDCT) is an important research topic in the field of CT imaging because of its ability to reduce radiation damage in clinical diagnosis. In recent years, deep learning techniques have been widely applied in LDCT imaging and a large number of denoising methods have been proposed. However, One major challenge of supervised deep learning-based methods is the exactly geometric pairing of datasets with different doses. Therefore, the aim of this study is to develop an unsupervised learning-based LDCT imaging method to address the aforementioned challenges. Approach. In this paper, we propose an unsupervised learning-based dual-domain method for LDCT denoising, which consists of two stages: the first stage is projection domain denoising, in which the unsupervised learning method Noise2Self is applied to denoise the projection data with statistically independent and zero-mean noise. The second stage is an iterative enhancement approach, which combines the prior information obtained from the generative model with an iterative reconstruction algorithm to enhance the details of the reconstructed image. Main results. Experimental results show that our proposed method outperforms the comparison method in terms of denoising effect. Particularly, in terms of SSIM, the denoised results obtained using our method achieve the highest SSIM. Significance. In conclusion, our unsupervised learning-based method can be a promising alternative to the traditional supervised methods for LDCT imaging, especially when the availability of the labeled datasets is limited. [ABSTRACT FROM AUTHOR]

Background. Concern has been expressed regarding the risk of carcinogenesis from medical computed tomography (CT) radiation. Lowering radiation in CT without appropriate modifications often leads to severe noise-induced artifacts in the images. The utilization of deep learning (DL) techniques has achieved promising reconstruction performance in low-dose CT (LDCT) imaging. However, most DL-based algorithms require the pre-collection of a large set of image pairs (low-dose/standard-dose) and the training of networks in an end-to-end supervised manner. Meanwhile, securing such a large volume of paired, well-registered training data in clinical practice is challenging. Moreover, these algorithms often overlook the potential to utilize the abundant information in a large collection of LDCT-only images/sinograms. Methods. In this paper, we introduce a semi-supervised iterative adaptive network (SIA-Net) for LDCT imaging, utilizing both labeled and unlabeled sinograms in a cohesive network framework, integrating supervised and unsupervised learning processes. Specifically, the supervised process captures critical features (i.e. noise distribution and tissue characteristics) latent in the paired sinograms, while the unsupervised process effectively learns these features in the unlabeled low-dose sinograms, employing a conventional weighted least-squares model with a regularization term. Furthermore, the SIA-Net method is designed to adaptively transfer the learned feature distribution from the supervised to the unsupervised process, thereby obtaining a high-fidelity sinogram through iterative adaptive learning. Finally, high-quality CT images can be reconstructed from the refined sinogram using the filtered back-projection algorithm. Results. Experimental results on two clinical datasets indicate that the proposed SIA-Net method achieves competitive performance in terms of noise reduction and structure preservation in LDCT imaging, when compared to traditional supervised learning methods. [ABSTRACT FROM AUTHOR]

Objective. Accurate extraction of mitral valve shape from clinical tomographic images acquired in patients has proven useful for planning surgical and interventional mitral valve treatments. However, manual extraction of the mitral valve shape is laborious, and the existing automatic extraction methods have not been sufficiently accurate. In this paper, we propose a fully automated method of extracting mitral valve shape from computed tomography (CT) images for the all phases of the cardiac cycle. Approach. This method extracts the mitral valve shape based on DenseNet using both the original CT image and the existence probability maps of the mitral valve area inferred by U-Net as input. A total of 1585 CT images from 204 patients with various cardiac diseases including mitral regurgitation were collected and manually annotated for mitral valve region. The proposed method was trained and evaluated by 10-fold cross validation using the collected data and was compared with the method without the existence probability maps. Main results. The mean error of shape extraction error in the proposed method is 0.88 mm, which is an improvement of 0.32 mm compared with the method without the existence probability maps. Significance. We present a novel fully automatic mitral valve extraction method from input to output for all phases of 4D CT images. We suggest that the accuracy of mitral valve shape extraction is improved by using existence probability maps. [ABSTRACT FROM AUTHOR]

Objective. Precise hip joint morphometry measurement from CT images is crucial for successful preoperative arthroplasty planning and biomechanical simulations. Although deep learning approaches have been applied to clinical bone surgery planning, there is still a lack of relevant research on quantifying hip joint morphometric parameters from CT images. Approach. This paper proposes a deep learning workflow for CT-based hip morphometry measurement. For the first step, a coarse-to-fine deep learning model is designed for accurate reconstruction of the hip geometry (3D bone models and key landmark points). Based on the geometric models, a robust measurement method is developed to calculate a full set of morphometric parameters, including the acetabular anteversion and inclination, the femoral neck shaft angle and the inclination, etc. Our methods were validated on two datasets with different imaging protocol parameters and further compared with the conventional 2D x-ray-based measurement method. Main results. The proposed method yields high bone segmentation accuracies (Dice coefficients of 98.18% and 97.85%, respectively) and low landmark prediction errors (1.55 mm and 1.65 mm) on both datasets. The automated measurements agree well with the radiologists' manual measurements (Pearson correlation coefficients between 0.47 and 0.99 and intraclass correlation coefficients between 0.46 and 0.98). This method provides more accurate measurements than the conventional 2D x-ray-based measurement method, reducing the error of acetabular cup size from over 2 mm to less than 1 mm. Moreover, our morphometry measurement method is robust against the error of the previous bone segmentation step. As we tested different deep learning methods for the prerequisite bone segmentation, our method produced consistent final measurement results, with only a 0.37 mm maximum inter-method difference in the cup size. Significance. This study proposes a deep learning approach with improved robustness and accuracy for pelvis arthroplasty planning. [ABSTRACT FROM AUTHOR]

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is expensive to obtain and cannot be perfectly simulated. Unsupervised learning utilizes unpaired data and is highly desirable for LDCT denoising. As an example, an artifact disentanglement network (ADN) relies on unpaired images and obviates the need for supervision but the results of artifact reduction are not as good as those through supervised learning. An important observation is that there is often hidden similarity among unpaired data that can be utilized. This paper introduces a new learning mode, called quasi-supervised learning, to empower ADN for LDCT image denoising. For every LDCT image, the best matched image is first found from an unpaired normal-dose CT (NDCT) dataset. Then, the matched pairs and the corresponding matching degree as prior information are used to construct and train our ADN-type network for LDCT denoising. The proposed method is different from (but compatible with) supervised and semi-supervised learning modes and can be easily implemented by modifying existing networks. The experimental results show that the method is competitive with state-of-the-art methods in terms of noise suppression and contextual fidelity. The code and working dataset are publicly available at https://github.com/ruanyuhui/ADN-QSDL.git. [ABSTRACT FROM AUTHOR]

In this paper, we propose a two-stage data-model driven pancreas segmentation method that combines a 3D convolution neural network with adaptive pointwise parametric hybrid variational model embedding the directional and magnitude information of the boundary intensity gradient. Firstly, nnU-net is used to segment the entire abdominal CT image with the aim of obtaining the region of the interest of pancreas. Secondly, an adaptive pointwise parametric variational model with a new edge term containing the directional and magnitude information of the boundary intensity gradient is used to refine the predicted results from CNN. Although CNN is good at extracting texture information, it does not capture weak boundary information very well. In order to well acquire more weak boundary information of the pancreas, we utilize not only the magnitude of the gradient, but also the directional information of the boundary intensity gradient to obtain more accurate results in the new edge term. In addition, the probability value for each pixel obtained by calculating the softmax function is exploited twice. Actually, it is applied firstly to generate the binary map as the initial contour of the variational model and then to design the adaptive pointwise weight parameters of internal and external area terms of the variational model rather than constants. It not only eliminates the trouble of manual parameter adjustment, but also, most importantly, provides a more accurate pointwise evolutionary trend of the level set contour, i.e. determine the tendency of the level set contour to pointwisely contract inward or expand outward. Our method is evaluated on three public datasets and outperformed the state-of-the-art pancreas segmentation methods. Accurate pancreatic segmentation allows for more reliable quantitative analysis of local morphological changes in the pancreas, which can assist in early diagnosis and treatment planning. [ABSTRACT FROM AUTHOR]

Objective. Accurate segmentation of head and neck (H&N) tumors is critical in radiotherapy. However, the existing methods lack effective strategies to integrate local and global information, strong semantic information and context information, and spatial and channel features, which are effective clues to improve the accuracy of tumor segmentation. In this paper, we propose a novel method called dual modules convolution transformer network (DMCT-Net) for H&N tumor segmentation in the fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) images. Approach. The DMCT-Net consists of the convolution transformer block (CTB), the squeeze and excitation (SE) pool module, and the multi-attention fusion (MAF) module. First, the CTB is designed to capture the remote dependency and local multi-scale receptive field information by using the standard convolution, the dilated convolution, and the transformer operation. Second, to extract feature information from different angles, we construct the SE pool module, which not only extracts strong semantic features and context features simultaneously but also uses the SE normalization to adaptively fuse features and adjust feature distribution. Third, the MAF module is proposed to combine the global context information, channel information, and voxel-wise local spatial information. Besides, we adopt the up-sampling auxiliary paths to supplement the multi-scale information. Main results. The experimental results show that the method has better or more competitive segmentation performance than several advanced methods on three datasets. The best segmentation metric scores are as follows: DSC of 0.781, HD95 of 3.044, precision of 0.798, and sensitivity of 0.857. Comparative experiments based on bimodal and single modal indicate that bimodal input provides more sufficient and effective information for improving tumor segmentation performance. Ablation experiments verify the effectiveness and significance of each module. Significance. We propose a new network for 3D H&N tumor segmentation in FDG-PET/CT images, which achieves high accuracy. [ABSTRACT FROM AUTHOR]

Iterative reconstruction frameworks show predominance in low dose and incomplete data situations. In the iterative reconstruction framework, there are two components, i.e., the fidelity term aims to maintain the structure details of the reconstructed object, and the regularization term uses prior information to suppress the artifacts such as noise. A regularization parameter balances them, aiming to find a good trade-off between noise and resolution. Currently, the regularization parameters are selected as a rule of thumb or some prior knowledge assumption is required, which limits practical uses. Furthermore, the computation cost of regularization parameter selection is also heavy. In this paper, we address this problem by introducing CT image quality assessment (IQA) into the iterative reconstruction framework. Several steps are involved during the study. First, we analyze the CT image statistics using the dual dictionary (DDL) method. Regularities are observed and concluded, revealing the relationship among the regularization parameter, iterations, and CT image quality. Second, with derivation and simplification of DDL procedure, a CT IQA metric named SODVAC is designed. The SODVAC locates the optimal regularization parameter that results in the reconstructed image with distinct structures and with no noise or little noise. Thirdly, we introduce SODVAC into the iterative reconstruction framework and then propose a general image-quality-guided iterative reconstruction (QIR) framework and give a specific framework example (sQIR) by introducing SODVAC into the iterative reconstruction framework. sQIR simultaneously optimizes the reconstructed image and the regularization parameter during the iterations. Results confirm the effectiveness of the proposed method. No prior information is needed and the low computation cost are the advantages of our method compared with existing state-of-the-art L-curve and ZIP selection strategies. [ABSTRACT FROM AUTHOR]

Most scanning schemes of multi-energy computed tomography (MECT) require multiple sets of full-scan measurements under different x-ray spectra, which limits the application of MECT with incomplete scan. To handle this problem, a flexible MECT scanning strategy is proposed in this paper, which divides one half scan into three curves. Also, a novel MECT reconstruction algorithm is developed to relax the requirement of data acquisition of MECT. For MECT, gradient images of CT images at different energies ideally share the same position of zero-value set (Pos-OS) for the same object. Based on this observation, the characteristics of limited-angle artifacts is first explored, and it is found that the limited-angle artifacts in the image domain are closely related to the angle trajectory of the scan. Inspired by this discovery, the Pos-OS of the gradient image from the fusion CT image is extracted, and it is incorporated as prior knowledge into the TV minimization model in the form of equality constraints. The alternating direction method is exploited to solve the improved optimization model iteratively. Based on this, the proposed algorithm is derived to eliminate the limited angle artifacts in the image domain.The experimental results show that the proposed method achieves higher reconstruction quality under the designed scanning configuration than other methods in the literature. [ABSTRACT FROM AUTHOR]

Accurate organ segmentation is a relatively challenging subject in medical imaging, especially for the pancreas, whose morphological characteristics are subtle but variable. In this paper, a novel dual adversarial convolutional network with multilevel cues (DACN-MC) is proposed to segment the pancreas in computerized tomography (CT). DACN-MC first involves a duplex adversarial network using a conventional model for biomedical image segmentation, which ensures the veracity of the predicted probability volumes and ultimately enhances the quality of the obtained maps. Specifically, one of the adversarial networks helps the predicted maps to resemble the ground truths by importing extra guidance into the original loss functions. The other adversarial network further judges whether the obtained maps are well segmented and improves the image quality once again. Then, a multilevel cue collection module (MCCM) is introduced to gather many useful details for pancreas segmentation. In other words, we collect several sets of material formed by features from different layers and pick out a group with optimal performance for use in the ultimate algorithm. The experimental results show that dual adversarial convolutional networks together with multilevel cue collection help our proposed algorithm to achieve competitive segmentation performance, based on the results of several evaluation indexes. [ABSTRACT FROM AUTHOR]

CT images for radiotherapy planning are usually acquired in thick slices to reduce the imaging dose, especially for pediatric patients, and to lessen the need for contouring and treatment planning on more slices. However, low through-plane resolution may degrade the accuracy of dose calculations. In this paper, a self-supervised deep learning workflow is proposed to synthesize high through-plane resolution CT images by learning from their high in-plane resolution features. The proposed workflow was designed to facilitate neural networks to learn the mapping from low-resolution (LR) to high-resolution (HR) images in the axial plane. During the inference step, the HR sagittal and coronal images were generated by feeding two parallel-trained neural networks with the respective LR sagittal and coronal images to the trained neural networks. The CT simulation images of a cohort of 75 patients with head and neck cancer (1 mm slice thickness) and 200 CT images of a cohort of 20 lung cancer patients (3 mm slice thickness) were retrospectively investigated in a cross-validation manner. The HR images generated with the proposed method were qualitatively (visual quality, image intensity profiles and preliminary observer study) and quantitatively (mean absolute error, edge keeping index, structural similarity index measurement, information fidelity criterion and visual information fidelity in pixel domain) inspected, while taking the original CT images of the head and neck and lung cancer patients as the reference. The qualitative results showed the capability of the proposed method for generating high through-plane resolution CT images with data from both groups of cancer patients. All the improvements in the measure metrics were confirmed to be statistically significant with paired two-sample t-test analysis. The innovative point of the work is that the proposed deep learning workflow for CT image generation with high through-plane resolution in radiotherapy is self-supervised, meaning that it does not rely on ground truth CT images to train the network. In addition, the assumption that the in-plane HR information can supervise the through-plane HR generation is confirmed. We hope that this will inspire more research on this topic to further improve the through-plane resolution of medical images. [ABSTRACT FROM AUTHOR]

Micro-CT has important applications in biomedical research due to its ability to perform high-precision 3D imaging of micro-architecture in a non-invasive way. Because of the limited power of the radiation source, it is difficult to obtain a high signal-to-noise image under the requirement of temporal resolution. Therefore, low-dose CT image denoising has attracted considerable attention to improve the image quality of micro-CT while maintaining time resolution. In this paper, an end-to-end asymmetric perceptual convolutional network (APCNet) is proposed to enhance the network's ability to capture and retain image details by improving the convolutional layer and introducing an edge detection layer. Compared with the previously proposed denoising models such as DnCNN, CNN-VGG, and RED-CNN, experiments proved that our proposed method has achieved better results in both numerical indicators and visual perception. [ABSTRACT FROM AUTHOR]

In x-ray CT imaging, the existence of metal in the imaging field of view deteriorates the quality of the reconstructed image. This is because rays penetrating dense metal implants are highly corrupted, causing huge inconsistency between projection data. The result appears as strong artifacts such as black and white streaks on the reconstructed image disturbing correct diagnosis. For several decades, there have been various trials to reduce metal artifacts for better image quality. As the computing power of computer processors became more powerful, more complex algorithms with improved performance have been introduced. For instance, the initially developed metal artifact reduction (MAR) algorithms based on simple sinogram interpolation were combined with computationally expensive iterative reconstruction techniques to pursue better image quality. Recently, even machine learning based techniques have been introduced, which require huge amounts of computations for training. In this paper, we introduce an image based novel MAR algorithm in which severe metal artifacts such as black shadings are detected by the proposed method in a straightforward manner based on a linear interpolation. To do that, a new concept of metal artifact classification is devised using linear interpolation in the virtual projection domain. The proposed method reduces severe artifacts very quickly and effectively and has good performance to keep the detailed body structure preserved. Results of qualitative and quantitative comparisons with other representative algorithms such as LIMAR and NMAR support the excellence of the proposed algorithm. Thanks to the nature of reducing artifacts in the image itself and its low computational cost, the proposed algorithm can function as an initial image generator for other MAR algorithms, as well as being integrated in the modalities under limited computation power such as mobile CT scanners. [ABSTRACT FROM AUTHOR]

In x-ray multispectral (or photon-counting) computed tomography (MCT), the object of interest is scanned under multiple x-ray spectra, and it can acquire more information about the scanned object than conventional CT, in which only one x-ray spectrum is used. The obtained polychromatic projections are utilized to perform material-selective and energy-selective image reconstruction. Compared with the conventional single spectral CT, MCT has a superior material distinguishability. Therefore, it has wide potential applications in both medical and industrial areas. However, the nonlinearity and ill condition of the MCT problem make it difficult to get high-quality and fast convergence of images for existing MCT reconstruction algorithms. In this paper, we proposed an iterative reconstruction algorithm based on an oblique projection modification technique (OPMT) for fast basis material decomposition of MCT. In the case of geometric inconsistency, along the current x-ray path, the oblique projection modification direction not only relates to the polychromatic projection equation of the known spectrum, but it also comprehensively refers to the polychromatic projection equation information of the unknown spectra. Moreover, the ray-by-ray correction makes it applicable to geometrically consistent projection data. One feature of the proposed algorithm is its fast convergence speed. The OPMT considers the information from multiple polychromatic projection equations, which greatly speeds up the convergence of MCT reconstructed images. Another feature of the proposed algorithm is its high flexibility. The ray-by-ray correction will be suitable for any common MCT scanning mode. The proposed algorithm is validated with numerical experiments from both simulated and real data. Compared with the ASD-NC-POCS and E-ART algorithms, the proposed algorithm achieved high-quality reconstructed images while accelerating the convergence speed of them. [ABSTRACT FROM AUTHOR]

Dynamic myocardial perfusion computed tomography (DMP-CT) is an effective medical imaging technique for coronary artery disease diagnosis and therapy guidance. However, the radiation dose received by the patient during repeated CT scans is a widespread concern of radiologists because of the increased risk of cancer. The sparse few-view CT scanning protocol can be a feasible approach to reduce the radiation dose of DMP-CT imaging; however, an advanced reconstruction algorithm is needed. In this paper, a temporal feature prior-aided separated reconstruction method (TFP-SR) for low-dose DMP-CT images reconstruction from sparse few-view sinograms is proposed. To implement the proposed method, the objective perfusion image is divided into the baseline fraction and the enhancement fraction introduced by the arrival of the contrast agent. The core of the proposed TFP-SR method is the utilization of the temporal evolution information that naturally exists in the DMP-CT image sequence to aid the enhancement image reconstruction from limited data. The temporal feature vector of an image pixel is defined by the intensities of this pixel in the pre-reconstructed enhancement sequence, and the connection between two related features is calculated via a zero-mean Gaussian function. A prior matrix is constructed based on the connections between the extracted temporal features and used in the iterative reconstruction of the enhancement images. To evaluate the proposed method, the conventional filtered back-projection algorithm, the total variation regularized PWLS (PWLS-TV) and the prior image constrained compressed sensing are compared in this paper based on studies on a digital extended cardiac-torso (XCAT) thoracic phantom and a preclinical porcine DMP-CT data set that take image misregistration into account. The experimental results demonstrate that the proposed TFP-SR method has superior performance in sparse DMP-CT images reconstruction in terms of image quality and the analyses of the time attenuation curve and hemodynamic parameters. [ABSTRACT FROM AUTHOR]

Pulmonary nodule false-positive reduction is of great significance for automated nodule detection in clinical diagnosis of low-dose computed tomography (LDCT) lung cancer screening. Due to individual intra-nodule variations and visual similarities between true nodules and false positives as soft tissues in LDCT images, the current clinical practices remain subject to shortcomings of potential high-risk and time-consumption issues. In this paper, we propose a multi-dimensional nodule detection network (MD-NDNet) for automatic nodule false-positive reduction using deep convolutional neural network (DCNNs). The underlying method collaboratively integrates multi-dimensional nodule information to complementarily and comprehensively extract nodule inter-plane volumetric correlation features using three-dimensional CNNs (3D CNNs) and spatial nodule correlation features from sagittal, coronal, and axial planes using two-dimensional CNNs (2D CNNs) with attention module. To incorporate different sizes and shapes of nodule candidates, a multi-scale ensemble strategy is employed for probability aggregation with weights. The proposed method is evaluated on the LUNA16 challenge dataset in ISBI 2016 with ten-fold cross-validation. Experiment results show that the proposed framework achieves classification performance with a CPM score of 0.9008. All of these indicate that our method enables an efficient, accurate and reliable pulmonary nodule detection for clinical diagnosis. [ABSTRACT FROM AUTHOR]

In computed tomography, high attenuation occurs when x-rays pass through a dense region or a long path in the scanning object. In this case, only limited photons reach the detector, which causes photon starvation artifacts. The artifacts usually appear as streaks along the directions with high attenuation. It might lower the discrimination of minor structures and lead to misdiagnosis. Applying a local filter to the projection data adaptively is a common solution, however, if the parameters of projection-based filter are not well selected, new artifacts and noise might appear in the final image. In this paper, a post image processing technique was developed to suppress the photon starvation streak artifacts. Based on the directional characteristics of streaks, a semi-adaptive anisotropic diffusion filter was applied to the high frequency sub-bands after wavelet transformation (WASA). Qualitative and quantitative experiments were performed on phantom data and clinical data to prove the effectiveness of this method for photon starvation artifact suppression. [ABSTRACT FROM AUTHOR]

Computed tomography perfusion (CTP) is a functional imaging that allows for providing capillary-level hemodynamics information of the desired tissue in clinics. In this paper, we aim to offer insight into CTP imaging which covers the basics and current state of CTP imaging, then summarize the technical applications in the CTP imaging as well as the future technological potential. At first, we focus on the fundamentals of CTP imaging including systematically summarized CTP image acquisition and hemodynamic parameter map estimation techniques. A short assessment is presented to outline the clinical applications with CTP imaging, and then a review of radiation dose effect of the CTP imaging on the different applications is presented. We present a categorized methodology review on known and potential solvable challenges of radiation dose reduction in CTP imaging. To evaluate the quality of CTP images, we list various standardized performance metrics. Moreover, we present a review on the determination of infarct and penumbra. Finally, we reveal the popularity and future trend of CTP imaging. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID-19) has brought huge losses to the world, and it remains a great threat to public health. X-ray computed tomography (CT) plays a central role in the management of COVID-19. Traditional diagnosis with pulmonary CT images is time-consuming and error-prone, which could not meet the need for precise and rapid COVID-19 screening. Nowadays, deep learning (DL) has been successfully applied to CT image analysis, which assists radiologists in workflow scheduling and treatment planning for patients with COVID-19. Traditional methods use cross-entropy as the loss function with a Softmax classifier following a fully-connected layer. Most DL-based classification methods target intraclass relationships in a certain class (early, progressive, severe, or dissipative phases), ignoring the natural order of different phases of the disease progression, i.e., from an early stage and progress to a late stage. To learn both intraclass and interclass relationships among different stages and improve the accuracy of classification, this paper proposes an ensemble learning method based on ordinal regression, which leverages the ordinal information on COVID-19 phases. The proposed method uses multi-binary, neuron stick-breaking (NSB), and soft labels (SL) techniques, and ensembles the ordinal outputs through a median selection. To evaluate our method, we collected 172 confirmed cases. In a 2-fold cross-validation experiment, the accuracy is increased by 22% compared with traditional methods when we use modified ResNet-18 as the backbone. And precision, recall, and F 1-score are also improved. The experimental results show that our proposed method achieves a better classification performance than the traditional methods, which helps establish guidelines for the classification of COVID-19 chest CT images. [ABSTRACT FROM AUTHOR]

Metallic implants can heavily attenuate x-rays in computed tomography (CT) scans, leading to severe artifacts in reconstructed images, which significantly jeopardize image quality and negatively impact subsequent diagnoses and treatment planning. With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT. Despite the encouraging results achieved by these methods, there is still much room to further improve performance. In this paper, a novel dual-domain adaptive-scaling non-local network (DAN-Net) is proposed for MAR. We correct the corrupted sinogram using adaptive scaling first to preserve more tissue and bone details. Then, an end-to-end dual-domain network is adopted to successively process the sinogram and its corresponding reconstructed image is generated by the analytical reconstruction layer. In addition, to better suppress the existing artifacts and restrain the potential secondary artifacts caused by inaccurate results of the sinogram-domain network, a novel residual sinogram learning strategy and non-local module are leveraged in the proposed network model. Experiments demonstrate the performance of the proposed DAN-Net is competitive with several state-of-the-art MAR methods in both qualitative and quantitative aspects. [ABSTRACT FROM AUTHOR]

The nanoparticle agent, combined with a targeting factor reacting with lesions, enables specific CT imaging. Thus, the identification of the nanoparticle agents has the potential to improve clinical diagnosis. Thanks to the energy sensitivity of the photon-counting detector (PCD), it can exploit the K-edge of the nanoparticle agents in the clinical x-ray energy range to identify the agents. In this paper, we propose a novel data-driven approach for nanoparticle agent identification using the PCD. We generate two sets of training data consisting of PCD measurements from calibration phantoms, one in the presence of nanoparticle agent and the other in the absence of the agent. For a given sinogram of PCD counts, the proposed method calculates the normalized log-likelihood sinogram for each class (class 1: with the agent, class 2: without the agent) using the K nearest neighbors (KNN) estimator, backproject the sinograms, and compare the backprojection images to identify the agent. We also proved that the proposed algorithm is equivalent to the maximum likelihood-based classification. We studied the robustness of dose reduction with gold nanoparticles as the K-edge contrast media and demonstrated that the proposed method identifies targets with different concentrations of the agents without background noise. [ABSTRACT FROM AUTHOR]

Purpose. Accurate localization and labeling of vertebrae in computed tomography (CT) is an important step toward more quantitative, automated diagnostic analysis and surgical planning. In this paper, we present a framework (called Ortho2D) for vertebral labeling in CT in a manner that is accurate and memory-efficient. Methods. Ortho2D uses two independent faster R-convolutional neural network networks to detect and classify vertebrae in orthogonal (sagittal and coronal) CT slices. The 2D detections are clustered in 3D to localize vertebrae centroids in the volumetric CT and classify the region (cervical, thoracic, lumbar, or sacral) and vertebral level. A post-process sorting method incorporates the confidence in network output to refine classifications and reduce outliers. Ortho2D was evaluated on a publicly available dataset containing 302 normal and pathological spine CT images with and without surgical instrumentation. Labeling accuracy and memory requirements were assessed in comparison to other recently reported methods. The memory efficiency of Ortho2D permitted extension to high-resolution CT to investigate the potential for further boosts to labeling performance. Results. Ortho2D achieved overall vertebrae detection accuracy of 97.1%, region identification accuracy of 94.3%, and individual vertebral level identification accuracy of 91.0%. The framework achieved 95.8% and 83.6% level identification accuracy in images without and with surgical instrumentation, respectively. Ortho2D met or exceeded the performance of previously reported 2D and 3D labeling methods and reduced memory consumption by a factor of ∼50 (at 1 mm voxel size) compared to a 3D U-Net, allowing extension to higher resolution datasets than normally afforded. The accuracy of level identification increased from 80.1% (for standard/low resolution CT) to 95.1% (for high-resolution CT). Conclusions. The Ortho2D method achieved vertebrae labeling performance that is comparable to other recently reported methods with significant reduction in memory consumption, permitting further performance boosts via application to high-resolution CT. [ABSTRACT FROM AUTHOR]

Reducing radiation-induced side effects is one of the most important challenges in paediatric cancer treatment. Recently, there has been growing interest in using spatial normalisation to enable voxel-based analysis of radiation-induced toxicities in a variety of patient groups. The need to consider three-dimensional distribution of doses, rather than dose-volume histograms, is desirable but not yet explored in paediatric populations. In this paper, we investigate the feasibility of atlas construction and spatial normalisation in paediatric radiotherapy. We used planning computed tomography (CT) scans from twenty paediatric patients historically treated with craniospinal irradiation to generate a template CT that is suitable for spatial normalisation. This childhood cancer population representative template was constructed using groupwise image registration. An independent set of 53 subjects from a variety of childhood malignancies was then used to assess the quality of the propagation of new subjects to this common reference space using deformable image registration (i.e. spatial normalisation). The method was evaluated in terms of overall image similarity metrics, contour similarity and preservation of dose-volume properties. After spatial normalisation, we report a dice similarity coefficient of 0.95 ± 0.05, 0.85 ± 0.04, 0.96 ± 0.01, 0.91 ± 0.03, 0.83 ± 0.06 and 0.65 ± 0.16 for brain and spinal canal, ocular globes, lungs, liver, kidneys and bladder. We then demonstrated the potential advantages of an atlas-based approach to study the risk of second malignant neoplasms after radiotherapy. Our findings indicate satisfactory mapping between a heterogeneous group of patients and the template CT. The poorest performance was for organs in the abdominal and pelvic region, likely due to respiratory and physiological motion and to the highly deformable nature of abdominal organs. More specialised algorithms should be explored in the future to improve mapping in these regions. This study is the first step toward voxel-based analysis in radiation-induced toxicities following paediatric radiotherapy. [ABSTRACT FROM AUTHOR]

Automated brain structures segmentation in positron emission tomography (PET) images has been widely investigated to help brain disease diagnosis and follow-up. To relieve the burden of a manual definition of volume of interest (VOI), automated atlas-based VOI definition algorithms were developed, but these algorithms mostly adopted a global optimization strategy which may not be particularly accurate for local small structures (especially the deep brain structures). This paper presents a PET/CT-based brain VOI segmentation algorithm combining anatomical atlas, local landmarks, and dual-modality information. The method incorporates local deep brain landmarks detected by the Deep Q-Network (DQN) to constrain the atlas registration process. Dual-modality PET/CT image information is also combined to improve the registration accuracy of the extracerebral contour. We compare our algorithm with the representative brain atlas registration methods based on 86 clinical PET/CT images. The proposed algorithm obtained accurate delineation of brain VOIs with an average Dice similarity score of 0.79, an average surface distance of 0.97 mm (sub-pixel level), and a volume recovery coefficient close to 1. The main advantage of our method is that it optimizes both global-scale brain matching and local-scale small structure alignment around the key landmarks, it is fully automated and produces high-quality parcellation of the brain structures from brain PET/CT images. [ABSTRACT FROM AUTHOR]

With the emergence of online MRI radiotherapy treatments, MR-based workflows have increased in importance in the clinical workflow. However proper dose planning still requires CT images to calculate dose attenuation due to bony structures. In this paper, we present a novel deep image synthesis model that generates in an unsupervised manner CT images from diagnostic MRI for radiotherapy planning. The proposed model based on a generative adversarial network (GAN) consists of learning a new invariant representation to generate synthetic CT (sCT) images based on high frequency and appearance patterns. This new representation encodes each convolutional feature map of the convolutional GAN discriminator, leading the training of the proposed model to be particularly robust in terms of image synthesis quality. Our model includes an analysis of common histogram features in the training process, thus reinforcing the generator such that the output sCT image exhibits a histogram matching that of the ground-truth CT. This CT-matched histogram is embedded then in a multi-resolution framework by assessing the evaluation over all layers of the discriminator network, which then allows the model to robustly classify the output synthetic image. Experiments were conducted on head and neck images of 56 cancer patients with a wide range of shape sizes and spatial image resolutions. The obtained results confirm the efficiency of the proposed model compared to other generative models, where the mean absolute error yielded by our model was 26.44(0.62), with a Hounsfield unit error of 45.3(1.87), and an overall Dice coefficient of 0.74(0.05), demonstrating the potential of the synthesis model for radiotherapy planning applications. [ABSTRACT FROM AUTHOR]

Physics in Medicine and Biology (PMB) awards its ‘Citations Prize’ to the authors of the original research paper that has received the most citations in the preceding five years (according to the Institute for Scientific Information (ISI)). The lead author of the winning paper is presented with the Rotblat Medal (named in honour of Professor Sir Joseph Rotblat, a Nobel Prize winner who also was the second—and longest serving—Editor of PMB, from 1961–1972). The winner of the 2013 Citations Prize for the paper which has received the most citations in the previous five years (2008–2012) is Figure. Four of the prize winning authors. From left to right: Thomas Istel (Philips), Jens-Peter Schlomka (with medal, MorphoDetection), Ewald Roessl (Philips), and Gerhard Martens (Philips). Title: Experimental feasibility of multi-energy photon-counting K-edge imaging in pre-clinical computed tomography Authors: Jens Peter Schlomka1, Ewald Roessl1, Ralf Dorscheid2, Stefan Dill2, Gerhard Martens1, Thomas Istel1, Christian Bäumer3, Christoph Herrmann3, Roger Steadman3, Günter Zeitler3, Amir Livne4 and Roland Proksa1 Institutions: 1 Philips Research Europe, Sector Medical Imaging Systems, Hamburg, Germany 2 Philips Research Europe, Engineering & Technology, Aachen, Germany 3 Philips Research Europe, Sector Medical Imaging Systems, Aachen, Germany 4 Philips Healthcare, Global Research and Advanced Development, Haifa, Israel Reference: Schlomka et al 2008 Phys. Med. Biol. 53 4031–47 This paper becomes the first to win both this citations prize and also the PMB best paper prize (The Roberts Prize), which it won for the year 2008. Discussion of the significance of the winning paper can be found in this medicalphysicsweb article from the time of the Roberts Prize win (http://medicalphysicsweb.org/cws/article/research/39907). The author's enthusiasm for their prototype spectral CT system has certainly been reflected in the large number of citations the paper subsequently has received. Our warm congratulations go to the winning authors. [ABSTRACT FROM AUTHOR]

An effective registration framework between preoperative 3D computed tomography and intraoperative 2D x-ray images is crucial in image-guided therapy. In this paper, a novel 2D/3D hierarchical registration framework via principal-directional Fourier transform operator (HRF-PDFTO) is proposed. First, a PDFTO was established to obtain the in-plane translation and rotation invariance. Then, an initial free template-matching approach based on PDFTO was utilized to avoid initial value assignment and expand the capture range of registration. Finally, the hierarchical registration framework, HRF-PDFTO, was proposed to reduce the dimensions of the registration search space from n6 to n2. The experimental results demonstrated that the proposed HRF-PDFTO has good performance with an accuracy of 0.72 mm, and a single registration time of 16 s, which improves the registration efficiency by ten times. Consequently, the HRF-PDFTO can meet the accuracy and efficiency requirements of 2D/3D registration in related clinical applications. [ABSTRACT FROM AUTHOR]

Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on low-dose training data without considering dose differences. However, the radiation dose difference has a great impact on the ultimate results, and lower doses increase the difficulty of restoration. Moreover, there is increasing demand to design and estimate acceptable scanning doses for patients in clinical practice, necessitating dose-aware networks embedded with adaptive dose estimation. In this paper, we consider these dose differences of input LDCT images and propose an adaptive dose-aware network. First, considering a large dose distribution range for simulation convenience, we coarsely define five dose levels in advance as lowest, lower, mild, higher and highest radiation dose levels. Instead of directly building the end-to-end mapping function between LDCT images and high-dose CT counterparts, the dose level is primarily estimated in the first stage. In the second stage, the adaptively learned low-dose level is used to guide the image restoration process as the pattern of prior information through the channel feature transform. We conduct experiments on a simulated dataset based on original high dose parts of American Association of Physicists in Medicine challenge datasets from the Mayo Clinic. Ablation studies validate the effectiveness of the dose-level estimation, and the experimental results show that our method is superior to several other DL-based methods. Specifically, our method provides obviously better performance in terms of the peak signal-to-noise ratio and visual quality reflected in subjective scores. Due to the dual-stage process, our method may suffer limitations under more parameters and coarse dose-level definitions, and thus, further improvements in clinical practical applications with different CT equipment vendors are planned in future work. [ABSTRACT FROM AUTHOR]

Infection segmentation on chest CT plays an important role in the quantitative analysis of COVID-19. Developing automatic segmentation tools in a short period with limited labelled images has become an urgent need. Pseudo label-based semi-supervised method is a promising way to leverage unlabelled data to improve segmentation performance. Existing methods usually obtain pseudo labels by first training a network with limited labelled images and then inferring unlabelled images. However, these methods may generate obviously inaccurate labels and degrade the subsequent training process. To address these challenges, in this paper, an active contour regularized semi-supervised learning framework was proposed to automatically segment infections with few labelled images. The active contour regularization was realized by the region-scalable fitting (RSF) model which is embedded to the loss function of the network to regularize and refine the pseudo labels of the unlabelled images. We further designed a splitting method to separately optimize the RSF regularization term and the segmentation loss term with iterative convolution-thresholding method and stochastic gradient descent, respectively, which enable fast optimization of each term. Furthermore, we built a statistical atlas to show the infection spatial distribution. Extensive experiments on a small public dataset and a large scale dataset showed that the proposed method outperforms state-of-the-art methods with up to 5% in dice similarity coefficient and normalized surface dice, 10% in relative absolute volume difference and 8 mm in 95% Hausdorff distance. Moreover, we observed that the infections tend to occur at the dorsal subpleural lung and posterior basal segments that are not mentioned in current radiology reports and are meaningful to advance our understanding of COVID-19. [ABSTRACT FROM AUTHOR]

The suppression of streak artifacts in computed tomography with a limited-angle configuration is challenging. Conventional analytical algorithms, such as filtered backprojection (FBP), are not successful due to incomplete projection data. Moreover, model-based iterative total variation algorithms effectively reduce small streaks but do not work well at eliminating large streaks. In contrast, FBP mapping networks and deep-learning-based postprocessing networks are outstanding at removing large streak artifacts; however, these methods perform processing in separate domains, and the advantages of multiple deep learning algorithms operating in different domains have not been simultaneously explored. In this paper, we present a hybrid-domain convolutional neural network (hdNet) for the reduction of streak artifacts in limited-angle computed tomography. The network consists of three components: the first component is a convolutional neural network operating in the sinogram domain, the second is a domain transformation operation, and the last is a convolutional neural network operating in the CT image domain. After training the network, we can obtain artifact-suppressed CT images directly from the sinogram domain. Verification results based on numerical, experimental and clinical data confirm that the proposed method can significantly reduce serious artifacts. [ABSTRACT FROM AUTHOR]

Multi-material decomposition (MMD) technique decomposes the CT images into basis material images and has been promising in clinical practice for material composition quantification within the human body. MMD could be implemented using the image data acquired from spectral CT or its special case, dual-energy CT (DECT) while the spectral CT data acquisition usually requires a hardware modification. In this paper, we propose an image domain MMD method using single energy CT (SECT). The proposed objective function applies a least square data fidelity term to enforce the minimization between the linear combination of decomposed material image and the measured SECT image, and an edge-preserving (EP) regularization term to meet the piecewise constant property of the material image. We apply the optimization transfer principle to form a pixel-wise separable quadratic surrogate (PWSQS) function in each iteration to decrease the objective function. The pixelwise direct inversion method assisted by the two-material assumption (TMA) is applied to obtain a good initial value. The proposed method is evaluated using a digital phantom, a Catphan phantom and the clinical data. A low-pass filtration method is implemented for a comparison purpose. In the phantom study, the proposed TMA method achieves high volume fraction accuracy (VFA) of 79.64% and the proposed EP method further increases the VFA by 15.56% and decreases the decomposition standard deviation (STD) by 81.51% compared with the TMA method. At the comparable noise level, the proposed EP method increases spatial resolution by an overall factor of 1.01 when the modulation transfer function magnitude is decreased to 50% compared with the low-pass filtration method. In clinical data study, the virtual non-contrast image generated by the proposed method achieves the root-mean-squared-relative error of 2.93% compared with the contrast-free ground-truth image. [ABSTRACT FROM AUTHOR]

Objective. This study simulated the potential of gold nanoparticles (GNPs) to improve the effectiveness of radiation therapy in pancreatic cancer cases. The purpose of this study was to assess the impact of GNPs on tumor control probability (TCP) and normal tissue complication probability (NTCP) in pancreatic cancer cases undergoing radiation therapy. The work aimed to compare treatment plans generated with a novel 2.5 MV beam using GNPs to conventional 6 MV plans and evaluate the dose-volume histogram (DVH), TCP, and NTCP. Approach. Treatment planning for five pancreatic computed tomography (CT) images was performed using the open-source MATLAB-based treatment planning program matRad. MATLAB codes were developed to calculate the relative biological effectiveness (RBE) of GNPs and apply the corresponding dose and RBE values to each voxel. TCP and NTCP were calculated based on the applied RBE values. Main results. Adding GNPs to the 2.5 MV treatment plan resulted in a significant increase in TCP, from around 59% to 93.5%, indicating that the inclusion of GNPs improved the effectiveness of the radiation treatment. The range in NTCP without GNPs was relatively larger compared to that with GNPs. Significance. The results indicated that the addition of GNPs to a 2.5 MV plan can increase TCP while maintaining a relatively low NTCP value (<1%). The use of GNPs may also reduce NTCP values by decreasing the dose to normal tissues while maintaining the same prescribed dose to the tumor. Hence, the addition of GNPs can improve the balance between TCP and NTCP. [ABSTRACT FROM AUTHOR]

Objective. This study describes geometry-based and intensity-based tools for quality assurance (QA) of automatically generated structures for online adaptive radiotherapy, and designs an operator-independent traffic light system that identifies erroneous structure sets. Approach. A cohort of eight head and neck (HN) patients with daily CBCTs was selected for test development. Radiotherapy contours were propagated from planning computed tomography (CT) to daily cone beam CT (CBCT) using deformable image registration. These propagated structures were visually verified for acceptability. For each CBCT, several error scenarios were used to generate what were judged unacceptable structures. Ten additional HN patients with daily CBCTs and different error scenarios were selected for validation. A suite of tests based on image intensity, intensity gradient, and structure geometry was developed using acceptable and unacceptable HN planning structures. Combinations of one test applied to one structure, referred to as structure-test combinations, were selected for inclusion in the QA system based on their discriminatory power. A traffic light system was used to aggregate the structure-test combinations, and the system was evaluated on all fractions of the ten validation HN patients. Results. The QA system distinguished between acceptable and unacceptable fractions with high accuracy, labeling 294/324 acceptable fractions as green or yellow and 19/20 unacceptable fractions as yellow or red. Significance. This study demonstrates a system to supplement manual review of radiotherapy planning structures. Automated QA is performed by aggregating results from multiple intensity- and geometry-based tests. [ABSTRACT FROM AUTHOR]

Objective. The partial-volume effect (PVE) is an important factor impairing tumour quantification in molecular imaging. The commonly used contour-volume-of-interest (contour-VOI) approach to correct for this effect employs phantom-based recovery coefficients. Applying oversize-VOIs could offer superior quantification accuracy in small lesions. The oversize-VOI approach uses a large oversize volume to determine the total tumour activity after applying a background correction. Aims of this study were to provide a procedure for the application of the oversize-VOI approach and to compare its performance to the contour-VOI approach in PET imaging. Approach. A sphere tumour model was simulated to determine the oversize diameter that contained 90%, 95%, and 98% of the total activity as a function of the tumour size. Experimental investigations involving phantom and clinical data were conducted on a digital PET/CT scanner. In the phantom investigation, 12 spherical tumour inserts (diameters ranging from 3.7 to 37.4 mm) containing 18F-solution were used. The accuracy of the contour- and oversize-VOI approach was evaluated for different signal-to-background ratios (20–3). Clinically, both approaches were applied on PET/CT images acquired with 18F-labelled prostate-specific membrane antigen in prostate cancer patients. Main results. From the tumour model, we deduced that an oversize-VOI of two PET spatial resolutions larger than the physical lesion diameter contains at least 98% of the total activity for lesions with diameters down to one PET spatial resolution, while minimizing the background contribution. Both approaches were robust against varying phantom and clinical imaging conditions. Performance of the oversize-VOI approach was favorable for lesions below 10 mm in diameter, whereas the contour-VOI approach was slightly more accurate for sizes above 10 mm. Significance. The oversize-VOI approach facilitates image quantification of small tumours. It is simple and effective to correct for the PVE and may be used in pre-therapeutic (small) tumour dosimetry. [ABSTRACT FROM AUTHOR]

Objective. Head and neck (H&N) cancers are among the most prevalent types of cancer worldwide, and [18F]F-FDG PET/CT is widely used for H&N cancer management. Recently, the diffusion model has demonstrated remarkable performance in various image-generation tasks. In this work, we proposed a 3D diffusion model to accurately perform H&N tumor segmentation from 3D PET and CT volumes. Approach. The 3D diffusion model was developed considering the 3D nature of PET and CT images acquired. During the reverse process, the model utilized a 3D UNet structure and took the concatenation of 3D PET, CT, and Gaussian noise volumes as the network input to generate the tumor mask. Experiments based on the HECKTOR challenge dataset were conducted to evaluate the effectiveness of the proposed diffusion model. Several state-of-the-art techniques based on U-Net and Transformer structures were adopted as the reference methods. Benefits of employing both PET and CT as the network input, as well as further extending the diffusion model from 2D to 3D, were investigated based on various quantitative metrics and qualitative results. Main results. Results showed that the proposed 3D diffusion model could generate more accurate segmentation results compared with other methods (mean Dice of 0.739 compared to less than 0.726 for other methods). Compared to the diffusion model in 2D form, the proposed 3D model yielded superior results (mean Dice of 0.739 compared to 0.669). Our experiments also highlighted the advantage of utilizing dual-modality PET and CT data over only single-modality data for H&N tumor segmentation (with mean Dice less than 0.570). Significance. This work demonstrated the effectiveness of the proposed 3D diffusion model in generating more accurate H&N tumor segmentation masks compared to the other reference methods. [ABSTRACT FROM AUTHOR]

The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively. [ABSTRACT FROM AUTHOR]

This paper studies the sensitivity of a range of image texture parameters used in radiomics to: (i) the number of intensity levels, (ii) the method of quantisation to select the intensity levels and (iii) the use of an intensity threshold. 43 commonly used texture features were studied for the gross target volume outlined on the CT component of PET/CT scans of 50 patients with non-small cell lung carcinoma (NSCLC). All cases were quantised for all values between 4 and 128 intensity levels using four commonly used quantisation methods. All results were analysed with and without a threshold range of −200 HU to 300 HU. Cases were ranked for each texture feature and for all quantisation methods with the Spearman's rank correlation coefficient determined to evaluate stability. Results showed large fluctuations in ranking, particularly for low numbers of levels, differences between quantisation methods and with the use of a threshold, with values Spearman's Rank Correlation for many parameters below 0.2. Our results demonstrated the sensitivity of radiomics features to the parameters used during analysis and highlight the risk of low reproducibility comparing studies with slightly different parameters. In terms of the lung cancer CT datasets, this study supports the use of 128 intensity levels, the same uniform quantiser applied to all scans and thresholding of the data. It also supports several of the features recommended in the literature for such studies such as skewness and kurtosis. A recommended framework is presented for curation of the data analysis process to ensure stability of results. [ABSTRACT FROM AUTHOR]

External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0 ± 3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60 ± 0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy. [ABSTRACT FROM AUTHOR]

Multi-modality examinations have been extensively applied in current clinical cancer management. Leveraging multi-modality medical images can be highly beneficial for automated tumor segmentation as they provide complementary information that could make the segmentation of tumors more accurate. This paper investigates CNN-based methods for automated nasopharyngeal carcinoma (NPC) segmentation using computed tomography (CT) and magnetic resonance (MR) images. Specially, a multi-modality convolutional neural network (M-CNN) is designed to jointly learn a multi-modal similarity metric and segmentation of paired CT-MR images. By jointly optimizing the similarity learning error and the segmentation error, the feature learning processes of both modalities are mutually guided. In doing so, the segmentation sub-networks are able to take advantage of the other modality's information. Considering that each modality possesses certain distinctive characteristics, we combine the higher-layer features extracted by a single-modality CNN (S-CNN) and M-CNN to form a combined CNN (C-CNN) for each modality, which is able to further utilize the complementary information of different modalities and improve the segmentation performance. The proposed M-CNN and C-CNN were evaluated on 90 CT-MR images of NPC patients. Experimental results demonstrate that our methods achieve improved segmentation performance compared to their counterparts without multi-modal information fusion and the existing CNN-based multi-modality segmentation methods. [ABSTRACT FROM AUTHOR]

Tomography images are essential for clinical diagnosis and trauma surgery, allowing doctors to understand the internal information of patients in more detail. Since the large amount of x-ray radiation from the continuous imaging during the process of computed tomography scanning can cause serious harm to the human body, reconstructing tomographic images from sparse views becomes a potential solution to this problem. Here we present a deep-learning framework for tomography image reconstruction, namely TIReconNet, which defines image reconstruction as a data-driven supervised learning task that allows a mapping between the 2D projection view and the 3D volume to emerge from corpus. The proposed framework consists of four parts: feature extraction module, shape mapping module, volume generation module and super resolution module. The proposed framework combines 2D and 3D operations, which can generate high-resolution tomographic images with a relatively small amount of computing resources and maintain spatial information. The proposed method is verified on chest digitally reconstructed radiographs, and the reconstructed tomography images have achieved PSNR value of 18.621 ± 1.228 dB and SSIM value of 0.872 ± 0.041 when compared against the ground truth. In conclusion, an innovative convolutional neural network architecture is proposed and validated in this study, which proves that there is the potential to generate a 3D high-resolution tomographic image from a single 2D image using deep learning. This method may actively promote the application of reconstruction technology for radiation reduction, and further exploration of intraoperative guidance in trauma and orthopedics. [ABSTRACT FROM AUTHOR]

Objective. Modern medical imaging plays a vital role in clinical practice, enabling non-invasive visualization of anatomical structures. Dynamic contrast enhancement (DCE) imaging is a technique that uses contrast agents to visualize blood flow dynamics in a time-resolved manner. It can be applied to different modalities, such as computed tomography (CT) and electrical impedance tomography (EIT). This study aims to develop a common theoretical and practical hemodynamic extraction basis for DCE modelling across modalities, based on the gamma-variate function. Approach. The study introduces a framework to generate time-intensity curves for multiple DCE imaging modalities from user-defined hemodynamic parameters. Thus, extensive datasets were simulated for both DCE-CT and EIT, representing different hemodynamic scenarios. Additionally, gamma-variate extensions to account for several physiological effects were detailed in a modality-agnostic manner, and three corresponding fitting strategies, namely nonlinear, linear, and a novel hybrid approach, were implemented and compared on the basis of accuracy of parameter estimation, first pass reconstruction, speed of computation, and failure rate. Main results. As a result, we found the linear method to be the most modality-dependent, exhibiting the greatest bias, variance and failure rates, although remaining the fastest alternative. The hybrid method at least matches the state-of-the-art nonlinear method's accuracy, while improving its robustness and speed by 10 times. Significance. Our research suggests that the hybrid method may bring noteworthy accuracy and efficiency improvements in handling the high-dimensionality of DCE imaging in general, being a step towards real-time processing. Moreover, our generative model presents a potential asset to produce benchmarking and data augmentation datasets across modalities. [ABSTRACT FROM AUTHOR]

Objective. We introduce a robust image reconstruction algorithm named residual-guided Golub–Kahan iterative reconstruction technique (RGIRT) designed for sparse-view computed tomography (CT), which aims at high-fidelity image reconstruction from a limited number of projection views. Approach. RGIRT utilizes an inner-outer dual iteration framework, with a flexible least square QR (FLSQR) algorithm implemented in the inner iteration and a restarted iterative scheme applied in the outer iteration. The inner FLSQR employs a flexible Golub–Kahan bidiagonalization method to reduce the size of the inverse problem, and a weighted generalized cross-validation method to adaptively estimate the regularization hyper-parameter. The inner iteration efficiently yields the intermediate reconstruction result, while the outer iteration minimizes the residual and refines the solution by using the result obtained from the inner iteration. Main results. The reconstruction performance of RGIRT is evaluated and compared to other reference methods (FBPConvNet, SART-TV, and FLSQR) using projection data from both numerical phantoms and real experimental Micro-CT data. The experimental findings, from testing various numbers of projection views and different noise levels, underscore the robustness of RGIRT. Meanwhile, theoretical analysis confirms the convergence of residual for our approach. Significance. We propose a robust iterative reconstruction algorithm for x-ray CT scans with sparse views, thereby shortening scanning time and mitigating excessive ionizing radiation exposure to small animals. [ABSTRACT FROM AUTHOR]

Objective. Limited-angle computed tomography (CT) presents a challenge due to its ill-posed nature. In such scenarios, analytical reconstruction methods often exhibit severe artifacts. To tackle this inverse problem, several supervised deep learning-based approaches have been proposed. However, they are constrained by limitations such as generalization issue and the difficulty of acquiring a large amount of paired CT images. Approach. In this work, we propose an iterative neural reconstruction framework designed for limited-angle CT. By leveraging a coordinate-based neural representation, we formulate tomographic reconstruction as a convex optimization problem involving a deep neural network. We then employ differentiable projection layer to optimize this network by minimizing the discrepancy between the predicted and measured projection data. In addition, we introduce a prior-based weight initialization method to ensure the network starts optimization with an informed initial guess. This strategic initialization significantly improves the quality of iterative reconstruction by stabilizing the divergent behavior in ill-posed neural fields. Our method operates in a self-supervised manner, thereby eliminating the need for extensive data. Main results. The proposed method outperforms other iterative and learning-based methods. Experimental results on XCAT and Mayo Clinic datasets demonstrate the effectiveness of our approach in restoring anatomical features as well as structures. This finding was substantiated by visual inspections and quantitative evaluations using NRMSE, PSNR, and SSIM. Moreover, we conduct a comprehensive investigation into the divergent behavior of iterative neural reconstruction, thus revealing its suboptimal convergence when starting from scratch. In contrast, our method consistently produced accurate images by incorporating an initial estimate as informed initialization. Significance. This work showcases the feasibility to reconstruct high-fidelity CT images from limited-angle x-ray projections. The proposed methodology introduces a novel data-free approach to enhance medical imaging, holding promise across various clinical applications. [ABSTRACT FROM AUTHOR]

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches. [ABSTRACT FROM AUTHOR]

Objective. The textures and detailed structures in computed tomography (CT) images are highly desirable for clinical diagnosis. This study aims to expand the current body of work on textures and details preserving convolutional neural networks for low-dose CT (LDCT) image denoising task. Approach. This study proposed a novel multi-scale feature aggregation and fusion network (MFAF-net) for LDCT image denoising. Specifically, we proposed a multi-scale residual feature aggregation module to characterize multi-scale structural information in CT images, which captures regional-specific inter-scale variations using learned weights. We further proposed a cross-level feature fusion module to integrate cross-level features, which adaptively weights the contributions of features from encoder to decoder by using a spatial pyramid attention mechanism. Moreover, we proposed a self-supervised multi-level perceptual loss module to generate multi-level auxiliary perceptual supervision for recovery of salient textures and structures of tissues and lesions in CT images, which takes advantage of abundant semantic information at various levels. We introduced parameters for the perceptual loss to adaptively weight the contributions of auxiliary features of different levels and we also introduced an automatic parameter tuning strategy for these parameters. Main results. Extensive experimental studies were performed to validate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method can achieve better performance on both fine textures preservation and noise suppression for CT image denoising task compared with other competitive convolutional neural network (CNN) based methods. Significance. The proposed MFAF-net takes advantage of multi-scale receptive fields, cross-level features integration and self-supervised multi-level perceptual loss, enabling more effective recovering of fine textures and detailed structures of tissues and lesions in CT images. [ABSTRACT FROM AUTHOR]