Search

Biomedical multi-modality data (also named multi-omics data) refer to data that span different types and derive from multiple sources in clinical practices (e.g. gene sequences, proteomics and histopathological images), which can provide comprehensive perspectives for cancers and generally improve the performance of survival models. However, the performance improvement of multi-modality survival models may be hindered by two key issues as follows: (1) how to learn and fuse modality-sharable and modality-individual representations from multi-modality data; (2) how to explore the potential risk-aware characteristics in each risk subgroup, which is beneficial to risk stratification and prognosis evaluation. Additionally, learning-based survival models generally refer to numerous hyper-parameters, which requires time-consuming parameter setting and might result in a suboptimal solution. In this paper, we propose an adaptive risk-aware sharable and individual subspace learning method for cancer survival analysis. The proposed method jointly learns sharable and individual subspaces from multi-modality data, whereas two auxiliary terms (i.e. intra-modality complementarity and inter-modality incoherence) are developed to preserve the complementary and distinctive properties of each modality. Moreover, it equips with a grouping co-expression constraint for obtaining risk-aware representation and preserving local consistency. Furthermore, an adaptive-weighted strategy is employed to efficiently estimate crucial parameters during the training stage. Experimental results on three public datasets demonstrate the superiority of our proposed model. [ABSTRACT FROM AUTHOR]

High censoring phenomenon usually occurs in cancer prognosis analysis, which, however, would introduce bias for model construction and limit generalization performance. In this paper, we first explore and identify an appropriate censoring range for cancer prognosis evaluation, upon which we present a mix-supervised multiset learning framework to cope with high-censoring data. Specifically, we construct multiple subsets with the specified censoring proportion, followed by a multiset representation learning method to learn subset-specific representations, which equips with adversary integrality preservation and dependency limitation constraints to ensure the unbiasedness of subsets and eliminate the redundancy among subsets, respectively. Furthermore, a mix-supervised multiset fusion model is proposed to estimate the relative survival risk, in which teacher model can make full use of the survival time of uncensored samples and the prognosis-related attributes of censored ones to generate reliable pseudo-labels and latent-space for student model. We evaluate the proposed method on three public datasets, and extensive experimental results demonstrate its superiority. • A mix-supervised multiset learning method for cancer prognosis analysis. • A solution of multiset learning with two constraints to high censoring problem. • Extending the semi-supervised paradigm into the mix-supervised method. • Extensive experiments demonstrate the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Protocatechuic acid (PCA) has a protective effect on alcoholic liver injury, but the role of PCA in type 2 diabetes-induced liver injury is not well known. This study explores the therapeutic effect and potential mechanism of PCA on type 2 diabetes-induced liver injury. An insulin resistance/type 2 diabetic (IR/D) model was established by high-fat diet for 4 weeks + streptozotocin (35 mg/kg; i.p) in male Wistar rats pretreated with or without PCA (15 or 30 mg/kg for 6 d). PCA at 15 and 30 mg/kg significantly upregulated the levels of body weight (BW; 230.2, 257.8 g), high density lipids (22.68, 34.78 mg/dL), glutathione (10.24, 16.21 nmol/mg), superoxide dismutase (21.62, 29.34 U/mg), glucagon-like peptide-1, glucose transporter-4, Wnt1, and β-catenin, while downregulating those of liver weight (LW; 9.4, 6.7 g), BW/LW (4.1, 2.6%), serum glucose (165, 120 mg/dL), serum insulin (13.46, 8.67 μIU/mL), homeostatic model assessment of insulin resistance (5.48, 2.57), total cholesterol (68.52, 54.31 mg/dL), triglycerides (72.15, 59.64 mg/dL), low density lipids (42.18, 30.71), aspartate aminotransferase (54.34 and 38.68 U/L), alanine aminotransferase (42.87, 29.98 U/L), alkaline phosphatase (210.16, 126.47 U/L), malondialdehyde (16.52, 10.35), pro-inflammatory markers (tumor necrosis factor α (TNF-α (149.67, 120.33 pg/mg)) , IL-6 (89.79, 73.69 pg/mg) and IL-1β (49.67, 38.73 pg/mg)), nuclear factor kappa B (NF-κB), and interleukin-1β, and ameliorated the abnormal pathological changes in IR/D rats. PCA mitigates the IR, lipid accumulation, oxidative stress, and inflammation in liver tissues of IR/D rats by modulating the NF-κB and Wnt1/β-catenin pathways. [ABSTRACT FROM AUTHOR]

Objectives: To predict sentinel lymph node (SLN) metastasis in breast cancer patients using radiomics based on T2-weighted fat suppression (T2-FS) and diffusion-weighted MRI (DWI).Methods: We enrolled 146 patients with histologically proven breast cancer. All underwent pretreatment T2-FS and DWI MRI scan. In all, 10,962 texture and four non-texture features were extracted for each patient. The 0.623 + bootstrap method and the area under the curve (AUC) were used to select the features. We constructed ten logistic regression models (orders of 1-10) based on different combination of image features using stepwise forward method.Results: For T2-FS, model 10 with ten features yielded the highest AUC of 0.847 in the training set and 0.770 in the validation set. For DWI, model 8 with eight features reached the highest AUC of 0.847 in the training set and 0.787 in the validation set. For joint T2-FS and DWI, model 10 with ten features yielded an AUC of 0.863 in the training set and 0.805 in the validation set.Conclusions: Full utilisation of breast cancer-specific textural features extracted from anatomical and functional MRI images improves the performance of radiomics in predicting SLN metastasis, providing a non-invasive approach in clinical practice.Key Points: • SLN biopsy to access breast cancer metastasis has multiple complications. • Radiomics uses features extracted from medical images to characterise intratumour heterogeneity. • We combined T 2 -FS and DWI textural features to predict SLN metastasis non-invasively. [ABSTRACT FROM AUTHOR]

In this experiment, we used streptozotocin (STZ) to establish a model of gestational diabetes mellitus (GDM) rats, where Zuogui Wan was given to GDM rats. After pregnancy, offspring rats were divided into 4 groups: control group, high fat and sugar as the control group, GDM group, and Zuogui Wan GDM group. Rats in high fat and sugar as the control group, GDM group, and Zuogui Wan GDM group were fed with high fat and sugar diet. Rats in control group were fed the basic diet. The means of 2hPG were higher than 7.8 mmol·L−1 and lower than 11.1 mmol·L−1 on the rats of GDM group on week 15, and IGT models were successful. Body weight, abdominal fat weight, the ratio of abdominal fat weight and body weight, fasting plasma glucose, 2hPG, insulin, leptin, total cholesterol, and low density lipoprotein (LDL) of Zuogui Wan GDM group were significantly lower than GDM group. The level of adiponectin in Zuogui Wan GDM group was significantly higher than GDM group. And we concluded that giving Zuogui Wan to GDM rats can have a preventive effect on the offsprings’ IGT induced by high fat and sugar diet. [ABSTRACT FROM AUTHOR]

Purpose: A content-based image retrieval (CBIR) method for T1-weighted contrast-enhanced MRI (CE-MRI) images of brain tumors is presented for diagnosis aid. The method is thoroughly evaluated on a large image dataset. Methods: Using the tumor region as a query, the authors' CBIR system attempts to retrieve tumors of the same pathological category. Aside from commonly used features such as intensity, texture, and shape features, the authors use a margin information descriptor (MID), which is capable of describing the characteristics of tissue surrounding a tumor, for representing image contents. In addition, the authors designed a distance metric learning algorithm called Maximum mean average Precision Projection (MPP) to maximize the smooth approximated mean average precision (mAP) to optimize retrieval performance. Results: The effectiveness of MID and MPP algorithms was evaluated using a brain CE-MRI dataset consisting of 3108 2D scans acquired from 235 patients with three categories of brain tumors (meningioma, glioma, and pituitary tumor). By combining MID and other features, the mAP of retrieval increased by more than 6% with the learned distance metrics. The distance metric learned by MPP significantly outperformed the other two existing distance metric learning methods in terms of mAP. The CBIR system using the proposed strategies achieved a mAP of 87.3% and a precision of 89.3% when top 10 images were returned by the system. Compared with scale-invariant feature transform, the MID, which uses the intensity profile as descriptor, achieves better retrieval performance. Conclusions: Incorporating tumor margin information represented by MID with the distance metric learned by the MPP algorithm can substantially improve the retrieval performance for brain tumors in CE-MRI. [ABSTRACT FROM AUTHOR]

Abstract: Bayesian methods have been widely applied to the ill-posed problem of image reconstruction. Typically the prior information of the objective image is needed to produce reasonable reconstructions. In this paper, we propose a novel generalized Gibbs prior (GG-Prior), which exploits the basic affinity structure information in an image. The motivation for using the GG-Prior is that it has been shown to be effective noise suppression, while also maintaining sharp edges without oscillations. This feature makes it particularly attractive for the reconstruction of positron emission tomography (PET) where the aim is to identify the shape of objects from the background by sharp edges. We show that the standard paraboloidal surrogate coordinate ascent (PSCA) algorithm can be modified to incorporate the GG-Prior using a local linearized scheme in each iteration process. The proposed GG-Prior MAP reconstruction algorithm based on PSCA has been tested on simulated, real phantom data. Comparison studies with conventional filtered backprojection (FBP) method and Huber prior clearly demonstrate that the proposed GG-Prior performs better in lowering the noise, preserving the image edge and in higher signal noise ratio (SNR) condition. [Copyright &y& Elsevier]

Objectives: To develop an ensemble multi-task deep learning (DL) framework for automatic and simultaneous detection, segmentation, and classification of primary bone tumors (PBTs) and bone infections based on multi-parametric MRI from multi-center. Methods: This retrospective study divided 749 patients with PBTs or bone infections from two hospitals into a training set (N = 557), an internal validation set (N = 139), and an external validation set (N = 53). The ensemble framework was constructed using T1-weighted image (T1WI), T2-weighted image (T2WI), and clinical characteristics for binary (PBTs/bone infections) and three-category (benign/intermediate/malignant PBTs) classification. The detection and segmentation performances were evaluated using Intersection over Union (IoU) and Dice score. The classification performance was evaluated using the receiver operating characteristic (ROC) curve and compared with radiologist interpretations. Result: On the external validation set, the single T1WI-based and T2WI-based multi-task models obtained IoUs of 0.71 ± 0.25/0.65 ± 0.30 for detection and Dice scores of 0.75 ± 0.26/0.70 ± 0.33 for segmentation. The framework achieved AUCs of 0.959 (95%CI, 0.955–1.000)/0.900 (95%CI, 0.773–0.100) and accuracies of 90.6% (95%CI, 79.7–95.9%)/78.3% (95%CI, 58.1–90.3%) for the binary/three-category classification. Meanwhile, for the three-category classification, the performance of the framework was superior to that of three junior radiologists (accuracy: 65.2%, 69.6%, and 69.6%, respectively) and comparable to that of two senior radiologists (accuracy: 78.3% and 78.3%). Conclusion: The MRI-based ensemble multi-task framework shows promising performance in automatically and simultaneously detecting, segmenting, and classifying PBTs and bone infections, which was preferable to junior radiologists. Clinical relevance statement: Compared with junior radiologists, the ensemble multi-task deep learning framework effectively improves differential diagnosis for patients with primary bone tumors or bone infections. This finding may help physicians make treatment decisions and enable timely treatment of patients. Key Points: • The ensemble framework fusing multi-parametric MRI and clinical characteristics effectively improves the classification ability of single-modality models. • The ensemble multi-task deep learning framework performed well in detecting, segmenting, and classifying primary bone tumors and bone infections. • The ensemble framework achieves an optimal classification performance superior to junior radiologists' interpretations, assisting the clinical differential diagnosis of primary bone tumors and bone infections. [ABSTRACT FROM AUTHOR]

Deep learning methods, especially convolutional neural networks, have been successfully applied to lesion segmentation in breast ultrasound (BUS) images. However, pattern complexity and intensity similarity between the surrounding tissues (i.e., background) and lesion regions (i.e., foreground) bring challenges for lesion segmentation. Considering that such rich texture information is contained in background, very few methods have tried to explore and exploit background-salient representations for assisting foreground segmentation. Additionally, other characteristics of BUS images, i.e., 1) low-contrast appearance and blurry boundary, and 2) significant shape and position variation of lesions, also increase the difficulty in accurate lesion segmentation. In this paper, we present a saliency-guided morphology-aware U-Net (SMU-Net) for lesion segmentation in BUS images. The SMU-Net is composed of a main network with an additional middle stream and an auxiliary network. Specifically, we first propose generation of saliency maps which incorporate both low-level and high-level image structures, for foreground and background. These saliency maps are then employed to guide the main network and auxiliary network for respectively learning foreground-salient and background-salient representations. Furthermore, we devise an additional middle stream which basically consists of background-assisted fusion, shape-aware, edge-aware and position-aware units. This stream receives the coarse-to-fine representations from the main network and auxiliary network for efficiently fusing the foreground-salient and background-salient features and enhancing the ability of learning morphological information for network. Extensive experiments on five datasets demonstrate higher performance and superior robustness to the scale of dataset than several state-of-the-art deep learning approaches in breast lesion segmentation in ultrasound image. [ABSTRACT FROM AUTHOR]

The fusion of multi-modal data (e.g., magnetic resonance imaging (MRI) and positron emission tomography (PET)) has been prevalent for accurate identification of Alzheimer’s disease (AD) by providing complementary structural and functional information. However, most of the existing methods simply concatenate multi-modal features in the original space and ignore their underlying associations which may provide more discriminative characteristics for AD identification. Meanwhile, how to overcome the overfitting issue caused by high-dimensional multi-modal data remains appealing. To this end, we propose a relation-induced multi-modal shared representation learning method for AD diagnosis. The proposed method integrates representation learning, dimension reduction, and classifier modeling into a unified framework. Specifically, the framework first obtains multi-modal shared representations by learning a bi-directional mapping between original space and shared space. Within this shared space, we utilize several relational regularizers (including feature-feature, feature-label, and sample-sample regularizers) and auxiliary regularizers to encourage learning underlying associations inherent in multi-modal data and alleviate overfitting, respectively. Next, we project the shared representations into the target space for AD diagnosis. To validate the effectiveness of our proposed approach, we conduct extensive experiments on two independent datasets (i.e., ADNI-1 and ADNI-2), and the experimental results demonstrate that our proposed method outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

MRI of effective transverse relaxation rate (R2*) measurement is a reliable method for liver iron concentration quantification. However, R2* mapping can be degraded by noise, especially in the case of iron overload. This study aimed to develop a deep learning method for MRI R2* relaxometry of an iron-loaded liver using a two-stage cascaded neural network. The proposed method, named CadamNet, combines two convolutional neural networks separately designed for image denoising and parameter mapping into a cascade framework, and the physics-based R2* decay model was incorporated in training the mapping network to enforce data consistency further. CadamNet was trained using simulated liver data with Rician noise, which was constructed from clinical liver data. The performance of CadamNet was quantitatively evaluated on simulated data with varying noise levels as well as clinical liver data and compared with the single-stage parameter mapping network (MappingNet) and two conventional model-based R2* mapping methods. CadamNet consistently achieved high-quality R2* maps and outperformed MappingNet at varying noise levels. Compared with conventional R2* mapping methods, CadamNet yielded R2* maps with lower errors, higher quality, and substantially increased efficiency. In conclusion, the proposed CadamNet enables accurate and efficient iron-loaded liver R2* mapping, especially in the presence of severe noise. [ABSTRACT FROM AUTHOR]

Purpose: Automated measurement of spine indices on axial magnetic resonance (MR) images plays a significant role in lumbar spinal stenosis diagnosis. Existing direct spine indices measurement approaches fail to explicitly focus on the task‐specific region or feature channel with the additional information for guiding. We aim to achieve accurate spine indices measurement by introducing the guidance of the segmentation task. Methods: In this paper, we propose a segmentation‐guided regression network (SGRNet) to achieve automated spine indices measurement. SGRNet consists of a segmentation path for generating the spine segmentation prediction and a regression path for producing spine indices estimation. The segmentation path is a U‐Net‐like network which includes a segmentation encoder and a decoder which generates multilevel segmentation features and segmentation prediction. The proposed segmentation‐guided attention module (SGAM) in the regression encoder extracts the attention‐aware regression feature under the guidance of the segmentation feature. Based on the attention‐aware regression feature, a fully connected layer is utilized to output the accurate spine indices estimation. Results: Experiments on the open‐access Lumbar Spine MRI data set show that SGRNet achieves state‐of‐the‐art performance with a mean absolute error of 0.49 mm and mean Pearson correlation coefficient of 0.956 for four indices estimation. Conclusions: The proposed SGAM in SGRNet is capable of improving the performance of spine indices measurement by focusing on the task‐specific region and feature channel under the guidance of the segmentation task. [ABSTRACT FROM AUTHOR]

The three‐dimensional (3D) anatomy of Kambin's triangle is crucial for surgical planning in minimally invasive spine surgery via the transforaminal approach. Few pieces of research have, however, used image segmentation to explore the 3D reconstruction of Kambin's triangle. This study aimed to develop a new method of 3D reconstruction of Kambin's triangle based on automated magnetic resonance image (MRI) segmentation of the lumbar spinal structures. An experienced (>5 years) "ground truth" spinal pain physician meticulously segmented and labeled spinal structures (e.g., bones, dura mater, discs, and nerve roots) on MRI. Subsequently, a 3D U‐Net algorithm was developed for automatically segmenting lumbar spinal structures for the 3D reconstruction of Kambin's triangle. The Dice similarity coefficient (DSC), precision, recall, and the area of Kambin's triangle were used to assess anatomical performance. The automatic segmentation of all spinal structures at the L4/L5 levels and L5/S1 levels resulted in good performance: DSC = 0.878/0.883, precision = 0.889/0.890, recall = 0.873/0.882. Furthermore, the area measurements of Kambin's triangle revealed no significant difference between ground truth and automatic segmentation (p = 0.333 at the L4/L5 level, p = 0.302 at the L5/S1 level). The 3D U‐Net model used in this study performed well in terms of simultaneous segmentation of multi‐class spinal structures (including bones, dura mater, discs, and nerve roots) on MRI, allowing for accurate 3D reconstruction of Kambin's triangle. [ABSTRACT FROM AUTHOR]

Macrovascular invasion (MaVI) is a major threat to survival in hepatocellular carcinoma (HCC), which should be treated as early as possible to ensure safety and efficacy. In this aspect, MaVI prediction can be helpful. However, MaVI prediction is difficult because of the inter-class similarity and intra-class variation of HCC in computed tomography (CT) images. Moreover, existing methods fail to include clinical priori knowledge associated with HCC, leading to incomprehensive information extraction. In this paper, we proposed a prior knowledge-aware fusion network (PKAFnet) to accurately achieve MaVI prediction in CT images. First, a perception module was presented to extract features related to tumor marginal heterogeneity in the graph domain, which contributed to rotation invariance and captured intensity variations of tumor margin. Second, a tumor segmentation network was built to obtain global information of a 3D tumor image and information associated with tumor internal heterogeneity in the image domain. Finally, multi-domain features associated with the tumor margin and tumor region were combined by using a multi-domain attentional feature fusion module. Thus, by incorporating MaVI-related prior knowledge, our PKAFnet can alleviate overfitting, which can improve the discriminative ability. The proposed PKAFnet was validated on a multi-center dataset, and remarkable performance was achieved in an independent testing set. Moreover, the interpretability of perception module and segmentation network were presented in our paper, which illustrated the effectiveness and credibility of PKAFnet. Therefore, the proposed method showed great application potential for MaVI prediction. [ABSTRACT FROM AUTHOR]

Accurate processing and analysis of non-human primate (NHP) brain magnetic resonance imaging (MRI) serves an indispensable role in understanding brain evolution, development, aging, and diseases. Despite the accumulation of diverse NHP brain MRI datasets at various developmental stages and from various imaging sites/scanners, existing computational tools designed for human MRI typically perform poor on NHP data, due to huge differences in brain sizes, morphologies, and imaging appearances across species, sites, and ages, highlighting the imperative for NHP-specialized MRI processing tools. To address this issue, in this paper, we present a robust, generic, and fully automated computational pipeline, called non-human primates Brain Extraction and Segmentation Toolbox (nBEST), whose main functionality includes brain extraction, non-cerebrum removal, and tissue segmentation. Building on cutting-edge deep learning techniques by employing lifelong learning to flexibly integrate data from diverse NHP populations and innovatively constructing 3D U-NeXt architecture, nBEST can well handle structural NHP brain MR images from multi-species, multi-site, and multi-developmental-stage (from neonates to the elderly). We extensively validated nBEST based on, to our knowledge, the largest assemblage dataset in NHP brain studies, encompassing 1,469 scans with 11 species (e.g., rhesus macaques, cynomolgus macaques, chimpanzees, marmosets, squirrel monkeys, etc.) from 23 independent datasets. Compared to alternative tools, nBEST outperforms in precision, applicability, robustness, comprehensiveness, and generalizability, greatly benefiting downstream longitudinal, cross-sectional, and cross-species quantitative analyses. We have made nBEST an open-source toolbox (https://github.com/TaoZhong11/nBEST) and we are committed to its continual refinement through lifelong learning with incoming data to greatly contribute to the research field. • We proposed nBEST, a deep-learning toolbox for processing MR images of non-human primate brains. • nBEST leverages lifelong learning and 3D U-NeXt models, performing brain extraction, non-cerebrum removal, and tissue segmentation. • Validated with 1,400+ scans from 11 species, nBEST shows extensive applicabilit. • nBEST is available online with a user manual. [ABSTRACT FROM AUTHOR]

• Model-based MR parameter mapping network (MMPM-Net). • Unrolled ADMM algorithm with deep denoiser prior. • Superior performance for R 2 and R 1 mapping tasks. • Superior generalization across substantial variations in acquisition settings. • A generic framework that can be readily extended to other parameter mapping tasks. Deep learning methods show great potential for the efficient and precise estimation of quantitative parameter maps from multiple magnetic resonance (MR) images. Current deep learning-based MR parameter mapping (MPM) methods are mostly trained and tested using data with specific acquisition settings. However, scan protocols usually vary with centers, scanners, and studies in practice. Thus, deep learning methods applicable to MPM with varying acquisition settings are highly required but still rarely investigated. In this work, we develop a model-based deep network termed MMPM-Net for robust MPM with varying acquisition settings. A deep learning-based denoiser is introduced to construct the regularization term in the nonlinear inversion problem of MPM. The alternating direction method of multipliers is used to solve the optimization problem and then unrolled to construct MMPM-Net. The variation in acquisition parameters can be addressed by the data fidelity component in MMPM-Net. Extensive experiments are performed on R 2 mapping and R 1 mapping datasets with substantial variations in acquisition settings, and the results demonstrate that the proposed MMPM-Net method outperforms other state-of-the-art MR parameter mapping methods both qualitatively and quantitatively. [Display omitted] [ABSTRACT FROM AUTHOR]

Purpose: Automated retinal vessel segmentation is crucial to the early diagnosis and treatment of ophthalmological diseases. Many deep‐learning‐based methods have shown exceptional success in this task. However, current approaches are still inadequate in challenging vessels (e.g., thin vessels) and rarely focus on the connectivity of vessel segmentation. Methods: We propose using an error discrimination network (D) to distinguish whether the vessel pixel predictions of the segmentation network (S) are correct, and S is trained to obtain fewer error predictions of D. Our method is similar to, but not the same as, the generative adversarial network. Three types of vessel samples and corresponding error masks are used to train D, as follows: (1) vessel ground truth; (2) vessel segmented by S; (3) artificial thin vessel error samples that further improve the sensitivity of D to wrong small vessels. As an auxiliary loss function of S, D strengthens the supervision of difficult vessels. Optionally, we can use the errors predicted by D to correct the segmentation result of S. Results: Compared with state‐of‐the‐art methods, our method achieves the highest scores in sensitivity (86.19%, 86.26%, and 86.53%) and G‐Mean (91.94%, 91.30%, and 92.76%) on three public datasets, namely, STARE, DRIVE, and HRF. Our method also maintains a competitive level in other metrics. On the STARE dataset, the F1‐score and area under the receiver operating characteristic curve (AUC) of our method rank second and first, respectively, reaching 84.51% and 98.97%. The top scores of the three topology‐relevant metrics (Conn, Inf, and Cor) demonstrate that the vessels extracted by our method have excellent connectivity. We also validate the effectiveness of error discrimination supervision and artificial error sample training through ablation experiments. Conclusions: The proposed method provides an accurate and robust solution for difficult vessel segmentation. [ABSTRACT FROM AUTHOR]

The lumen of aortic dissection (AD) has important clinical value for preoperative diagnosis, interoperative intervention, and post-operative evaluation of AD diseases. AD segmentation is challenging because (i) fitting its irregular profile by using traditional models is difficult, and (ii) the size of the AD image is usually so big that many algorithms have to perform down-sampling to reduce the computational burden, thereby reducing the resolution of the result. In this paper, an automatic AD segmentation algorithm, in which a 3D mesh is gradually moved to the surface of AD based on the offset estimated by a deep mesh deformation module, is presented. AD morphology is used to constrain the initial mesh and guide the deformation, which improves the efficiency of the deep network and avoids down-sampling. Moreover, a stepwise regression strategy is introduced to solve the mesh folding problem and improve the uniformity of the mesh points. On an AD database that involves 35 images, the proposed method obtains the mean Dice of 94.12% and symmetric 95% Hausdorff distance of 2.85 mm, which outperforms five state-of-the-art AD segmentation methods. The average processing time is 16.6 s, and the memory used to train the network is only 0.36 GB, indicating that this method is easy to apply in clinical practice. [ABSTRACT FROM AUTHOR]

Ischemic stroke is the most common type of stroke, ranked as the second leading cause of death worldwide. The Alberta Stroke Program Early CT Score (ASPECTS) is considered as a systematic method of assessing ischemic change on non‐contrast CT scans (NCCT) of acute ischemic stroke (AIS) patients, while still suffering from the requirement of experts' experience and also the inconsistent results between readers. In this study, we proposed an automated ASPECTS method to utilize the powerful learning ability of neural networks for objectively scoring CT scans of AIS patients. First, we proposed to use the CT perfusion (CTP) from one‐stop stroke imaging to provide the golden standard of ischemic regions for ASPECTS scoring. Second, we designed an asymmetry network to capture features when comparing the left and right sides for each ASPECTS region to estimate its ischemic status. Third, we performed experiments in a large main dataset of 870 patients, as well as an independent testing dataset consisting of 207 patients with radiologists' scorings. Experimental results show that our network achieved remarkable performance, as sensitivity and accuracy of 93.7 and 92.4% in the main dataset, and 95.5 and 91.3% in the independent testing dataset, respectively. In the latter dataset, our analysis revealed a high positive correlation between the ASPECTS score and the prognosis of patients in 90DmRs. Also, we found ASPECTS score is a good indicator of the size of CTP core volume of an infraction. The proposed method shows its potential for automated ASPECTS scoring on NCCT images. [ABSTRACT FROM AUTHOR]

Background: Notch volume is associated with anterior cruciate ligament (ACL) injury. Manual tracking of intercondylar notch on MR images is time-consuming and laborious. Deep learning has become a powerful tool for processing medical images. This study aims to develop an MRI segmentation model of intercondylar fossa based on deep learning to automatically measure notch volume, and explore its correlation with ACL injury.Methods: The MRI data of 363 subjects (311 males and 52 females) with ACL injuries incurred during non-contact sports and 232 subjects (147 males and 85 females) with intact ACL were retrospectively analyzed. Each layer of intercondylar fossa was manually traced by radiologists on axial MR images. Notch volume was then calculated. We constructed an automatic segmentation system based on the architecture of Res-UNet for intercondylar fossa and used dice similarity coefficient (DSC) to compare the performance of segmentation systems by different networks. Unpaired t-test was performed to determine differences in notch volume between ACL-injured and intact groups, and between males and females.Results: The DSCs of intercondylar fossa based on different networks were all more than 0.90, and Res-UNet showed the best performance. The notch volume was significantly lower in the ACL-injured group than in the control group (6.12 ± 1.34 cm3 vs. 6.95 ± 1.75 cm3, P < 0.001). Females had lower notch volume than males (5.41 ± 1.30 cm3 vs. 6.76 ± 1.51 cm3, P < 0.001). Males and females who had ACL injuries had smaller notch than those with intact ACL (p < 0.001 and p < 0.005). Men had larger notches than women, regardless of the ACL injuries (p < 0.001).Conclusion: Using a deep neural network to segment intercondylar fossa automatically provides a technical support for the clinical prediction and prevention of ACL injury and re-injury after surgery. [ABSTRACT FROM AUTHOR]

This study aims to investigate the quality difference of short echo time (TE) breathhold 1H magnetic resonance spectroscopy (MRS) of the liver at 3.0T using the body and phased array coils, respectively. In total, 20 pairs of single-voxel proton spectra of the liver were acquired at 3.0T using the phased array and body coils as receivers. Consecutive stacks of breathhold spectra were acquired using the point resolved spectroscopy (PRESS) technique at a short TE of 30 ms and a repetition time (TR) of 1500 ms. The first spectroscopy sequence was “copied” for the second acquisition to ensure identical voxel positioning. The MRS prescan adjustments of shimming and water suppression, signal-to noise ratio (SNR), and major liver quantitative information were compared between paired spectra. Theoretical calculation of the SNR and homogeneity of the region of interest (ROI, 2 cm×2 cm×2 cm) using different coils loaded with 3D liver electromagnetic model of real human body was implemented in the theoretical analysis. The theoretical analysis showed that, inside the ROI, the SNR of the phase array coil was 2.8387 times larger than that of body coil and the homogeneity of the phase array coil and body coil was 80.10% and 93.86%, respectively. The experimental results showed excellent correlations between the paired data (all r > 0.86). Compared with the body coil group, the phased array group had slightly worse shimming effect and better SNR (all P values < .01). The discrepancy of the line width because of the different coils was approximately 0.8 Hz (0.00625 ppm). No significant differences of the major liver quantitative information of Cho/Lip2 height, Cho/Lip2 area, and lipid content were observed (all P values >0.05). The theoretical analysis and clinical experiment showed that the phased array coil was superior to the body coil with respect to 3.0T breathhold hepatic proton MRS. [ABSTRACT FROM AUTHOR]

Personal recognition using palm–vein patterns has emerged as a promising alternative for human recognition because of its uniqueness, stability, live body identification, flexibility, and difficulty to cheat. With the expanding application of palm–vein pattern recognition, the corresponding growth of the database has resulted in a long response time. To shorten the response time of identification, this paper proposes a simple and useful classification for palm–vein identification based on principal direction features. In the registration process, the Gaussian-Radon transform is adopted to extract the orientation matrix and then compute the principal direction of a palm–vein image based on the orientation matrix. The database can be classified into six bins based on the value of the principal direction. In the identification process, the principal direction of the test sample is first extracted to ascertain the corresponding bin. One-by-one matching with the training samples is then performed in the bin. To improve recognition efficiency while maintaining better recognition accuracy, two neighborhood bins of the corresponding bin are continuously searched to identify the input palm–vein image. Evaluation experiments are conducted on three different databases, namely, PolyU, CASIA, and the database of this study. Experimental results show that the searching range of one test sample in PolyU, CASIA and our database by the proposed method for palm–vein identification can be reduced to 14.29%, 14.50%, and 14.28%, with retrieval accuracy of 96.67%, 96.00%, and 97.71%, respectively. With 10,000 training samples in the database, the execution time of the identification process by the traditional method is 18.56 s, while that by the proposed approach is 3.16 s. The experimental results confirm that the proposed approach is more efficient than the traditional method, especially for a large database. [ABSTRACT FROM AUTHOR]

Diffusion kurtosis imaging (DKI) has been shown to be valuable in a wide range of neuroscientific and clinical applications. However, reliable estimation of DKI tensors is often compromised by noise, especially for the kurtosis tensor (KT). Here, we propose a joint denoising and estimating framework that integrates multiple sources of prior information, including nonlocal structural self-similarity (NSS), local spatial smoothness (LSS), physical relevance (PR) of the DKI model, and noise characteristics of magnitude diffusion MRI (dMRI) images for improved estimation of DKI tensors. The local and nonlocal spatial smoothing constraints are complementary to each other, making the proposed framework highly effective in reducing the noise fluctuations on DKI tensors, especially KT. As an additional refinement, we propose to impose a physically relevant constraint within our joint denoising and estimation framework. We further adopt the first-moment noise-corrected fitting model (M1NCM) to remove the noncentral ${\chi }$ -distribution noise bias. The effectiveness of integrating multiple sources of priors into the joint framework is verified by comparing the proposed M1NCM-NSS-LSS-PR method with various versions of M1NCM-based estimators and two state-of-the-art methods. Results show that the proposed method outperformed the compared methods in simulations and in-vivo dMRI datasets of both spatially stationary and nonstationary noise distributions. The in-vivo experiments also show that the proposed M1NCM-NSS-LSS-PR method was robust to the number of diffusion directions. [ABSTRACT FROM AUTHOR]

Automatic and accurate dose distribution prediction plays an important role in radiotherapy plan. Although previous methods can provide promising performance, most methods did not consider beam-shaped radiation of treatment delivery in clinical practice. This leads to inaccurate prediction, especially on beam paths. To solve this problem, we propose a beam-wise dose composition learning (BDCL) method for dose prediction in the context of head and neck (H&N) radiotherapy plan. Specifically, a global dose network is first utilized to predict coarse dose values in the whole-image space. Then, we propose to generate individual beam masks to decompose the coarse dose distribution into multiple field doses, called beam voters, which are further refined by a subsequent beam dose network and reassembled to form the final dose distribution. In particular, we design an overlap consistency module to keep the similarity of high-level features in overlapping regions between different beam voters. To make the predicted dose distribution more consistent with the real radiotherapy plan, we also propose a dose-volume histogram (DVH) calibration process to facilitate feature learning in some clinically concerned regions. We further apply an edge enhancement procedure to enhance the learning of the extracted feature from the dose falloff regions. Experimental results on a public H&N cancer dataset from the AAPM OpenKBP challenge show that our method achieves superior performance over other state-of-the-art approaches by significant margins. Source code is released at https://github.com/TL9792/BDCLDosePrediction. • Proposed beam-wise dose composition learning method for dose prediction. • Proposed beam mask generator for producing beam masks as geometric prior knowledge. • Proposing DVH calibration to enhance ROI prediction accuracy. • Applied edge enhancement for learning features from dose falloff. • Evaluated on dataset from OpenKBP challenge, our method shows superior performance. [ABSTRACT FROM AUTHOR]

The integrative analysis of complementary phenotype information contained in multi-modality data (e.g., histopathological images and genomic data) has advanced the prognostic evaluation of cancers. However, multi-modality based prognosis analysis confronts two challenges: (1) how to explore underlying relations inherent in different modalities data for learning compact and discriminative multi-modality representations; (2) how to take full consideration of incomplete multi-modality data for constructing accurate and robust prognostic model, since a host of complete multi-modality data are not always available. Additionally, many existing multi-modality based prognostic methods commonly ignore relevant clinical variables (e.g., grade and stage), which, however, may provide supplemental information to promote the performance of model. In this paper, we propose a relation-aware shared representation learning method for prognosis analysis of cancers, which makes full use of clinical information and incomplete multi-modality data. The proposed method learns multi-modal shared space tailored for prognostic model via a dual mapping. Within the shared space, it equips with relational regularizers to explore the potential relations (i.e., feature-label and feature-feature relations) among multi-modality data for inducing discriminatory representations and simultaneously obtaining extra sparsity for alleviating overfitting. Moreover, it regresses and incorporates multiple auxiliary clinical attributes with dynamic coefficients to meliorate performance. Furthermore, in training stage, a partial mapping strategy is employed to extend and train a more reliable model with incomplete multi-modality data. We have evaluated our method on three public datasets derived from The Cancer Genome Atlas (TCGA) project, and the experimental results demonstrate the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Purpose: Dynamic contrast‐enhanced MRI (DCE‐MRI) registration is a challenging task because of the effect of remarkable intensity changes caused by contrast agent injections. Unrealistic deformation usually occurs by using traditional intensity‐based algorithms. To alleviate the effect of contrast agent on registration, we proposed a DCE‐MRI registration strategy and investigated the registration performance on the clinical DCE‐MRI time series of liver. Method: We reconstructed the time–intensity curves of the contrast agent through sparse representation with a predefined dictionary whose columns were the time–intensity curves with high correlations with respect to a preselected contrast agent curve. After reshaping 1D‐reconstructed contrast agent time–intensity curves into a 4D contrast agent time series, we aligned the original time series to the reconstructed contrast agent time series through traditional free‐form deformation (FFD) registration scheme combined with a residual complexity (RC) similarity and an iterative registration strategy. This study included the DCE‐MRI time series of 20 patients with liver cancer. Results: Qualitatively, the time‐cut images and subtraction images of different registration methods did not obviously differ. Quantitatively, the mean (standard deviation) of temporal intensity smoothness of all the patients achieved 54.910 (18.819), 54.609 (18.859), and 53.391 (19.031) in FFD RC, RDDR, Zhou et al.'s method and the proposed method, respectively. The mean (standard deviation) of changes in the lesion volume were 0.985 (0.041), 0.983 (0.041), 0.981 (0.046), and 0.989 (0.036) in FFD RC, RDDR, Zhou et al.'s method and the proposed method. Conclusion: Our proposed method would be an effective registration strategy for DCE‐MRI time series, and its performance was comparable with that of three advanced registration methods. [ABSTRACT FROM AUTHOR]

Purpose: In current computed tomography (CT) examinations, the associated x-ray radiation dose is of a significant concern to patients and operators. A simple and cost-effective means to perform the examinations is to lower the milliampere-seconds (mAs) or kVp parameter (or delivering less x-ray energy to the body) as low as reasonably achievable in data acquisition. However, lowering the mAs parameter will unavoidably increase data noise and the noise would propagate into the CT image if no adequate noise control is applied during image reconstruction. Since a normal-dose high diagnostic CT image scanned previously may be available in some clinical applications, such as CT perfusion imaging and CT angiography (CTA), this paper presents an innovative way to utilize the normal-dose scan as a priori information to induce signal restoration of the current low-dose CT image series.Methods: Unlike conventional local operations on neighboring image voxels, nonlocal means (NLM) algorithm utilizes the redundancy of information across the whole image. This paper adapts the NLM to utilize the redundancy of information in the previous normal-dose scan and further exploits ways to optimize the nonlocal weights for low-dose image restoration in the NLM framework. The resulting algorithm is called the previous normal-dose scan induced nonlocal means (ndiNLM). Because of the optimized nature of nonlocal weights calculation, the ndiNLM algorithm does not depend heavily on image registration between the current low-dose and the previous normal-dose CT scans. Furthermore, the smoothing parameter involved in the ndiNLM algorithm can be adaptively estimated based on the image noise relationship between the current low-dose and the previous normal-dose scanning protocols.Results: Qualitative and quantitative evaluations were carried out on a physical phantom as well as clinical abdominal and brain perfusion CT scans in terms of accuracy and resolution properties. The gain by the use of the previous normal-dose scan via the presented ndiNLM algorithm is noticeable as compared to a similar approach without using the previous normal-dose scan.Conclusions: For low-dose CT image restoration, the presented ndiNLM method is robust in preserving the spatial resolution and identifying the low-contrast structure. The authors can draw the conclusion that the presented ndiNLM algorithm may be useful for some clinical applications such as in perfusion imaging, radiotherapy, tumor surveillance, etc. [ABSTRACT FROM AUTHOR]

The spatial resolution of photoacoustic tomography (PAT) can be characterized by the point spread function (PSF) of the imaging system. Due to the tomographic detection geometry, the PAT image degradation model could be generally described by using spatially variant PSFs. Deconvolution of the PAT image with these PSFs could restore image resolution and recover object details. Previous PAT image restoration algorithms assume that the degraded images can be restored by either a single uniform PSF, or some blind estimation of the spatially variant PSFs. In this work, we propose a PAT image restoration method to improve image quality and resolution based on experimentally measured spatially variant PSFs. Using photoacoustic absorbing microspheres, we design a rigorous PSF measurement procedure, and successfully acquire a dense set of spatially variant PSFs for a commercial cross-sectional PAT system. A pixel-wise PSF map is further obtained by employing a multi-Gaussian-based fitting and interpolation algorithm. To perform image restoration, an optimization-based iterative restoration model with two kinds of regularizations is proposed. We perform phantom and in vivo mice imaging experiments to verify the proposed method, and the results show significant image quality and resolution improvement. [ABSTRACT FROM AUTHOR]

Purpose: Breast ultrasound (BUS) image segmentation plays a crucial role in computer‐aided diagnosis systems for BUS examination, which are useful for improved accuracy of breast cancer diagnosis. However, such performance remains a challenging task owing to the poor image quality and large variations in the sizes, shapes, and locations of breast lesions. In this paper, we propose a new convolutional neural network with coarse‐to‐fine feature fusion to address the aforementioned challenges. Methods: The proposed fusion network consists of an encoder path, a decoder path, and a core fusion stream path (FSP). The encoder path is used to capture the context information, and the decoder path is used for localization prediction. The FSP is designed to generate beneficial aggregate feature representations (i.e., various‐sized lesion features, aggregated coarse‐to‐fine information, and high‐resolution edge characteristics) from the encoder and decoder paths, which are eventually used for accurate breast lesion segmentation. To better retain the boundary information and alleviate the effect of image noise, we input the superpixel image along with the original image to the fusion network. Furthermore, a weighted‐balanced loss function was designed to address the problem of lesion regions having different sizes. We then conducted exhaustive experiments on three public BUS datasets to evaluate the proposed network. Results: The proposed method outperformed state‐of‐the‐art (SOTA) segmentation methods on the three public BUS datasets, with average dice similarity coefficients of 84.71(±1.07), 83.76(±0.83), and 86.52(±1.52), average intersection‐over‐union values of 76.34(±1.50), 75.70(±0.98), and 77.86(±2.07), average sensitivities of 86.66(±1.82), 85.21(±1.98), and 87.21(±2.51), average specificities of 97.92(±0.46), 98.57(±0.19), and 99.42(±0.21), and average accuracies of 95.89(±0.57), 97.17(±0.3), and 98.51(±0.3). Conclusions: The proposed fusion network could effectively segment lesions from BUS images, thereby presenting a new feature fusion strategy to handle challenging task of segmentation, while outperforming the SOTA segmentation methods. The code is publicly available at https://github.com/mniwk/CF2‐NET. [ABSTRACT FROM AUTHOR]

Purpose: Traditional registration of functional magnetic resonance images (fMRI) is typically achieved through registering their coregistered structural MRI. However, it cannot achieve accurate performance in that functional units which are not necessarily located relative to anatomical structures. In addition, registration methods based on functional information focus on gray matter (GM) information but ignore the importance of white matter (WM). To overcome the limitations of exiting techniques, in this paper, we aim to register resting‐state fMRI (rs‐fMRI) based directly on rs‐fMRI data and make full use of GM and WM information to improve the registration performance. Methods: We provide a robust representation of WM functional connectivity features using tissue‐specific patch‐based functional correlation tensors (ts‐PFCTs) as auxiliary information to assist registration. Furthermore, we propose a semi‐supervised deep learning model that uses GM and WM information (GM ts‐PFCTs and WM ts‐PFCTs) during training as a fine tweak to improve registration accuracy when such information is not provided in new test image pairs. We implement our method on the 1000 Functional Connectomes Project dataset. To evaluate our method, a group‐level analysis was implemented in resting‐state brain functional networks after registration, resulting in t maps. Results: Our method increases the peak t values of the t maps of default mode network, visual network, central executive network, and sensorimotor network to 21.4, 20.0, 18.4, and 19.0, respectively. Through comparison with traditional methods (FMRIB Software Library(FSL), Statistical Parametric Mapping _ Echo Planar Image(SPM_EPI), and SPM_T1), our method achieves an average improvement of 67.39%, 12.96%, and 25.14%. Conclusion: We propose a semi‐supervised deep learning network by adding GM and WM information as auxiliary information for resting‐state fMRI registration. GM and WM information is extracted and described as GM ts‐PFCTs and WM ts‐PFCTs. Experimental results show that our method achieves superior registration performance. [ABSTRACT FROM AUTHOR]

Imaging genetics is an effective tool used to detect potential biomarkers of Alzheimer’s disease (AD) in imaging and genetic data. Most existing imaging genetics methods analyze the association between brain imaging quantitative traits (QTs) and genetic data [e.g., single nucleotide polymorphism (SNP)] by using a linear model, ignoring correlations between a set of QTs and SNP groups, and disregarding the varied associations between longitudinal imaging QTs and SNPs. To solve these problems, we propose a novel temporal group sparsity regression and additive model (T-GSRAM) to identify associations between longitudinal imaging QTs and SNPs for detection of potential AD biomarkers. We first construct a nonparametric regression model to analyze the nonlinear association between QTs and SNPs, which can accurately model the complex influence of SNPs on QTs. We then use longitudinal QTs to identify the trajectory of imaging genetic patterns over time. Moreover, the SNP information of group and individual levels are incorporated into the proposed method to boost the power of biomarker detection. Finally, we propose an efficient algorithm to solve the whole T-GSRAM model. We evaluated our method using simulation data and real data obtained from AD neuroimaging initiative. Experimental results show that our proposed method outperforms several state-of-the-art methods in terms of the receiver operating characteristic curves and area under the curve. Moreover, the detection of AD-related genes and QTs has been confirmed in previous studies, thereby further verifying the effectiveness of our approach and helping understand the genetic basis over time during disease progression. [ABSTRACT FROM AUTHOR]

Purpose: We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images. Procedures: A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts. Results: The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323). Conclusion: The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the capacity of ultrashort echo time (UTE) T1 mapping to non-invasively assess gadolinium deposition in cortical bone after gadolinium-based contrast agent (GBCA) administration. Methods: Twenty-eight New Zealand rabbits (male, 3.0–3.5 kg) were randomly allocated into control, macrocyclic, high-dose macrocyclic, and linear GBCA groups (n = 7 for each group), and respectively given daily doses of 0.9 ml/kg bodyweight saline, 0.3 mmol/kg bodyweight gadobutrol, 0.9 mmol/kg bodyweight gadobutrol, and 0.3 mmol/kg bodyweight gadopentetate dimeglumine for five consecutive days per week over a period of 4 weeks. After a subsequent 4 weeks of recovery, the rabbits were sacrificed and their tibiae harvested. T1 value of cortical bone was measured using a combination of UTE actual flip angle imaging and variable repetition time on a 7T animal scanner. Gadolinium concentration in cortical bone was measured using inductively coupled plasma mass spectrometry (ICP-MS). Pearson's correlation between R1 value (R1 = 1/T1) and gadolinium concentration in cortical bone was assessed. Results: Bone T1 values were significantly lower in the lower-dose macrocyclic (329.2 ± 21.0 ms, p < 0.05), higher-dose macrocyclic (316.8 ± 21.7 ms, p < 0.01), and linear (296.8 ± 24.1 ms, p < 0.001) GBCA groups compared with the control group (356.3 ± 19.4 ms). Gadolinium concentrations measured by ICP-MS in the control, lower-dose macrocyclic, higher-dose macrocyclic, and linear GBCA groups were 0.04 ± 0.02 μg/g, 2.60 ± 0.48 μg/g, 4.95 ± 1.17 μg/g, and 13.62 ± 1.55 μg/g, respectively. There was a strong positive correlation between R1 values and gadolinium concentrations in cortical bone (r = 0.73, p < 0.001). Conclusions: These results suggest that UTE T1 mapping has the potential to provide a non-invasive assessment of gadolinium deposition in cortical bone following GBCA administration. Key Points: • Changes in T1value related to gadolinium deposition were found in bone after both linear and macrocyclic GBCA administrations. • R1relaxometry correlates strongly with gadolinium concentration in cortical bone. • UTE T1mapping provides a potential tool for non-invasively monitoring gadolinium deposition in cortical bone. [ABSTRACT FROM AUTHOR]

Objective. To develop and externally validate a CT-based radiomics nomogram for pretreatment prediction of relapse in osteosarcoma patients within one year. Materials and Methods. In this multicenter retrospective study, a total of 80 patients (training cohort: 63 patients from three hospitals; validation cohort: 17 patients from three other hospitals) with osteosarcoma, undergoing pretreatment CT between August 2010 and December 2018, were identified from multicenter databases. Radiomics features were extracted and selected from tumor regions on CT image, and then, the radiomics signature was constructed. The radiomics nomogram that incorporated the radiomics signature and clinical-based risk factors was developed to predict relapse risk with a multivariate Cox regression model using the training cohort and validated using the external validation cohort. The performance of the nomogram was assessed concerning discrimination, calibration, reclassification, and clinical usefulness. Results. Kaplan-Meier curves based on the radiomics signature showed a significant difference between the high-risk and the low-risk groups in both training and validation cohorts (P < 0.001 and P = 0.015 , respectively). The radiomics nomogram achieved good discriminant results in the training cohort (C -index: 0.779) and the validation cohort (C -index: 0.710) as well as good calibration. Decision curve analysis revealed that the proposed model significantly improved the clinical benefit compared with the clinical-based nomogram (P < 0.001). Conclusions. This multicenter study demonstrates that a radiomics nomogram incorporated the radiomics signature and clinical-based risk factors can increase the predictive value of the osteosarcoma relapse risk, which supports the clinical application in different institutions. [ABSTRACT FROM AUTHOR]

Objective. To develop and externally validate a CT-based radiomics nomogram for pretreatment prediction of relapse in osteosarcoma patients within one year. Materials and Methods. In this multicenter retrospective study, a total of 80 patients (training cohort: 63 patients from three hospitals; validation cohort: 17 patients from three other hospitals) with osteosarcoma, undergoing pretreatment CT between August 2010 and December 2018, were identified from multicenter databases. Radiomics features were extracted and selected from tumor regions on CT image, and then, the radiomics signature was constructed. The radiomics nomogram that incorporated the radiomics signature and clinical-based risk factors was developed to predict relapse risk with a multivariate Cox regression model using the training cohort and validated using the external validation cohort. The performance of the nomogram was assessed concerning discrimination, calibration, reclassification, and clinical usefulness. Results. Kaplan-Meier curves based on the radiomics signature showed a significant difference between the high-risk and the low-risk groups in both training and validation cohorts (P < 0.001 and P = 0.015 , respectively). The radiomics nomogram achieved good discriminant results in the training cohort (C -index: 0.779) and the validation cohort (C -index: 0.710) as well as good calibration. Decision curve analysis revealed that the proposed model significantly improved the clinical benefit compared with the clinical-based nomogram (P < 0.001). Conclusions. This multicenter study demonstrates that a radiomics nomogram incorporated the radiomics signature and clinical-based risk factors can increase the predictive value of the osteosarcoma relapse risk, which supports the clinical application in different institutions. [ABSTRACT FROM AUTHOR]

Image registration plays a crucial role in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), used as a fundamental step for the subsequent diagnosis of benign and malignant tumors. However, the registration process encounters significant challenges due to the substantial intensity changes observed among different time points, resulting from the injection of contrast agents. Furthermore, previous studies have often overlooked the alignment of small structures, such as tumors and vessels. In this work, we propose a novel DCE-MRI registration framework that can effectively align the DCE-MRI time series. Specifically, our DCE-MRI registration framework consists of two steps, i.e., a de-enhancement synthesis step and a coarse-to-fine registration step. In the de-enhancement synthesis step, a disentanglement network separates DCE-MRI images into a content component representing the anatomical structures and a style component indicating the presence or absence of contrast agents. This step generates synthetic images where the contrast agents are removed from the original images, alleviating the negative effects of intensity changes on the subsequent registration process. In the registration step, we utilize a coarse registration network followed by a refined registration network. These two networks facilitate the estimation of both the coarse and refined displacement vector fields (DVFs) in a pairwise and groupwise registration manner, respectively. In addition, to enhance the alignment accuracy for small structures, a voxel-wise constraint is further conducted by assessing the smoothness of the time-intensity curves (TICs). Experimental results on liver DCE-MRI demonstrate that our proposed method outperforms state-of-the-art approaches, offering more robust and accurate alignment results. • De-enhancement of DCE-MRI improves the robustness of registration. • Coarse-to-fine registration effectively handles alignment of multiple time points. • Smoothness of time-intensity curves assists accurate results for small structures. [ABSTRACT FROM AUTHOR]

Automatic segmentation of the three substructures of glomerular filtration barrier (GFB) in transmission electron microscopy (TEM) images holds immense potential for aiding pathologists in renal disease diagnosis. However, the labor-intensive nature of manual annotations limits the training data for a fully-supervised deep learning model. Addressing this, our study harnesses self-supervised representation learning (SSRL) to utilize vast unlabeled data and mitigate annotation scarcity. Our innovation, GCLR, is a hybrid pixel-level pretext task tailored for GFB segmentation, integrating two subtasks: global clustering (GC) and local restoration (LR). GC captures the overall GFB by learning global context representations, while LR refines three substructures by learning local detail representations. Experiments on 18,928 unlabeled glomerular TEM images for self-supervised pre-training and 311 labeled ones for fine-tuning demonstrate that our proposed GCLR obtains the state-of-the-art segmentation results for all three substructures of GFB with the Dice similarity coefficient of 86.56 ± 0.16%, 75.56 ± 0.36%, and 79.41 ± 0.16%, respectively, compared with other representative self-supervised pretext tasks. Our proposed GCLR also outperforms the fully-supervised pre-training methods based on the three large-scale public datasets – MitoEM, COCO, and ImageNet – with less training data and time. • The first study of self-supervised representation learning for GFB ultrastructure segmentation. • A hybrid pretext task GCLR integrating two pixel-level subtasks: global clustering and local restoration. • No image-level subtask, avoiding the task alignment problem. • State-of-the-art performance and simple implementation. [ABSTRACT FROM AUTHOR]

Predicting whether subjects with mild cognitive impairment (MCI) can convert to Alzheimer's disease is significant for personalized treatment development and disease progression delay. Longitudinal and multimodal data have been recognized for their ability to capture longitudinal variations and provide complementary information for MCI conversion prediction. However, incomplete or missing data pose a persistent challenge in effectively utilizing such valuable information. Additionally, early-stage conversion prediction, particularly at baseline visit (BL), is crucial in clinical practice. Therefore, longitudinal data must only be incorporated during training to capture disease progression information. To address these challenges, we propose a multi-view imputation and cross-attention network (MCNet) to integrate data imputation and MCI conversion prediction in a unified framework. First, a multi-view imputation method combined with adversarial learning is presented to handle various missing data scenarios and reduce imputation errors. Second, two cross-attention blocks are introduced to exploit the potential associations in longitudinal and multimodal data. Finally, a multi-task learning model is established for data imputation, longitudinal classification, and conversion prediction. By appropriately training the model, disease progression information learned from longitudinal data improves the MCI conversion prediction that only uses BL data. To verify its effectiveness and flexibility in such MCI conversion prediction, we test MCNet on independent testing sets and single-modal BL data. Results show that MCNet outperforms competitive methods with an area under the receiver operating characteristic curve value of 86.0%. Furthermore, the interpretability of MCNet is demonstrated, indicating its potential as a valuable tool for incomplete data analysis in MCI conversion prediction. • A unified framework for data imputation and MCI conversion prediction is proposed. • The proposed data imputation module can handle missing data in various scenarios. • Cross-attention blocks are used to combine longitudinal and multimodal information. • Longitudinal data are only included during training to improve prediction at BL. • The proposed method is interpretable and is evaluated on publicly available datasets. [ABSTRACT FROM AUTHOR]

Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments. [ABSTRACT FROM AUTHOR]

Background: Existing studies have demonstrated that the integrative analysis of histopathological images and genomic data can be used to better understand the onset and progression of many diseases, as well as identify new diagnostic and prognostic biomarkers. However, since the development of pathological phenotypes are influenced by a variety of complex biological processes, complete understanding of the underlying gene regulatory mechanisms for the cell and tissue morphology is still a challenge. In this study, we explored the relationship between the chromatin accessibility changes and the epithelial tissue proportion in histopathological images of estrogen receptor (ER) positive breast cancer. Methods: An established whole slide image processing pipeline based on deep learning was used to perform global segmentation of epithelial and stromal tissues. We then used canonical correlation analysis to detect the epithelial tissue proportion-associated regulatory regions. By integrating ATAC-seq data with matched RNA-seq data, we found the potential target genes that associated with these regulatory regions. Then we used these genes to perform the following pathway and survival analysis. Results: Using canonical correlation analysis, we detected 436 potential regulatory regions that exhibited significant correlation between quantitative chromatin accessibility changes and the epithelial tissue proportion in tumors from 54 patients (FDR < 0.05). We then found that these 436 regulatory regions were associated with 74 potential target genes. After functional enrichment analysis, we observed that these potential target genes were enriched in cancer-associated pathways. We further demonstrated that using the gene expression signals and the epithelial tissue proportion extracted from this integration framework could stratify patient prognoses more accurately, outperforming predictions based on only omics or image features. Conclusion: This integrative analysis is a useful strategy for identifying potential regulatory regions in the human genome that are associated with tumor tissue quantification. This study will enable efficient prioritization of genomic regulatory regions identified by ATAC-seq data for further studies to validate their causal regulatory function. Ultimately, identifying epithelial tissue proportion-associated regulatory regions will further our understanding of the underlying molecular mechanisms of disease and inform the development of potential therapeutic targets. [ABSTRACT FROM AUTHOR]

Ultrasound elastography is a novel approach of evaluating regional myocardial systolic function and detecting infarcted area. This study aims to evaluate the radial motion of myocardial infarction (MI) area in left ventricular parasternal short axis (PSAX) view using a hybrid method of fast normalized cross-correlation and global analytic minimization (FNCCGLAM) and polar transformation. Fifteen rats were randomly selected for sham group, MI group and ischemia-reperfusion (IR) group (N = 5 for each group). The ultrasound radiofrequency data of the PSAX view of rat heart were acquired. After polar transformation of the data, the infarcted myocardium with the change of mechanical property was tracked over one myocardial systolic phase by the proposed method in comparison with fast normalized cross-correlation (FNCC) and dynamic programming analytic minimization (DPAM). To obtain a clear visualization of the myocardium, the inverse polar transformation was performed. The results indicated that the use of FNCCGLAM refined the myocardial displacements to obtain high-quality myocardial elastographic map with a higher contrast-to-noise ratio and dynamically tracked the infarcted myocardial segment with a higher success rate in comparison with FNCC and DPAM. It was found that the radial systolic motion of the infarcted anterior segment in the MI group reduced significantly (p < 0.05) in comparison with the sham group, while the systolic function of that myocardial segment in the IR group recovered at some extent. The results in this study suggest that FNCCGLAM is superior to FNCC and DPAM with the improved accuracy and robustness of motion estimation and has potentials as displacement estimator in ultrasound elastography. [ABSTRACT FROM AUTHOR]

Multispectral photoacoustic tomography (PAT) is capable of resolving tissue chromophore distribution based on spectral un-mixing. It works by identifying the absorption spectrum variations from a sequence of photoacoustic images acquired at multiple illumination wavelengths. Due to multispectral acquisition, this inevitably creates a large dataset. To cut down the data volume, sparse sampling methods that reduce the number of detectors have been developed. However, image reconstruction of sparse sampling PAT is challenging because of insufficient angular coverage. During spectral un-mixing, these inaccurate reconstructions will further amplify imaging artefacts and contaminate the results. To solve this problem, we present the interlaced sparse sampling (ISS) PAT, a method that involved: 1) a novel scanning-based image acquisition scheme in which the sparse detector array rotates while switching illumination wavelength, such that a dense angular coverage could be achieved by using only a few detectors; and 2) a corresponding image reconstruction algorithm that makes use of an anatomical prior image created from the ISS strategy to guide PAT image computation. Reconstructed from the signals acquired at different wavelengths (angles), this self-generated prior image fuses multispectral and angular information, and thus has rich anatomical features and minimum artefacts. A specialized iterative imaging model that effectively incorporates this anatomical prior image into the reconstruction process is also developed. Simulation, phantom, and in vivo animal experiments showed that even under 1/6 or 1/8 sparse sampling rate, our method achieved comparable image reconstruction and spectral un-mixing results to those obtained by conventional dense sampling method. [ABSTRACT FROM AUTHOR]

However, patients with cystic-solid lesions are seldom sent to the PET center for further evaluation using SP 18 sp F-FDG PET/CT. We wish to thank Hou and Cui for their commentary on our article on differential diagnosis between active pulmonary tuberculosis (TB) and lung cancer (LC) [[1]]. 10.1148/radiol.2018172361 11 Meyer M, Ronald J, Vernuccio F. Reproducibility of CT radiomic features within the same patient: influence of radiation dose and CT reconstruction settings. 28119328 3 Lu L, Lv W, Jiang J. Robustness of radiomic features in [11C]Choline and [18F]FDG PET/CT imaging of nasopharyngeal carcinoma: impact of segmentation and discretization. [Extracted from the article]

Purpose: This work aims to identify intratumoral habitats with distinct heterogeneity based on 2-deoxy-2-[18F]fluro-D-glucose positron emission tomography (PET)/X-ray computed tomography (CT) imaging, and to develop a subregional radiomics approach to predict progression-free survival (PFS) in patients with nasopharyngeal carcinoma (NPC).Procedures: In total, 128 NPC patients (85 vs. 43 for primary vs. validation cohorts) who underwent pre-treatment PET/CT scan were enrolled retrospectively. Each tumor was partitioned into several phenotypically consistent subregions based on individual- and population-level clustering. For each subregion, 202 radiomics features were extracted to construct imaging biomarker for prognosis via Cox's proportional hazard model combined with forward stepwise feature selection. Relevance of imaging biomarkers and clinicopathological factors were assessed by multivariate Cox regression analysis and Spearman's correlation analysis. To investigate whether imaging biomarkers could provide complementary prognosis information beyond existing predictors, a scoring system was further developed for risk stratification and compared with AJCC staging system.Results: Three subregions (denoted as S1, S2, and S3) were discovered with distinct PET/CT imaging characteristics in the two cohorts. The prognostic performance of imaging biomarker S3 outperformed the whole tumor (C-index, 0.69 vs. 0.58; log-rank test, p < 0.001 vs. p = 0.552). Imaging biomarker S3 and AJCC stage were identified as independent predictors (p = 0.011 and 0.042, respectively) after adjusting for clinicopathological factors. The scoring system outperformed the traditional AJCC staging system (log-rank test, p < 0.0001 vs. p = 0.0002 in primary cohort and p = 0.0021 vs. p = 0.0277 in validation cohort, respectively).Conclusions: Subregional radiomics analysis of PET/CT imaging has the potential to predict PFS in patients with NPC, which also provides complementary prognostic information for traditional predictors. [ABSTRACT FROM AUTHOR]

Purpose: To identify optimal machine learning methods for radiomics-based differentiation of local recurrence versus inflammation from post-treatment nasopharyngeal positron emission tomography/X-ray computed tomography (PET/CT) images.Procedures: Seventy-six nasopharyngeal carcinoma (NPC) patients were enrolled (41/35 local recurrence/inflammation as confirmed by pathology). Four hundred eighty-seven radiomics features were extracted from PET images for each patient. The diagnostic performance was investigated for 42 cross-combinations derived from 6 feature selection methods and 7 classifiers. Of the original cohort, 70 % was applied for feature selection and classifier development, and the remaining 30 % used as an independent validation set. The diagnostic performance was evaluated using area under the ROC curve (AUC), test error, sensitivity, and specificity. Furthermore, the performance of the radiomics signatures against routine features was statistically compared using DeLong's method.Results: The cross-combination fisher score (FSCR) + k-nearest neighborhood (KNN), FSCR + support vector machines with radial basis function kernel (RBF-SVM), FSCR + random forest (RF), and minimum redundancy maximum relevance (MRMR) + RBF-SVM outperformed others in terms of accuracy (AUC 0.883, 0.867, 0.892, 0.883; sensitivity 0.833, 0.864, 0.831, 0.750; specificity 1, 1, 0.873, 1) and reliability (test error 0.091, 0.136, 0.150, 0.136). Compared with conventional metrics, the radiomics signatures showed higher AUC values (0.867-0.892 vs. 0.817), though the differences were not statistically significant (p = 0.462-0.560).Conclusion: This study identified the most accurate and reliable machine learning methods, which could enhance the application of radiomics methods in the precision of diagnosis of NPC. [ABSTRACT FROM AUTHOR]

PURPOSE: Tumor-infiltrating lymphocytes (TILs) and their spatial characterizations on whole-slide images (WSIs) of histopathology sections have become crucial in diagnosis, prognosis, and treatment response prediction for different cancers. However, fully automatic assessment of TILs on WSIs currently remains a great challenge because of the heterogeneity and large size of WSIs. We present an automatic pipeline based on a cascade-training U-net to generate high-resolution TIL maps on WSIs. METHODS: We present global cell-level TIL maps and 43 quantitative TIL spatial image features for 1,000 WSIs of The Cancer Genome Atlas patients with breast cancer. For more specific analysis, all the patients were divided into three subtypes, namely, estrogen receptor (ER)–positive, ER-negative, and triple-negative groups. The associations between TIL scores and gene expression and somatic mutation were examined separately in three breast cancer subtypes. Both univariate and multivariate survival analyses were performed on 43 TIL image features to examine the prognostic value of TIL spatial patterns in different breast cancer subtypes. RESULTS: The TIL score was in strong association with immune response pathway and genes (eg, programmed death-1 and CLTA4). Different breast cancer subtypes showed TIL score in association with mutations from different genes suggesting that different genetic alterations may lead to similar phenotypes. Spatial TIL features that represent density and distribution of TIL clusters were important indicators of the patient outcomes. CONCLUSION: Our pipeline can facilitate computational pathology-based discovery in cancer immunology and research on immunotherapy. Our analysis results are available for the research community to generate new hypotheses and insights on breast cancer immunology and development. [ABSTRACT FROM AUTHOR]

Motivation The detection of potential biomarkers of Alzheimer's disease (AD) is crucial for its early prediction, diagnosis and treatment. Voxel-wise genome-wide association study (VGWAS) is a commonly used method in imaging genomics and usually applied to detect AD biomarkers in imaging and genetic data. However, existing VGWAS methods entail large computational cost and disregard spatial correlations within imaging data. A novel method is proposed to solve these issues. Results We introduce a novel method to incorporate spatial correlations into a VGWAS framework for the detection of potential AD biomarkers. To consider the characteristics of AD, we first present a modification of a simple linear iterative clustering method for spatial grouping in an anatomically meaningful manner. Second, we propose a spatial–anatomical similarity matrix to incorporate correlations among voxels. Finally, we detect the potential AD biomarkers from imaging and genetic data by using a fast VGWAS method and test our method on 708 subjects obtained from an Alzheimer's Disease Neuroimaging Initiative dataset. Results show that our method can successfully detect some new risk genes and clusters of AD. The detected imaging and genetic biomarkers are used as predictors to classify AD/normal control subjects, and a high accuracy of AD/normal control classification is achieved. To the best of our knowledge, the association between imaging and genetic data has yet to be systematically investigated while building statistical models for classifying AD subjects to create a link between imaging genetics and AD. Therefore, our method may provide a new way to gain insights into the underlying pathological mechanism of AD. Availability and implementation https://github.com/Meiyan88/SASM-VGWAS. [ABSTRACT FROM AUTHOR]

Purpose. To classify radiation necrosis versus recurrence in glioma patients using a radiomics model based on combinational features and multimodality MRI images. Methods. Fifty-one glioma patients who underwent radiation treatments after surgery were enrolled in this study. Sixteen patients revealed radiation necrosis while 35 patients showed tumor recurrence during the follow-up period. After treatment, all patients underwent T1-weighted, T1-weighted postcontrast, T2-weighted, and fluid-attenuated inversion recovery scans. A total of 41,284 handcrafted and 24,576 deep features were extracted for each patient. The 0.623 + bootstrap method and the area under the curve (denoted as 0.632 + bootstrap AUC) metric were used to select the features. The stepwise forward method was applied to construct 10 logistic regression models based on different combinations of image features. Results. For handcrafted features on multimodality MRI, model 7 with seven features yielded the highest AUC of 0.9624, sensitivity of 0.8497, and specificity of 0.9083 in the validation set. These values were higher than the accuracy of using handcrafted features on single-modality MRI (paired t-test, p<0.05, except sensitivity). For combined handcrafted and AlexNet features on multimodality MRI, model 6 with six features achieved the highest AUC of 0.9982, sensitivity of 0.9941, and specificity of 0.9755 in the validation set. These values were higher than the accuracy of using handcrafted features on multimodality MRI (paired t-test, p<0.05). Conclusions. Handcrafted and deep features extracted from multimodality MRI images reflecting the heterogeneity of gliomas can provide useful information for glioma necrosis/recurrence classification. [ABSTRACT FROM AUTHOR]

Purpose: To investigate the prognostic performance of radiomics features, as extracted from positron emission tomography (PET) and X-ray computed tomography (CT) components of baseline 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) PET/CT images and integrated with clinical parameters, in patients with nasopharyngeal carcinoma (NPC).Procedures: One hundred twenty-eight NPC patients (85 vs. 43 for training vs. validation), containing a subset of 86 patients with local-regional advanced stage, were enrolled. All patients underwent pretreatment PET/CT scans (mean follow-up time 24 ± 14 months). Three thousand two hundred seventy-six radiomics features extracted from PET or CT components and 13 clinical parameters were used to predict progression-free survival (PFS). Univariate analysis with Benjamini-Hochberg false discovery rate (FDR) correction was first used to screen significant features, and redundant features with Spearman's correlation > 0.8 were further eliminated. Then, seven multivariate models involving PET features and/or CT features and/or clinical parameters (denoted as clinical, PET, CT, clinical + PET, clinical + CT, PET + CT and clinical + PET + CT) were constructed by forward stepwise multivariate Cox regression. Model performance was evaluated by concordance index (C-index).Results: Sixty patients encountered events (28 recurrences, 17 metastases, and 15 deaths). Six clinical parameters, 3 PET features, and 14 CT features in training cohort and 4 clinical parameters, 10 PET features, and 4 CT features in subset of local-regional advanced stage were significantly associated with PFS. Combining PET and/or CT features with clinical parameters showed equal or higher prognostic performance than models with PET or CT or clinical parameters alone (C-index 0.71-0.76 vs. 0.67-0.73 and 0.62-0.75 vs. 0.54-0.75 for training and validation cohorts, respectively), while the prognostic performance was significantly improved in local-regional advanced cohort (C-index 0.67-0.84 vs. 0.64-0.77, p value 0.001-0.059).Conclusion: Radiomics features extracted from the PET and CT components of baseline PET/CT images provide complementary prognostic information and improved outcome prediction for NPC patients compared with use of clinical parameters alone. [ABSTRACT FROM AUTHOR]