MEDICAL IMAGE ANALYSIS医学图像分析
MEDICAL IMAGE ANALYSIS(英文缩写 MED IMAGE ANAL),ISSN 1361-8415,eISSN 1361-8423,中文译名:医学图像分析 是一本学术期刊。本页汇总该期刊的最新影响因子、分区信息以及最新收录于 PubMed 的文献,帮助您快速了解期刊全貌。
发文量统计区间：2025-11-01 至 2026-10-31，按本站收录文献的发表日期统计。
期刊介绍
历年影响因子趋势
| JCR 数据年份 | 影响因子 | JCR 分区 |
|---|---|---|
| 2021 | 13.828 | Q1 |
| 2022 | 10.900 | Q1 |
| 2023 | 10.700 | Q1 |
| 2024 | 11.800 | Q1 |
| 2025 | 14.000 | Q1 |
MEDICAL IMAGE ANALYSIS 最新收录文献
-
1. MSRepaint: Multiple Sclerosis Repaint with conditional denoising diffusion implicit model for bidirectional lesion filling and synthesis.
1. MSRepaint：基于条件去噪扩散隐式模型的多发性硬化病灶重绘，用于双向病灶填充与合成PMID:日期:2026-09-30In multiple sclerosis (MS), lesions interfere with automated magnetic resonance imaging (MRI) analyses such as brain parcellation and deformable registration, while lesion segmentation models are hindered by the limited availability of annotated training data. To address both issues, we propose MSRepaint, a unified diffusion-based generative model for bidirectional lesion filling and synthesis that restores anatomical continuity for downstream analyses and augments segmentation through realistic data generation. MSRepaint conditions on spatial lesion masks for voxel-level control, incorporates contrast dropout to handle missing inputs, integrates a repainting mechanism to preserve surrounding anatomy during lesion filling and synthesis, and employs a multi-view DDIM inversion and fusion pipeline for 3D consistency with fast inference. Extensive evaluations demonstrate the effectiveness of MSRepaint across multiple tasks. For lesion filling, we evaluate both the accuracy within the filled regions and the impact on downstream tasks including brain parcellation and deformable registration. MSRepaint outperforms the FSL and NiftySeg lesion filling methods, and achieves accuracy on par with FastSurfer-LIT, a recent diffusion model-based lesion filling method, while offering over 20×faster inference. For lesion synthesis, state-of-the-art MS lesion segmentation models trained on MSRepaint-synthesized data outperform those trained on CarveMix-synthesized data or real ISBI challenge training data across multiple benchmarks, including the MICCAI 2016 and UMCL datasets. Additionally, we demonstrate that MSRepaint's unified bidirectional filling and synthesis capability, with full spatial control over lesion appearance, enables high-fidelity mask-conditioned voxel-wise control of lesion appearance within a unified framework. Our code is available at https://github.com/Jinwei1209/msrepaint.
-
2. Cortex-grounded diffusion models for brain image generation.
2. 基于皮层基础的大脑图像生成扩散模型PMID:日期:2026-09-29Synthetic neuroimaging data can mitigate critical limitations of real-world datasets, including the scarcity of rare phenotypes, domain shifts across scanners, and insufficient longitudinal coverage. However, existing generative models largely rely on weak conditioning signals, such as labels or text, which lack anatomical grounding and often produce biologically implausible outputs. To this end, we introduce Cor2Vox, a cortex-grounded generative framework for brain magnetic resonance image (MRI) synthesis that ties image generation to continuous structural priors of the cerebral cortex. It leverages high-resolution cortical surfaces to guide a 3D shape-to-image Brownian bridge diffusion process, enabling topologically faithful synthesis and precise control over underlying anatomies. To support the generation of new, realistic brain shapes, we developed a large-scale statistical shape model of cortical morphology derived from over 33,000 UK Biobank scans. We validated the fidelity of Cor2Vox based on traditional image quality metrics, advanced cortical surface reconstruction, and whole-brain segmentation quality, outperforming many baseline methods. Across three applications, namely (i) anatomy-guided synthesis, (ii) simulation of progressive gray matter atrophy, and (iii) harmonization of in-house frontotemporal dementia scans with public datasets, Cor2Vox preserved fine-grained cortical morphology at the sub-voxel level. Notably, the proposed model exhibits inherent robustness to variations in cortical geometry and unseen dementia phenotypes without retraining, paving the way for disease progression modeling and robust data augmentation in rare neurodegenerative disorders.
-
3. Hierarchical multi-atlas fusion network for robust and interpretable cross-site analysis of functional connectomes in major depressive disorder.
3. 用于重性抑郁障碍功能连接组稳健且可解释的跨站点分析的层次多图谱融合网络PMID:日期:2026-09-29Major depressive disorder (MDD) is associated with distributed disruptions in functional brain networks, yet current connectome-based biomarkers often rely on a single parcellation and show limited cross-site robustness and biological interpretability. We propose a Hierarchical Multi-Atlas Fusion Network (HMAF-Net) for robust and interpretable cross-site analysis of functional connectomes in MDD. HMAF-Net reconciles heterogeneous anatomical and functional atlases by learning a small set of shared fusion nodes that serve as latent anchors for cross-atlas semantic alignment. For each atlas, it extracts node-wise descriptors and uses Transformer-based sparse soft assignment with a structure-aware contrastive objective to align atlas nodes in a common semantic space while retaining atlas-specific information. The resulting fusion-node embeddings support subject-level classification and spatial mapping for biomarker localization and imaging-transcriptomic association. We evaluated HMAF-Net on the multi-site REST-meta-MDD cohort (N = 1,611). Under 10-fold cross-validation, HMAF-Net achieved 72.28% accuracy and 71.49% AUC, showing the highest mean accuracy among representative atlas-fusion and graph-based baselines under identical splits. Under leave-one-site-out evaluation, it reached 77.48% mean accuracy, with site-wise analyses indicating residual variability associated with cohort size and head motion. External validation on two independent MDD datasets further supported cross-dataset generalizability. Fusion-node involvement shifts revealed reproducible fronto-limbic and default-mode-salience alterations. These spatial profiles were associated with Allen Human Brain Atlas expression gradients and enriched for synaptic and neurotransmission pathways, providing a molecularly grounded axis for interpretation. By integrating cross-atlas alignment, cross-site evaluation, and transcriptomic interpretation, HMAF-Net yields compact connectomic embeddings for reproducible and mechanistically informed MDD biomarker development.
-
4. Unsupervised high-resolution 3D MRI motion correction via physics-informed implicit neural representations.
PMID:日期:2026-09-29Motion-corrupted inverse problems remain a central bottleneck in magnetic resonance imaging (MRI), especially for high-resolution 3D acquisitions where long readouts couple rigid-body displacement with non-Cartesian k-space sampling. We present a physics-informed implicit neural representation (INR) that recasts 3D motion correction as continuous neural field estimation. The method embeds a differentiable rigid-body motion operator into the INR forward model, enabling joint, zero-shot optimization of the motion trajectory and motion-free volume directly from raw k-space, without external navigators or paired supervision. By enforcing strict data consistency in a coordinate-based representation, the framework yields globally coherent reconstructions and mitigates hallucination risks under severe motion. Across simulated perturbations and real in-vivo high-resolution radial scans, our approach consistently improves motion estimation accuracy, structural preservation, downstream segmentation, and generalizes across subjects and protocols. Remarkably, for kooshball acquisitions with motion severity up to 10°/20mm, our method outperforms the navigator-based method by approximately 2 dB in peak signal-to-noise ratio. These results establish a unified paradigm for unsupervised, physics-consistent artificial intelligence solving of motion-corrupted MRI inverse problems, with broad applicability beyond a single sequence or anatomy. The source code is available at: https://github.com/AMRI-Lab/MoCo-3DRadial.
-
5. Topology-aware unsupervised domain adaptation for curvilinear structure segmentation.
5. 面向曲线结构分割的拓扑感知无监督域适应PMID:日期:2026-09-24Unsupervised domain adaptation (UDA) enables segmentation models to generalize to unlabeled clinical domains. However, existing methods primarily address appearance-level discrepancies, while neglecting topological mismatches in connectivity, branching, and loop structure-characteristics of curvilinear anatomies. This oversight frequently leads to fragmented, clinically unreliable segmentations of structures such as vascular networks. To bridge this gap, we propose TopoUDA, a framework that explicitly integrates topological reasoning at multiple stages of adaptation. First, we design a Curvilinear-Aware Discriminator (CAD), an adversarial critic that distinguishes anatomically plausible structures from fragmented predictions based on a compact topological fingerprint. To enable end-to-end training, we introduce a differentiable proxy network that provides a valid gradient path through this otherwise non-differentiable structural assessment. Second, we develop a Hierarchical Topological Refiner (HTR) that leverages persistent homology to identify stable structural components and refine spatially related fragments, generating structurally coherent pseudo-labels. Third, we introduce a Hybrid Trust Mechanism (HTM) that combines appearance- and topology-based reliability scores from dual discriminators to adaptively weight pseudo-label supervision, ensuring the model learns primarily from anatomically plausible predictions. Extensive validation across retinal fundus photography, Optical Coherence Tomography Angiography (OCTA), and electron microscopy demonstrates that TopoUDA significantly outperforms state-of-the-art methods in both overlap and topological metrics. Furthermore, qualitative generalization on the large-scale, unlabeled AI-READI cohort underscores TopoUDA's practical applicability to real-world clinical data where ground-truth annotations are unavailable.
-
6. CXR-LT 2026 challenge: Multi-center long-tailed and zero shot chest X-ray classification.
6. CXR-LT 2026挑战赛：多中心长尾和零样本胸部X射线分类PMID:日期:2026-09-24Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing benchmarks often rely on closed-set classes from a single institution, failing to capture the prevalence of rare diseases or the appearance of novel findings. To address this, we present the CXR-LT challenge. The first event, CXR-LT 2023, established a large-scale benchmark for long-tailed multi-label CXR classification and identified key challenges in rare disease recognition. CXR-LT 2024 further expanded the label space and introduced a zero-shot task to study generalization to unseen findings. Building on the success of CXR-LT 2023 and 2024, this third iteration of the benchmark introduces a multi-center dataset comprising over 145,000 images from PadChest and NIH Chest X-ray datasets. Additionally, all development and test sets in CXR-LT 2026 are annotated by radiologists, providing a more reliable and clinically grounded evaluation than report-derived labels. The challenge defines two core tasks this year: (1) Robust Multi-Label Classification on 30 known classes and (2) Open-World Generalization to 6 unseen (out-of-distribution) rare disease classes. This paper summarizes the overview of the CXR-LT 2026 challenge. We describe the data collection and annotation procedures, analyze solution strategies adopted by participating teams, and evaluate head-versus-tail performance, calibration, and cross-center generalization gaps. Our results show that vision-language foundation models improve both in-distribution and zero-shot performance, but detecting rare findings under multi-center shift remains challenging. Our study provides a foundation for developing and evaluating AI systems in realistic long-tailed and open-world clinical conditions.
-
7. Meta-analysis prompt guided multi-task graph transformer for joint analysis of cognitive deficits and psychiatric disorders.
7. 元分析提示引导的多任务图变换器用于认知缺陷与精神疾病的联合分析PMID:日期:2026-09-23Psychiatric disorders, such as schizophrenia and attention-deficit/hyperactivity disorder (ADHD), are associated with altered functional connectivity (FC) and are often accompanied by cognitive deficits. Leveraging the shared neural mechanisms underlying both psychiatric disorders and cognitive impairment may improve diagnostic accuracy. However, due to the complexity and heterogeneity of these conditions, diagnosis based on FC alone remains challenging in terms of accuracy and biomarker reliability. To address these challenges, we propose a meta-analysis prompt guided multi-task graph transformer network that simultaneously predicts psychiatric disorder and cognitive deficits while identifying associated alterations in brain FC. The proposed framework employs a graph transformer as a common encoder and integrates a joint attention mechanism to capture shared disorder-cognition representations, together with saliency pooling to identify task-relevant brain regions. To enhance the robustness and interpretability of the learned saliency patterns, we introduce large language models (LLMs) to encode meta-analysis priors derived from the BrainMap database. Specifically, activation probability maps constructed from 466 functional neuroimaging studies are converted into natural-language prompts and embedded using LLMs, providing semantically rich and flexible priors that guide feature learning beyond handcrafted correlation constraints. In addition, subject-level demographic information is encoded as LLM-based text embeddings and incorporated into the model to support individualized prediction. A contrastive learning objective is further designed to align text-based embeddings with FC-derived representations. Experiments on the COBRE, ADHD-200, and SRPBS datasets, comprising 842 subjects in total, demonstrate that our method outperforms six single-task methods and seven state-of-the-art multi-task learning approaches in both schizophrenia and ADHD classification, as well as in the prediction of related cognitive deficits. The identified biomarkers are consistent with established findings while also revealing discriminative features, underscoring their potential relevance for future treatment development and longitudinal follow-up studies.
-
8. FPGL: A meta-learned implicit neural representation framework for medical image segmentation.
8. FPGL：一种用于医学图像分割的元学习隐式神经表示框架PMID:日期:2026-09-23Modern state-of-the-art deep learning architectures for medical image segmentation rely strictly on feed-forward passes over dense pixel/voxel grids, which scale poorly to large signals. Implicit neural representations (INRs) offer a lightweight, continuous alternative to raw grids, but are traditionally signal-specific and lack the semantic coherence needed for dataset-level predictive tasks. In this study, we introduce FPGL, a framework that adapts INRs for medical segmentation by meta-learning a shared initialization. By jointly fitting scans and segmentation maps across a training dataset, FPGL can segment novel subjects simply by fine-tuning on their raw test-time observations. We expand on our preliminary MICCAI study of this work in two key ways. First, we enable both first-order (Reptile) and second-order (MAML) meta-learning routines. Second, we introduce a generalized formulation that allows for segmentation from indirect measurements of a scan, such as tomographic projections and demonstrate several proofs-of-concept experiments across various forward and inverse tasks. We evaluate FPGL on a well-aligned brain 2D/3D MRI dataset and a more heterogeneous abdominal 2D CT dataset. On the MRI data, FPGL matches U-Net baselines. However, performance drops significantly on the CT dataset, revealing a sensitivity to spatial misalignments unexplored in our previous MRI-only study. Interestingly, performing CT segmentation directly from the scans and indirectly from sparse synthetic tomographic projections yields remarkably similar performance, suggesting that FPGL's current optimization design is not yet fully exploiting all details in a scan. We conduct additional studies and reveal key insights on the task- and optimizer-specific behavior of FPGL. By outlining both its promise and its current limitations, this study establishes a strong foundation for advancing the exciting new field of INR-based medical image segmentation. Our codebase is available at https://github.com/kushalvyas/FPGL.
-
9. {"_":"TID: Towards trustworthy incomplete modality diagnosis via dual-axis adaptive completion and confidence-aware integration.","sup":["2"]}
9. {"_":"TID：通过双轴自适应补全和置信度感知整合实现可信的不完整模态诊断。","sup":["2"]}PMID:日期:2026-09-23Multimodal medical images provide abundant and complementary diagnostic cues that are often indispensable for accurate clinical decision-making. However, various constraints, such as limited equipment availability, physical limitations of patients, etc. often lead to incomplete modality of medical data acquisition in the real world. This scenario makes it difficult to design robust and trustworthy diagnostic AI models under missing-modality conditions. In addition, for some samples, cross-modal completion may not always be beneficial when the available modality representation can already support a reliable prediction. Blindly completing every missing modality may introduce noisy or mismatched complementary features, increase unnecessary computation, and potentially degrade model performance. To address these limitations, we propose TID, a multimodal diagnostic framework, which adaptively completes missing modalities and explicitly models cross-modal interactions while maintaining trustworthiness and robustness against missing modality scenarios. Our framework incorporates two key innovations. Firstly, we design a Dual-axis Adaptive Modality Completion (DAA) module, which integrates vertical and horizontal completion strategies to efficiently estimate whether retrieval-based cross-modal completion is expected to provide reliable complementary evidence for the current sample, or cross-modal retrieval is needed for adaptive modality completion. Secondly, we introduce Dynamic Collaborative Confidence-aware Modality Integration (DCC) module, which estimates both unimodal-confidence and synergistic-confidence to capture synergistic or conflicting interactions across modalities, thereby ensuring trustworthy diagnostic predictions. Extensive experiments on three multimodal medical imaging datasets demonstrate that our TID achieves superior performance compared with other state-of-the-art methods under diverse missing-modality scenarios. The implementation code is publicly available at https://github.com/lijing-coder/T2ID.
-
10. A vector Bayesian beamforming framework with noise covariance learning for robust MEG source imaging.
10. 一种带有噪声协方差学习的矢量贝叶斯波束成形框架，用于稳健的MEG源成像PMID:日期:2026-09-23Magnetoencephalography (MEG) provides unparalleled spatiotemporal resolution for non-invasive brain functional imaging. This study aims to improve the robustness and accuracy of voxel-based vector beamformers for MEG source imaging by addressing covariance estimation instability under low-SNR, limited-sample, correlated-source, and non-white noise conditions. In this work, we propose a vector Bayesian beamforming framework with noise covariance learning to address these challenges. The proposed method formulates MEG source imaging as a hierarchical Bayesian inference problem, jointly modeling vector sources and full positive-definite noise covariance structures. By leveraging data-driven covariance learning and sparsity-promoting priors, the framework enables adaptive refinement of the data covariance matrix, thereby enhancing spatial focusing and temporal reconstruction fidelity. Notably, the proposed approach provides a unified interpretation of covariance regularization in beamforming and improves robustness against correlated sources and noise contamination. We evaluate the method on both simulated correlated sources datasets across a wide range of SNR conditions and real 64-channel optically pumped magnetometer (OPM)-MEG recordings under multiple stimulus paradigms. Experimental results demonstrate that the proposed approach achieves an average improvement of 18.03% in AUC compared to conventional beamformers, while maintaining millimeter-level localization accuracy. These results highlight its superior performance in both spatial localization and dynamic signal reconstruction, suggesting strong potential for neuroscience research and clinical applications. The implementation is publicly available at: https://github.com/gao815/VBNLBF.