Medical image analysis最新文献

{"title":"Context-enriched contrastive auto-encoder with topology learning for medical hyperspectral image classification to diagnose tumors","authors":"Meiling Wang ,&nbsp;Changda Xing ,&nbsp;Yifang Wu ,&nbsp;Cheng Wang","doi":"10.1016/j.media.2026.103998","DOIUrl":"10.1016/j.media.2026.103998","url":null,"abstract":"<div><div>Deep learning has emerged as a highly effective approach for the automatic classification of medical hyperspectral images (MedHSIs), facilitating the accurate diagnosis of diverse tumors. Most of current methods suffer from the challenges in the separability of latent representation and the preservation of topological structure. To remedy such deficiencies, we propose a novel context-enriched contrastive auto-encoder with topology learning (CCAET) based MedHSI classification for tumor diagnosis. Concretely, we initially employ an auto-encoder (AE) network as the foundational framework to achieve latent representation and data reconstruction. Subsequently, to enhance the separability of the latent representation, we integrate a context-enriched contrastive loss into the AE framework, where both individual pixels and their contextual information are used to redefine contrastive learning, so that small distances between intra-class features and large distances between inter-class features are achieved. Further, we construct a topology-preserved loss by incorporating a graph based approach into the foundational framework, which aims to maintain the topological structure during latent representation learning. Furthermore, we devise a gradient descent-based optimization scheme to optimize the overall loss of the proposed CCAET method, so as to obtain the final latent representation of MedHSI. Finally, we implement soft-max-based label prediction to obtain the classification results. Different from most existing methods, the CCAET approach considers both the separability of latent representations and the preservation of topological structure to enhance MedHSI classification performance. Extensive experimental evidence has been presented to substantiate that the proposed CCAET method outperforms several state-of-the-art techniques in terms of MedHSI classification based tumor diagnosis.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103998"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146209949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing uncertainty assessment in dynamic PET imaging with residual permutation and clustering","authors":"Kun Ma ,&nbsp;Fangxiao Cheng ,&nbsp;Wei Liu ,&nbsp;Wenrui Shao ,&nbsp;Yalei Yang ,&nbsp;Nan Li ,&nbsp;Xiangxi Meng ,&nbsp;Zhaoheng Xie","doi":"10.1016/j.media.2026.103997","DOIUrl":"10.1016/j.media.2026.103997","url":null,"abstract":"<div><div>Quantitative positron emission tomography (PET) is widely used for disease diagnosis and therapy monitoring, yet the reliability of kinetic parameters depends on robust uncertainty quantification. Existing Bayesian methods are computationally demanding, bootstrap approaches are noise-sensitive, and recent deep learning models often require large training datasets and lack physical scale sensitivity. To address these limitations, we propose a clustering-based residual permutation (RP) framework for uncertainty estimation in dynamic PET. The method generates pseudo time-activity curves (TACs) by permuting fitting residuals within kinetically homogeneous clusters, preserving spatiotemporal noise characteristics while avoiding noise misallocation across heterogeneous regions. To ensure meaningful residual construction, we introduce a regularized model with Huber loss and elastic-net regularization, improving numerical stability and preventing overfitting. Extensive validation on simulated data (TACs and XCAT-OSEM reconstructions) and clinical total-body PET demonstrates that RP yields uncertainty estimates that scale consistently with noise level and preserve expected physical disparities between kinetic parameters. Compared with reference baselines, the proposed framework provides a distribution-free, training-independent, and computationally efficient solution for voxel-wise uncertainty quantification. Overall, RP fills a practical gap between expensive Bayesian inference and data-hungry deep learning, offering a robust and clinically deployable approach to uncertainty-aware dynamic PET analysis. The code of the proposed RP method and reference methods is available at: <span><span>https://github.com/ANMMILab-PKU</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103997"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146209646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artifact-suppressed 3D retinal microvascular segmentation via multi-scale topology regulation","authors":"Ting Luo ,&nbsp;Jinxian Zhang ,&nbsp;Tao Chen ,&nbsp;Zhouyan He ,&nbsp;Yanda Meng ,&nbsp;Mengting Liu ,&nbsp;Jiong Zhang ,&nbsp;Dan Zhang","doi":"10.1016/j.media.2026.103988","DOIUrl":"10.1016/j.media.2026.103988","url":null,"abstract":"<div><div>Optical coherence tomography angiography (OCTA) enables non-invasive visualization of retinal microvasculature, and accurate 3D vessel segmentation is essential for quantifying biomarkers critical for early diagnosis and monitoring of diabetic retinopathy. However, reliable 3D OCTA segmentation is hindered by capillary invisibility, complex vascular topology, and motion artifacts, which compromise biomarker accuracy. Furthermore, the scarcity of manually annotated 3D OCTA microvascular data constrains methodological development. To address this challenge, we introduce our publicly accessible 3D microvascular dataset and propose MT-Net, a multi-view, topology-aware 3D retinal microvascular segmentation network. First, a novel dimension transformation strategy is employed to enhance topological accuracy by effectively encoding spatial dependencies across multiple planes. Second, to mitigate the impact of motion artifacts, we introduce a unidirectional Artifact Suppression Module (ASM) that selectively suppresses noise along the B-scan direction. Third, a Twin-Cross Attention Module (TCAM), guided by vessel centerlines, is designed to enhance the continuity and completeness of segmented vessels by reinforcing cross-view contextual information. Experiments on two 3D OCTA datasets show that MT-Net achieves state-of-the-art accuracy and topological consistency, with strong generalizability validated by cross-dataset analysis. We plan to release our manual annotations to facilitate future research in retinal OCTA segmentation.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103988"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SurgLaVi: Large-scale hierarchical dataset for surgical vision-language representation learning","authors":"Alejandra Perez ,&nbsp;Chinedu Nwoye ,&nbsp;Ramtin Raji Kermani ,&nbsp;Omid Mohareri ,&nbsp;Muhammad Abdullah Jamal","doi":"10.1016/j.media.2026.103982","DOIUrl":"10.1016/j.media.2026.103982","url":null,"abstract":"<div><div>Vision-language pre-training (VLP) offers unique advantages for surgery by aligning language with surgical videos, enabling workflow understanding and transfer across tasks without relying on expert-labeled datasets. However, progress in surgical VLP remains constrained by the limited scale, procedural diversity, semantic quality, and hierarchical structure of existing datasets. In this work, we present SurgLaVi, the largest and most diverse surgical vision-language dataset to date, comprising nearly 240k clip-caption pairs from more than 200 procedures, and featuring hierarchical levels at coarse-, mid-, and fine-level. At the core of SurgLaVi lies a fully automated pipeline that systematically generates fine-grained transcriptions of surgical videos and segments them into coherent procedural units. To ensure high-quality annotations, it applies dual-modality filtering to remove irrelevant and noisy samples. Within this framework, the resulting captions are enriched with contextual detail, producing annotations that are both semantically rich and easy to interpret. To ensure accessibility, we release <span><span>SurgLaVi-β</span><svg><path></path></svg></span>, an open-source derivative of 113k clip-caption pairs constructed entirely from public data, which is over four times larger than existing surgical VLP datasets. To demonstrate the value of the SurgLaVi datasets, we introduce SurgCLIP, a CLIP-style video-text contrastive framework with dual encoders, as a representative base model. SurgCLIP achieves consistent improvements across phase, step, action, and tool recognition, surpassing prior state-of-the-art methods, often by large margins. These results validate that large-scale, semantically rich, and hierarchically structured datasets directly translate into stronger and more generalizable representations, establishing SurgLaVi as a key resource for developing surgical foundation models.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103982"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality-label-free fetal brain MRI quality control based on image orientation recognition uncertainty","authors":"Mingxuan Liu ,&nbsp;Yi Liao ,&nbsp;Haoxiang Li ,&nbsp;Juncheng Zhu ,&nbsp;Hongjia Yang ,&nbsp;Yingqi Hao ,&nbsp;Haibo Qu ,&nbsp;Qiyuan Tian","doi":"10.1016/j.media.2026.103994","DOIUrl":"10.1016/j.media.2026.103994","url":null,"abstract":"<div><div>Quality control (QC) in fetal MRI is essential for efficient, high-quality data acquisition and analysis aimed at assessing fetal brain development and detecting abnormalities. Supervised deep learning methods require numerous image-quality labels and have limited generalization to cross-domain out-of-distribution data. To address these problems, an Orientation Recognition Kolmogorov-Arnold Network (OR-KAN), composed of stacked Bottleneck KAN Convolution layers, was trained on turbo spin echo (TSE) T₂-weighted data augmented from seven fetal brain atlases to predict stack orientation (i.e., axial, sagittal, and coronal). Image quality was quantified as the entropy of the prediction uncertainty. Experiments showed that OR-KAN achieved an area under the receiver operating characteristic curve (AUROC) of 0.840 and an area under the precision recall curve (AUPR) of 0.954 on the TSE data. Its performance on balanced turbo field echo (BTFE) data, which exhibit a distinct T₂-weighted contrast, did not degrade (AUROC: 0.840 to 0.881; AUPR: 0.954 to 0.857). Moreover, bagging OR-KAN with models pre-trained on quality labels delivered the best results on both datasets, outperforming the state-of-the-art (SOTA) supervised method FetMRQC by 14.1 % on TSE (AUROC: 0.828 vs. 0.945) and by 21.9 % on BTFE (AUROC: 0.763 vs. 0.930). By selecting the highest-quality stack in each orientation, OR-KAN improved brain volume reconstruction success rates (with NiftyMIC) by 29.2 % (from 64.4 % to 83.2 %) and by 42.5 % (from 60.0 % to 85.5 %) for normal and abnormal fetuses, respectively. We anticipate its immediate utility in improving the diagnosis of fetal brain abnormalities and advancing the study of human brain development in utero across a wide range of clinical and neuroscientific applications. Code is available at: <span><span>https://github.com/birthlab/OR-KAN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103994"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hippocampal surface morphological variation-based genome-wide association analysis network for biomarker detection of Alzheimer’s disease","authors":"Xiumei Chen ,&nbsp;Xinyue Zhang ,&nbsp;Wei Xiong ,&nbsp;Tao Wang ,&nbsp;Aiwei Jia ,&nbsp;Qianjin Feng ,&nbsp;Meiyan Huang","doi":"10.1016/j.media.2026.103952","DOIUrl":"10.1016/j.media.2026.103952","url":null,"abstract":"<div><div>Performing genome-wide association analysis (GWAS) between hippocampus and whole-genome data can facilitate disease-related biomarker detection of Alzheimer’s disease (AD). However, most existing studies have prioritized hippocampal volume changes and ignored the morphological variations and subfield differences of the hippocampus in AD progression. This disregard restricts the comprehensive understanding of the associations between hippocampus and whole-genome data, which may result in some potentially specific biomarkers of AD being missed. Moreover, the representation of the complex associations between ultra-high-dimensional imaging and whole-genome data remains an unresolved problem in GWAS. To address these issues, we propose an end-to-end hippocampal surface morphological variation-based genome-wide association analysis network (HSM-GWAS) to explore the nonlinear associations between hippocampal surface morphological variations and whole-genome data for AD-related biomarker detection. First, a multi-modality feature extraction module that includes a graph convolution network and an improved diet network is presented to extract imaging and genetic features from non-Euclidean hippocampal surface and whole-genome data, respectively. Second, a dual contrastive learning-based association analysis module is introduced to map and align genetic features to imaging features, thus narrowing the gap between these features and helping explore the complex associations between hippocampal and whole-genome data. Last, a dual cross-attention fusion module is applied to combine imaging and genetic features for disease diagnosis and biomarker detection of AD. Extensive experiments on the real Alzheimer’s Disease Neuroimaging Initiative dataset and simulated data demonstrate that HSM-GWAS considerably improves biomarker detection and disease diagnosis. These findings highlight the ability of HSM-GWAS to discover disease-related biomarkers, suggesting its potential to provide new insights into pathological mechanisms and aid in AD diagnosis. The codes are to be made publicly available at <span><span>https://github.com/Meiyan88/HSM-GWAS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103952"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WSISum: WSI summarization via dual-level semantic reconstruction","authors":"Baizhi Wang ,&nbsp;Kun Zhang ,&nbsp;Yuhao Wang ,&nbsp;Yunjie Gu ,&nbsp;Haijing Luan ,&nbsp;Ying Zhou ,&nbsp;Taiyuan Hu ,&nbsp;Rundong Wang ,&nbsp;Zhidong Yang ,&nbsp;Zihang Jiang ,&nbsp;Rui Yan ,&nbsp;S. Kevin Zhou","doi":"10.1016/j.media.2026.103970","DOIUrl":"10.1016/j.media.2026.103970","url":null,"abstract":"<div><div>Each gigapixel whole slide image (WSI) contains tens of thousands of patches, many of which are redundant, leading to significant computational, storage, and transmission overhead. This motivates the need for automatic WSI summarization, which aims to extract a compact subset of patches that can effectively approximate the original WSI. In this paper, we propose <strong>WSISum</strong>, a unified framework that performs <strong>WSI Sum</strong>marization through dual-level semantic reconstruction. Specifically, WSISum integrates two complementary reconstruction strategies: <em>low-level patch semantic reconstruction</em> via clustering-based sparse sampling; and <em>high-level slide semantic reconstruction</em> through knowledge distillation from multiple WSI-level foundation models. Experimental results show that WSISum achieves satisfactory performance in a variety of downstream tasks, including cancer subtyping, biomarker prediction, and metastasis subtyping, while significantly reducing computational cost. Code and models are available at <span><span>https://github.com/Badgewho/WSISum</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"110 ","pages":"Article 103970"},"PeriodicalIF":11.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Expression of concern “Accelerating cardiac radial-MRI: Fully polar based technique using compressed sensing and deep learning” [Medical Image Analysis, 105C (2025) 103732]","authors":"","doi":"10.1016/j.media.2026.104054","DOIUrl":"https://doi.org/10.1016/j.media.2026.104054","url":null,"abstract":"","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"61 1","pages":""},"PeriodicalIF":10.9,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147524829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition","authors":"Weiyi Zhang ,&nbsp;Peranut Chotcomwongse ,&nbsp;Yinwen Li ,&nbsp;Pusheng Xu ,&nbsp;Ruijie Yao ,&nbsp;Lianhao Zhou ,&nbsp;Yuxuan Zhou ,&nbsp;Hui Feng ,&nbsp;Qiping Zhou ,&nbsp;Xinyue Wang ,&nbsp;Shoujin Huang ,&nbsp;Zihao Jin ,&nbsp;Florence H T Chung ,&nbsp;Shujun Wang ,&nbsp;Yalin Zheng ,&nbsp;Mingguang He ,&nbsp;Danli Shi ,&nbsp;Paisan Ruamviboonsuk","doi":"10.1016/j.media.2026.103942","DOIUrl":"10.1016/j.media.2026.103942","url":null,"abstract":"<div><div>Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2000 patients with labels across four sub-tasks. This paper details the competition’s structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06 %, highlighting the potential of AI in personalized DME treatment and clinical decision-making.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103942"},"PeriodicalIF":11.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reason like a radiologist: Chain-of-thought and reinforcement learning for verifiable report generation","authors":"Peiyuan Jing ,&nbsp;Kinhei Lee ,&nbsp;Zhenxuan Zhang ,&nbsp;Huichi Zhou ,&nbsp;Zhengqing Yuan ,&nbsp;Zhifan Gao ,&nbsp;Lei Zhu ,&nbsp;Giorgos Papanastasiou ,&nbsp;Yingying Fang ,&nbsp;Guang Yang","doi":"10.1016/j.media.2025.103910","DOIUrl":"10.1016/j.media.2025.103910","url":null,"abstract":"<div><div>Radiology report generation is critical for efficiency, but current models often lack the structured reasoning of experts and the ability to explicitly ground findings in anatomical evidence, which limits clinical trust and explainability. This paper introduces BoxMed-RL, a unified training framework to generate spatially verifiable and explainable chest X-ray reports. BoxMed-RL advances chest X-ray report generation through two integrated phases: (1) Pretraining Phase. BoxMed-RL learns radiologist-like reasoning through medical concept learning and enforces spatial grounding with reinforcement learning. (2) Downstream Adapter Phase. Pretrained weights are frozen while a lightweight adapter ensures fluency and clinical credibility. Experiments on two widely used public benchmarks (MIMIC-CXR and IU X-Ray) demonstrate that BoxMed-RL achieves an average 7 % improvement in both METEOR and ROUGE-L metrics compared to state-of-the-art methods. An average 5 % improvement in large language model-based metrics further underscores BoxMed-RL’s robustness in generating high-quality reports. Related code and training templates are publicly available at <span><span>https://github.com/ayanglab/BoxMed-RL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"109 ","pages":"Article 103910"},"PeriodicalIF":11.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145730672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}