Computerized Medical Imaging and Graphics最新文献

{"title":"Towards Generic Abdominal Multi-Organ Segmentation with multiple partially labeled datasets","authors":"Xiang Li ,&nbsp;Faming Fang ,&nbsp;Liyan Ma ,&nbsp;Tieyong Zeng ,&nbsp;Guixu Zhang ,&nbsp;Ming Xu","doi":"10.1016/j.compmedimag.2025.102642","DOIUrl":"10.1016/j.compmedimag.2025.102642","url":null,"abstract":"<div><div>An increasing number of publicly available datasets have facilitated the exploration of building universal medical segmentation models. Existing approaches address partially labeled problem of each dataset by harmonizing labels across datasets and independently focusing on the labeled foreground regions. However, significant challenges persist, particularly in the form of cross-site domain shifts and the limited utilization of partially labeled datasets. In this paper, we propose a GAMOS (<strong>G</strong>eneric <strong>A</strong>bdominal <strong>M</strong>ulti-<strong>O</strong>rgan <strong>S</strong>egmentation) framework. Specifically, GAMOS integrates a self-guidance strategy to adopt diffusion models for partial labeling issue, while employing a self-distillation mechanism to effectively leverage unlabeled data. A sparse semantic memory is introduced to mitigate domain shifts by ensuring consistent representations in the latent space. To further enhance performance, we design a sparse similarity loss to align multi-view memory representations and enhance the discriminability and compactness of the memory vectors. Extensive experiments on real-world medical datasets demonstrate the superiority and generalization ability of GAMOS. It achieves a mean Dice Similarity Coefficient (DSC) of 91.33% and a mean 95th percentile Hausdorff Distance (HD95) of 1.83 on labeled foreground regions. For unlabeled foreground regions, GAMOS obtains a mean DSC of 86.88% and a mean HD95 of 3.85, outperforming existing state-of-the-art methods.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102642"},"PeriodicalIF":4.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond unimodal analysis: Multimodal ensemble learning for enhanced assessment of atherosclerotic disease progression.","authors":"Valerio Guarrasi, Amanda Bertgren, Ulf Näslund, Patrik Wennberg, Paolo Soda, Christer Grönlund","doi":"10.1016/j.compmedimag.2025.102617","DOIUrl":"10.1016/j.compmedimag.2025.102617","url":null,"abstract":"<p><p>Atherosclerosis is a leading cardiovascular disease typified by fatty streaks accumulating within arterial walls, culminating in potential plaque ruptures and subsequent strokes. Existing clinical risk scores, such as systematic coronary risk estimation and Framingham risk score, profile cardiovascular risks based on factors like age, cholesterol, and smoking, among others. However, these scores display limited sensitivity in early disease detection. Parallelly, ultrasound-based risk markers, such as the carotid intima media thickness, while informative, only offer limited predictive power. Notably, current models largely focus on either ultrasound image-derived risk markers or clinical risk factor data without combining both for a comprehensive, multimodal assessment. This study introduces a multimodal ensemble learning framework to assess atherosclerosis severity, especially in its early sub-clinical stage. We utilize a multi-objective optimization targeting both performance and diversity, aiming to integrate features from each modality effectively. Our objective is to measure the efficacy of models using multimodal data in assessing vascular aging, i.e., plaque presence and vascular age, over a six-year period. We also delineate a procedure for optimal model selection from a vast pool, focusing on best-suited models for classification tasks. Additionally, through eXplainable Artificial Intelligence techniques, this work delves into understanding key model contributors and discerning unique subject subgroups.</p>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"124 ","pages":"102617"},"PeriodicalIF":4.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144805229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LearnDiff: MRI image super-resolution using a diffusion model with learnable noise","authors":"Sagnik Goswami ,&nbsp;Akriti Gupta ,&nbsp;Angshuman Paul","doi":"10.1016/j.compmedimag.2025.102641","DOIUrl":"10.1016/j.compmedimag.2025.102641","url":null,"abstract":"<div><div>MRI images with a superior spatial resolution may facilitate an accurate and faster diagnosis. We present LearnDiff, a diffusion probabilistic model with learnable noise for the super-resolution of MRI images. Unlike the standard diffusion models that rely on a fixed, standard normal distribution, LearnDiff utilizes a learnable Gaussian distribution in the diffusion bottleneck, enabling both forward and reverse processes to adapt dynamically. This flexibility addresses a critical limitation.</div><div>A standard normal distribution for noise may not be adequate in the context of MRI super-resolution using a residual approach. By allowing the noise distribution to be learnable, our model achieves SOTA performance on publicly available MRI images, showing a 3.8% improvement in PSNR compared to previous SOTA methods, significantly outperforming traditional diffusion models. Across multiple MRI datasets, our approach yields superior image quality and enhanced quantitative metrics, highlighting its effectiveness in capturing finer image details and achieving more accurate super-resolution. <span><span>Link to the codebase</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102641"},"PeriodicalIF":4.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An arbitrary-modal fusion network for volumetric cranial nerves tract segmentation","authors":"Lei Xie ,&nbsp;Huajun Zhou ,&nbsp;Junxiong Huang ,&nbsp;Qingrun Zeng ,&nbsp;Jiahao Huang ,&nbsp;Jianzhong He ,&nbsp;Jiawei Zhang ,&nbsp;Baohua Fan ,&nbsp;Mingchu Li ,&nbsp;Guoqiang Xie ,&nbsp;Hao Chen ,&nbsp;Yuanjing Feng","doi":"10.1016/j.compmedimag.2025.102635","DOIUrl":"10.1016/j.compmedimag.2025.102635","url":null,"abstract":"<div><div>The segmentation of cranial nerves (CNs) tract provides a valuable quantitative tool for the analysis of the morphology and trajectory of individual CNs. Multimodal CN segmentation networks, e.g., CNTSeg, which combine structural Magnetic Resonance Imaging (MRI) and diffusion MRI, have achieved promising segmentation performance. However, it is laborious or even infeasible to collect complete multimodal data in clinical practice due to limitations in equipment, user privacy, and working conditions. In this work, we propose a novel arbitrary-modal fusion network for volumetric CN segmentation, called CNTSeg-v2, which trains one model to handle different combinations of available modalities. Instead of directly combining all the modalities, we select T1-weighted (T1w) images as the primary modality due to its simplicity in data acquisition and contribution most to the results, which supervises the information selection of other auxiliary modalities. Our model encompasses an Arbitrary-Modal Collaboration Module (ACM) designed to effectively extract informative features from other auxiliary modalities, guided by the supervision of T1w images. Meanwhile, we construct a Deep Distance-guided Multi-stage (DDM) decoder to correct small errors and discontinuities through signed distance maps to improve segmentation accuracy. We evaluate our CNTSeg-v2 on the Human Connectome Project (HCP) dataset and the clinical Multi-shell Diffusion MRI (MDM) dataset. Extensive experimental results show that our CNTSeg-v2 achieves state-of-the-art segmentation performance, outperforming all competing methods.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102635"},"PeriodicalIF":4.9,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144989357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CS2former: Multimodal feature fusion transformer with dual channel-spatial feature extraction module for bipolar disorder diagnosis","authors":"Guoxin Wang ,&nbsp;Fengmei Fan ,&nbsp;Shipeng Dai ,&nbsp;Shan An ,&nbsp;Chao Zhang ,&nbsp;Sheng Shi ,&nbsp;Yunan Mei ,&nbsp;Feng Yu ,&nbsp;Qi Wang ,&nbsp;Xiaole Han ,&nbsp;Shuping Tan ,&nbsp;Yunlong Tan ,&nbsp;Zhiren Wang","doi":"10.1016/j.compmedimag.2025.102632","DOIUrl":"10.1016/j.compmedimag.2025.102632","url":null,"abstract":"<div><div>Bipolar disorder (BD) is a debilitating mental illness characterized by significant mood swings, posing a substantial challenge for accurate diagnosis due to its clinical complexity. This paper presents CS2former, a novel approach leveraging a dual channel-spatial feature extraction module within a Transformer model to diagnose BD from resting-state functional MRI (Rs-fMRI) and T1-weighted MRI (T1w-MRI) data. CS2former employs a Channel-2D Spatial Feature Aggregation Module to decouple channel and spatial information from Rs-fMRI, while a Channel-3D Spatial Attention Module with Synchronized Attention Module (SAM) concurrently computes attention for T1w-MRI feature maps. This dual extraction strategy is coupled with a Transformer, enhancing feature integration across modalities. Our experimental results on two datasets, including the OpenfMRI and our collected datasets, demonstrate CS2former’s superior performance. Notably, the model achieves a 10.8% higher Balanced Accuracy on our dataset and a 5.7% improvement on the OpenfMRI dataset compared to the baseline models. These results underscore CS2former’s innovation in multimodal feature fusion and its potential to elevate the efficiency and accuracy of BD diagnosis.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102632"},"PeriodicalIF":4.9,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SSIFNet: Spatial–temporal stereo information fusion network for self-supervised surgical video inpainting","authors":"Xiaoyang Zou ,&nbsp;Zhuyuan Zhang ,&nbsp;Derong Yu ,&nbsp;Wenyuan Sun ,&nbsp;Wenyong Liu ,&nbsp;Donghua Hang ,&nbsp;Wei Bao ,&nbsp;Guoyan Zheng","doi":"10.1016/j.compmedimag.2025.102622","DOIUrl":"10.1016/j.compmedimag.2025.102622","url":null,"abstract":"<div><div>During minimally invasive robot-assisted surgical procedures, surgeons rely on stereo endoscopes to provide image guidance. Nevertheless, the field-of-view is typically restricted owing to the limited size of the endoscope and constrained workspace. Such a visualization challenge becomes even more severe when surgical instruments are inserted into the already restricted field-of-view, where important anatomical landmarks and relevant clinical contents may become occluded by the inserted instruments. To address the challenge, in this work, we propose a novel end-to-end trainable spatial–temporal stereo information fusion network, referred as SSIFNet, for inpainting surgical videos of surgical scene under instrument occlusions in robot-assisted endoscopic surgery. The proposed SSIFNet features three essential modules including a novel optical flow-guided deformable feature propagation (OFDFP) module, a novel spatial–temporal stereo focal transformer (S<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>FT)-based information fusion module, and a novel stereo-consistency enforcement (SE) module. These three modules work synergistically to inpaint occluded regions in the surgical scene. More importantly, SSIFNet is trained in a self-supervised manner with simulated occlusions by a novel loss function, which is designed to combine flow completion, disparity matching, cross-warping consistency, warping-consistency, image and adversarial loss terms to generate high fidelity and accurate occlusion reconstructions in both views. After training, the trained model can be applied directly to inpainting surgical videos with true instrument occlusions to generate results with not only spatial and temporal consistency but also stereo-consistency. Comprehensive quantitative and qualitative experimental results demonstrate that SSIFNet outperforms state-of-the-art (SOTA) video inpainting methods. The source code of this study will be released at <span><span>https://github.com/SHAUNZXY/SSIFNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102622"},"PeriodicalIF":4.9,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144902402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Straightening the path to clarity: A subpixel-level vessel segmentation framework in X-ray coronary angiography","authors":"Chunming Li ,&nbsp;Miao Chu ,&nbsp;Xun Liu ,&nbsp;Botao Yang ,&nbsp;Yingguang Li ,&nbsp;Guanyu Li ,&nbsp;Shengxian Tu","doi":"10.1016/j.compmedimag.2025.102634","DOIUrl":"10.1016/j.compmedimag.2025.102634","url":null,"abstract":"<div><div>Coronary artery disease (CAD) is the leading cause of death globally. X-ray coronary angiography (XCA) is the standard method for routine evaluation of coronary artery disease and its precise quantitative analysis relies heavily on contour segmentation. However, existing direct contour segmentation algorithms for XCA vessels can only achieve pixel-level accuracy, compromising the reliability of quantitative measurements. To address this, we propose the first deep learning-based framework for subpixel-level XCA vessel segmentation, achieving an average error of less than one pixel. The framework includes an automated vessel landmarks localization to identify main vessels and stenotic lesions, followed by a planar coordinate transformation to convert vessels into a straightened view. Subsequently, we designed an efficient SuPP-Net for subpixel contour prediction on the straightened view, which was ultimately transformed back to the original image coordinates. Our method achieved state-of-the-art performance on clinical data, with a contour MSE of 0.53 ± 0.30 pixel and an average diameter stenosis error of 3.23 ± 2.51%. Beyond achieving subpixel-level accuracy, our framework specifically addresses diverse stenotic lesion types, optimizes labeling techniques, and enables a fully automated workflow. Moreover, the method demonstrates robust generalization across different image quality, vessel perturbation levels, and external noise levels. This subpixel analysis of XCA vessels meets the precision demands of coronary anatomical and physiological assessments, thereby may enhance CAD diagnosis and treatment strategies.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102634"},"PeriodicalIF":4.9,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144907967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CrossNeXt: ConvNeXt-based cross-teaching with entropy minimization for semi-supervised liver segmentation from abdominal MRI","authors":"Zhiji Zheng ,&nbsp;Xiao Luo ,&nbsp;Peiwen Li ,&nbsp;Sirong Piao ,&nbsp;Xin Cao ,&nbsp;Xiao Liu ,&nbsp;Liqin Yang ,&nbsp;Bin Hu ,&nbsp;Yan Geng ,&nbsp;Daoying Geng","doi":"10.1016/j.compmedimag.2025.102624","DOIUrl":"10.1016/j.compmedimag.2025.102624","url":null,"abstract":"<div><div>Recent advancements in artificial intelligence have significantly enhanced the efficiency of abdominal MRI segmentation, thereby improving the screening and diagnosis of liver diseases. However, accurate precise liver segmentation in MRI remains a challenging task due to the high variability in liver morphology and the limited availability of high-quality annotated datasets. To address these challenges, this study presents an advanced semi-supervised learning framework that integrates cross-teaching with pseudo-label generation and intra-batch entropy minimization. This framework facilitates the effective extraction of information from unlabeled data while minimizing dependence on labeled datasets. Specifically, the proposed method utilizes a cross-teaching mechanism between UNet and MedNeXt, where the prediction of one network serves as a pseudo-label to guide the training of the other. Additionally, entropy minimization within the training batch is employed to refine each network’s predictions. This strategy effectively reduces the reliance on annotated data while maintaining high segmentation accuracy even with several well-annotated images. Conducted on two public annotated datasets and an unannotated private dataset containing 1281 DICOM-format MRI images from Huashan Hospital with approved protocols, comprehensive experiments demonstrate the efficacy of the proposed approach. The results indicate superior segmentation performance, achieving a Dice Similarity Coefficient of 0.965, Intersection over Union of 0.932, 95% Hausdorff Distance of 2.625, and Average Symmetric Surface Distance of 0.760. Compared with ten state-of-the-art semi-supervised learning 3D segmentation methods, the proposed approach exhibited superior performance and robustness in medical system.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102624"},"PeriodicalIF":4.9,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Secure and privacy-preserving surgical instrument segmentation in minimally invasive surgeries using federated differential privacy approach","authors":"Bakiya. K,&nbsp;Nickolas Savarimuthu","doi":"10.1016/j.compmedimag.2025.102637","DOIUrl":"10.1016/j.compmedimag.2025.102637","url":null,"abstract":"<div><div>Accurate segmentation of surgical instruments is essential for practical intraoperative guidance in robot-assisted procedures, contributing to improved surgical navigation and enhanced patient safety. Federated Learning is a decentralized approach that enables collaborative model training across institutions without sharing raw data, thereby ensuring data privacy, which is particularly crucial in healthcare. This paper introduces the Federated Averaging algorithm to address the quantity skew by aggregating client model weights centrally. In parallel, the Federated Differential Privacy algorithm was implemented to enhance data privacy by introducing controlled noise to gradients at the client level. For segmentation, we evaluated a U-Net, a Multi-head Attention U-Net for small instruments, and a Squeeze-and-Excitation U-Net for overall accuracy. These models were benchmarked on the datasets of the Kvasir-Instrument (gastrointestinal endoscopy) and RoboTool (20 diverse surgical procedures). Quantitative evaluations using FedAvg, FedSGD, and FedDP across U-Net variants demonstrated that SE-UNet with FedDP at 60 epochs yielded the best results with Dice Score: 99.00 % ± 0.01, Accuracy: 99.68 % ± 0.25, and mIoU: 98.05 % ± 0.01, highlighting superior generalization and convergence stability. Across all architectures, FedDP consistently outperformed FedAvg and FedSGD, with accuracy improvements ranging from 0.3 % to 2.0 % and mIoU gains up to 6.8 %, especially pronounced in SE-UNet. Extending training from 40 to 60 epochs enhanced model stability, with standard deviations reducing from as high as ±3.28 % to as low as ±0.01 %. Statistical analysis confirmed this benefit, with 83.3 % of configurations showing improved p-values, and overall significance rates increasing from 84.4 % to 91.1 %. SE-UNet exhibited the most consistent and robust performance improvements, with an average p-value reduction of 40.7 %, affirming its reliability under federated settings.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102637"},"PeriodicalIF":4.9,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing breast cancer screening: Unveiling explainable cross-view contributions in dual-view mammography with Sparse Bipartite Graphs Attention Networks","authors":"Guillaume Pelluet ,&nbsp;Mira Rizkallah ,&nbsp;Mickael Tardy ,&nbsp;Diana Mateus","doi":"10.1016/j.compmedimag.2025.102620","DOIUrl":"10.1016/j.compmedimag.2025.102620","url":null,"abstract":"<div><div>Medical imaging techniques like mammography enable early breast cancer detection and are part of regular screening programs. Typically, a mammogram exam involves two views of each breast, providing complementary information, but physicians rate the breast as a whole. Computer-Aided Diagnostic tools focus on detecting lesions in a single view, which is challenging due to high image resolution and varying scales of abnormalities. The projective nature of the two views and different acquisition protocols add complexity to dual-view analysis. To address these challenges, we propose a Graph Neural Network approach that models image information at multiple scales and the complementarity of the two views. To this end, we rely on a superpixel decomposition, assigning hierarchical features to superpixels, designing a dual-view graph to share information, and introducing a modified Sparse Graph Attention Layer to keep relevant dual-view relations. This improves interpretability of decisions and avoids the need to register pairs of views under strong deformations. Our model is trained with a fully supervised approach and evaluated on public and private datasets. Experiments demonstrate state-of-the-art classification and detection performance on Full Field Digital Mammographies, achieving a breast-wise AUC of 0.96 for the INbreast dataset, a sensitivity of 0.97 with few false positives per image (0.33), and a case-wise AUC of 0.92 for the VinDr dataset. This study presents a Sparse Graph Attention method for dual-view mammography analysis, generating meaningful explanations that radiologists can interpret. Extensive evaluation shows the relevance of our approach in breast cancer detection and classification.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"125 ","pages":"Article 102620"},"PeriodicalIF":4.9,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144926277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}