Medical image analysis最新文献_第5页

MSARAE: Multiscale adversarial regularized autoencoders for cortical network classification 用于皮质网络分类的多尺度对抗正则化自编码器

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-19 DOI: 10.1016/j.media.2025.103775

Yihui Zhu , Yue Zhou , Xiaotong Zhang , Yueying Li , Yonggui Yuan , Youyong Kong

{"title":"MSARAE: Multiscale adversarial regularized autoencoders for cortical network classification","authors":"Yihui Zhu , Yue Zhou , Xiaotong Zhang , Yueying Li , Yonggui Yuan , Youyong Kong","doi":"10.1016/j.media.2025.103775","DOIUrl":"10.1016/j.media.2025.103775","url":null,"abstract":"<div><div>Due to privacy regulations and technical limitations, current research on the cerebral cortex frequently faces challenges, including limited data availability. The number of samples significantly influences the performance and generalization ability of deep learning models. In general, these models require sufficient training data to effectively learn underlying distributions and features, enabling strong performance on unseen samples. A limited sample size can lead to overfitting, thereby weakening the model’s generalizability. To address these challenges from a data augmentation perspective, we propose a Multi-Scale Adversarial Regularized Autoencoder (MSARAE) for augmenting and classifying cortical structural connectivity. The approach begins with data preprocessing and the construction of cortical structural connectivity networks. To better capture cortical features, the model leverages Laplacian eigenvectors to enhance topological information. Structural connectivity is then generated using variational autoencoders, with multi-scale graph convolutional layers serving as encoders to capture graph representations at different scales. An adversarial regularization mechanism is introduced to minimize the distribution discrepancy in the latent space. By training a discriminator, the model encourages the encoder to produce latent representations that closely match the distribution of real data, thereby improving its representational capacity. Finally, extensive experiments on the major depression disorder (MDD) dataset, the Human Connectome Project (HCP) dataset, and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrated the superiority of the model.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103775"},"PeriodicalIF":11.8,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895890","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}

引用次数: 0

Federated modality-specific encoders and partially personalized fusion decoder for multimodal brain tumor segmentation 联邦模式特定编码器和部分个性化融合解码器用于多模式脑肿瘤分割

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-18 DOI: 10.1016/j.media.2025.103759

Hong Liu , Dong Wei , Qian Dai , Xian Wu , Yefeng Zheng , Liansheng Wang

{"title":"Federated modality-specific encoders and partially personalized fusion decoder for multimodal brain tumor segmentation","authors":"Hong Liu , Dong Wei , Qian Dai , Xian Wu , Yefeng Zheng , Liansheng Wang","doi":"10.1016/j.media.2025.103759","DOIUrl":"10.1016/j.media.2025.103759","url":null,"abstract":"<div><div>Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, some FL participants may possess only a subset of the complete imaging modalities, posing intermodal heterogeneity as a challenge to effectively training a global model on all participants’ data. Meanwhile, each participant expects a personalized model tailored to its local data characteristics in FL. This work proposes a new FL framework with federated modality-specific encoders and partially personalized multimodal fusion decoders (FedMEPD) to address the two concurrent issues. Specifically, FedMEPD employs an exclusive encoder for each modality to account for the intermodal heterogeneity. While these encoders are fully federated, the decoders are partially personalized to meet individual needs—using the discrepancy between global and local parameter updates to dynamically determine which decoder filters are personalized. Implementation-wise, a server with full-modal data employs a fusion decoder to fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation. Moreover, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the model parameters. Conversely, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up for the information loss due to absent modalities. FedMEPD is validated on the BraTS 2018 and 2020 multimodal brain tumor segmentation benchmarks. Results show that it outperforms various up-to-date methods for multimodal and personalized FL, and its novel designs are effective.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103759"},"PeriodicalIF":11.8,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895754","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}

引用次数: 0

Collaborative surgical instrument segmentation for monocular depth estimation in minimally invasive surgery 微创手术中用于单眼深度估计的协同手术器械分割

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-18 DOI: 10.1016/j.media.2025.103765

Xue Li , Wenxin Chen , Xingguang Duan , Xiaoyi Gu , Changsheng Li

{"title":"Collaborative surgical instrument segmentation for monocular depth estimation in minimally invasive surgery","authors":"Xue Li , Wenxin Chen , Xingguang Duan , Xiaoyi Gu , Changsheng Li","doi":"10.1016/j.media.2025.103765","DOIUrl":"10.1016/j.media.2025.103765","url":null,"abstract":"<div><div>Depth estimation is essential for image-guided surgical procedures, particularly in minimally invasive environments where accurate 3D perception is critical. This paper proposes a two-stage self-supervised monocular depth estimation framework that incorporates instrument segmentation as a task-level prior to enhance spatial understanding. In the first stage, segmentation and depth estimation models are trained separately on the RIS, SCARED datasets to capture task-specific representations. In the second stage, segmentation masks predicted on the dVPN dataset are fused with RGB inputs to guide the refinement of depth prediction.</div><div>The framework employs a shared encoder and multiple decoders to enable efficient feature sharing across tasks. Comprehensive experiments on the RIS, SCARED, dVPN, and SERV-CT datasets validate the effectiveness and generalizability of the proposed approach. The results demonstrate that segmentation-aware depth estimation improves geometric reasoning in challenging surgical scenes, including those with occlusions, specularities regions.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103765"},"PeriodicalIF":11.8,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887526","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}

引用次数: 0

BiasPruner: Mitigating bias transfer in continual learning for fair medical image analysis BiasPruner：在持续学习中减轻公平医学图像分析的偏见转移

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-18 DOI: 10.1016/j.media.2025.103764

Nourhan Bayasi , Jamil Fayyad , Alceu Bissoto , Ghassan Hamarneh , Rafeef Garbi

{"title":"BiasPruner: Mitigating bias transfer in continual learning for fair medical image analysis","authors":"Nourhan Bayasi , Jamil Fayyad , Alceu Bissoto , Ghassan Hamarneh , Rafeef Garbi","doi":"10.1016/j.media.2025.103764","DOIUrl":"10.1016/j.media.2025.103764","url":null,"abstract":"<div><div>Continual Learning (CL) enables neural networks to learn new tasks while retaining previous knowledge. However, most CL methods fail to address bias transfer, where spurious correlations propagate to future tasks or influence past knowledge. This bidirectional bias transfer negatively impacts model performance and fairness, especially in medical imaging, where it can lead to misdiagnoses and unequal treatment. In this work, we show that conventional CL methods amplify these biases, posing risks for diverse patient cohorts. To address this, we propose <span>BiasPruner</span>, a framework that mitigates bias propagation through debiased subnetworks, while preserving sequential learning and avoiding catastrophic forgetting. <span>BiasPruner</span> computes a bias attribution score to identify and prune network units responsible for spurious correlations, creating task-specific subnetworks that learn unbiased representations. As new tasks are learned, the framework integrates non-biased units from previous subnetworks to preserve transferable knowledge and prevent bias transfer. During inference, a task-agnostic gating mechanism selects the optimal subnetwork for robust predictions. We evaluate <span>BiasPruner</span> on medical imaging benchmarks, including skin lesion and chest X-ray classification tasks, where biased data (e.g., spurious skin tone correlations) can exacerbate disparities. Our experiments show that <span>BiasPruner</span> outperforms state-of-the-art CL methods in both accuracy and fairness. Code is available at: <span><span>BiasPruner</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103764"},"PeriodicalIF":11.8,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865887","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}

引用次数: 0

Aligning personalized biomarker trajectories onto a common time axis: a connectome-based ODE model for Tau–Amyloid beta dynamics 将个性化生物标志物轨迹对准共同的时间轴：tau -淀粉样蛋白动力学的基于连接体的ODE模型

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-15 DOI: 10.1016/j.media.2025.103757

Zheyu Wen , George Biros , the Alzheimer’s Disease Neuroimaging Initiative (ADNI)

{"title":"Aligning personalized biomarker trajectories onto a common time axis: a connectome-based ODE model for Tau–Amyloid beta dynamics","authors":"Zheyu Wen , George Biros , the Alzheimer’s Disease Neuroimaging Initiative (ADNI)","doi":"10.1016/j.media.2025.103757","DOIUrl":"10.1016/j.media.2025.103757","url":null,"abstract":"<div><div>Abnormal tau and amyloid beta are two primary imaging biomarkers used to assist in the diagnosis of Alzheimer’s disease (AD). Recent efforts have focused on developing mechanism-based biophysical models to explain the spatiotemporal dynamics of these biomarkers. In this study, we adopt a connectome-based ODE model to capture the dynamics of tau and amyloid beta (<span><math><mrow><mtext>A</mtext><mi>β</mi></mrow></math></span>), aiming to predict personalized future values of these biomarkers. The ODE model includes diffusion, reaction, and clearance terms, and accounts for tau–<span><math><mrow><mtext>A</mtext><mi>β</mi></mrow></math></span> interactions. Additionally, it assumes a sparse initial condition (IC) of abnormalities, based on the assumption of localized initiation. Besides tau and <span><math><mrow><mtext>A</mtext><mi>β</mi></mrow></math></span>, brain atrophy is used as a marker of neurodegeneration. We discuss the mathematical model of atrophy integrated into the tau–<span><math><mrow><mtext>A</mtext><mi>β</mi></mrow></math></span> model. A common limitation in popular models is the use of chronological age as the time axis, which prevents the unification of subject trajectories onto a common time scale and hinders comprehensive cohort analysis. To address this issue, we use a normalized disease age that relates chronological age to biomarker values. In the ODE model, we use the disease age to track time and the biomarker dynamics. Furthermore, our analysis of region-of-interest-wise tau–<span><math><mrow><mtext>A</mtext><mi>β</mi></mrow></math></span> temporal correlation reveals that different regions of interest (ROIs) play distinct roles across various disease stages.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103757"},"PeriodicalIF":11.8,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893532","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}

引用次数: 0

Pixel-responsive optimization beamforming method for ultrasound transcranial imaging 超声经颅成像的像素响应优化波束形成方法

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-14 DOI: 10.1016/j.media.2025.103762

Junyi Wang , Tianhua Zhou , Gaobo Zhang , Boyi Li , Xin Liu , Dean Ta

{"title":"Pixel-responsive optimization beamforming method for ultrasound transcranial imaging","authors":"Junyi Wang , Tianhua Zhou , Gaobo Zhang , Boyi Li , Xin Liu , Dean Ta","doi":"10.1016/j.media.2025.103762","DOIUrl":"10.1016/j.media.2025.103762","url":null,"abstract":"<div><div>The propagation of acoustic waves through bone remains a longstanding challenge in transcranial ultrasound imaging. As a highly scattering medium, the skull causes significant distortions in the ultrasonic wavefield, introducing complex aberrations that hinder precise image reconstruction. Conventional delay-and-sum (DAS) algorithms, which process pixels independently, fail to account for inter-pixel relationships, limiting their ability to correct such distortions. To address this issue, we propose a Pixel-Responsive Optimization (PRO) Beamforming Method that leverages backscattered signals from compound plane waves. By constructing a pixel-response matrix and simulating a virtual acoustic lens, PRO isolates and aligns distorted fields with reference phases to restore near-ideal propagation. Experiments on bovine femur plates and a human skull demonstrate improved image resolution, recovery of submerged signals, and artifact suppression. PRO achieves up to a 90% improvement in full-width at half-maximum (FWHM) compared to DAS, requiring no prior assumptions and showing strong generalizability in complex scenarios through bone. This advancement holds promise for future <em>in vivo</em> transcranial brain imaging applications.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103762"},"PeriodicalIF":11.8,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860858","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}

引用次数: 0

Speckle2Self: Self-supervised ultrasound speckle reduction without clean data Speckle2Self：无需清洁数据的自我监督超声斑点减少

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-13 DOI: 10.1016/j.media.2025.103755

Xuesong Li , Nassir Navab , Zhongliang Jiang

{"title":"Speckle2Self: Self-supervised ultrasound speckle reduction without clean data","authors":"Xuesong Li , Nassir Navab , Zhongliang Jiang","doi":"10.1016/j.media.2025.103755","DOIUrl":"10.1016/j.media.2025.103755","url":null,"abstract":"<div><div>Image denoising is a fundamental task in computer vision, particularly in medical ultrasound (US) imaging, where speckle noise significantly degrades image quality. Although recent advancements in deep neural networks have led to substantial improvements in denoising for natural images, these methods cannot be directly applied to US speckle noise, as it is not purely random. Instead, US speckle arises from complex wave interference within the body microstructure, making it tissue-dependent. This dependency means that obtaining two independent noisy observations of the same scene, as required by pioneering Noise2Noise, is not feasible. Additionally, blind-spot networks also cannot handle US speckle noise due to its high spatial dependency. To address this challenge, we introduce Speckle2Self, a novel self-supervised algorithm for speckle reduction using only single noisy observations. The key insight is that applying a multi-scale perturbation (MSP) operation introduces tissue-dependent variations in the speckle pattern across different scales, while preserving the shared anatomical structure. This enables effective speckle suppression by modeling the clean image as a low-rank signal and isolating the sparse noise component. To demonstrate its effectiveness, Speckle2Self is comprehensively compared with conventional filter-based denoising algorithms and SOTA learning-based methods, using both realistic simulated US images and human carotid US images. Additionally, data from multiple US machines are employed to evaluate model generalization and adaptability to images from unseen domains. <strong>Project page:</strong> <span><span>https://noseefood.github.io/us-speckle2self/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103755"},"PeriodicalIF":11.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860859","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}

引用次数: 0

Exploring the robustness of TractOracle methods in RL-based tractography 探索基于rl的TractOracle方法的鲁棒性

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-13 DOI: 10.1016/j.media.2025.103743

Jeremi Levesque, Antoine Théberge, Maxime Descoteaux, Pierre-Marc Jodoin

{"title":"Exploring the robustness of TractOracle methods in RL-based tractography","authors":"Jeremi Levesque, Antoine Théberge, Maxime Descoteaux, Pierre-Marc Jodoin","doi":"10.1016/j.media.2025.103743","DOIUrl":"10.1016/j.media.2025.103743","url":null,"abstract":"<div><div>Tractography algorithms leverage diffusion MRI to reconstruct the fibrous architecture of the brain’s white matter. Among machine learning approaches, reinforcement learning (RL) has emerged as a promising framework for tractography, outperforming traditional methods in several key aspects. TractOracle-RL, a recent RL-based approach, reduces false positives by incorporating anatomical priors into the training process via a reward-based mechanism.</div><div>In this paper, we investigate four extensions of the original TractOracle-RL framework by integrating recent advances in RL, and we evaluate their performance across five diverse diffusion MRI datasets. Results demonstrate that combining an oracle with the RL framework consistently leads to robust and reliable tractography, regardless of the specific method or dataset used.</div><div>We also introduce a novel RL training scheme called <em>Iterative Reward Training (IRT)</em>, inspired by the Reinforcement Learning from Human Feedback (RLHF) paradigm. Instead of relying on human input, IRT leverages bundle filtering methods to iteratively refine the oracle’s guidance throughout training. Experimental results show that RL methods trained with oracle feedback significantly outperform widely used tractography techniques in terms of accuracy and anatomical validity.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103743"},"PeriodicalIF":11.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852185","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}

引用次数: 0

Acquisition-independent deep learning for quantitative MRI parameter estimation using neural controlled differential equations 利用神经控制微分方程进行定量MRI参数估计的非获取深度学习

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-11 DOI: 10.1016/j.media.2025.103768

Daan Kuppens , Sebastiano Barbieri , Daisy van den Berg , Pepijn Schouten , Harriet C. Thoeny , Hanneke W.M. van Laarhoven , Myrte Wennen , Oliver J. Gurney-Champion

{"title":"Acquisition-independent deep learning for quantitative MRI parameter estimation using neural controlled differential equations","authors":"Daan Kuppens , Sebastiano Barbieri , Daisy van den Berg , Pepijn Schouten , Harriet C. Thoeny , Hanneke W.M. van Laarhoven , Myrte Wennen , Oliver J. Gurney-Champion","doi":"10.1016/j.media.2025.103768","DOIUrl":"10.1016/j.media.2025.103768","url":null,"abstract":"<div><div>Deep learning has proven to be a suitable alternative to least squares (LSQ) fitting for parameter estimation in various quantitative MRI (QMRI) models. However, current deep learning implementations are not robust to changes in MR acquisition protocols. In practice, QMRI acquisition protocols differ substantially between different studies and clinical settings. The lack of generalizability and adoptability of current deep learning approaches for QMRI parameter estimation impedes the implementation of these algorithms in clinical trials and clinical practice. Neural Controlled Differential Equations (NCDEs) allow for the sampling of incomplete and irregularly sampled data with variable length, making them ideal for use in QMRI parameter estimation. In this study, we show that NCDEs can function as a generic tool for the accurate estimation of QMRI parameters, regardless of QMRI sequence length, configuration of independent variables and QMRI forward model (variable flip angle <em>T1</em>-mapping, intravoxel incoherent motion MRI, dynamic contrast-enhanced MRI). NCDEs achieved lower mean squared error than LSQ fitting in low-SNR simulations and in vivo in challenging anatomical regions like the abdomen and leg, but this improvement was no longer evident at high SNR. When NCDEs improve parameter estimation, they tend to do so by reducing the variance in estimation errors. These findings suggest that NCDEs offer a robust approach for reliable QMRI parameter estimation, especially in scenarios with high uncertainty or low image quality. We believe that with NCDEs, we have solved one of the main challenges for using deep learning for QMRI parameter estimation in a broader clinical and research setting.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103768"},"PeriodicalIF":11.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144899217","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}

引用次数: 0

Towards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond 心脏MRI基础模型：全心评估及其他方面的综合可视化表表示

IF 11.8 1区医学

Medical image analysis Pub Date : 2025-08-11 DOI: 10.1016/j.media.2025.103756

Yundi Zhang , Paul Hager , Che Liu , Suprosanna Shit , Chen Chen , Daniel Rueckert , Jiazhen Pan

{"title":"Towards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond","authors":"Yundi Zhang , Paul Hager , Che Liu , Suprosanna Shit , Chen Chen , Daniel Rueckert , Jiazhen Pan","doi":"10.1016/j.media.2025.103756","DOIUrl":"10.1016/j.media.2025.103756","url":null,"abstract":"<div><div>Cardiac magnetic resonance (CMR) imaging is the gold standard for non-invasive cardiac assessment, offering rich spatio-temporal views of the heart’s anatomy and physiology. Patient-level health factors, such as demographics, metabolic, and lifestyle, are known to substantially influence cardiovascular health and disease risk, yet remain uncaptured by CMR alone. To holistically understand cardiac health and to enable the best possible interpretation of an individual’s disease risk, CMR and patient-level factors must be jointly exploited within an integrated framework. Recent multi-modal approaches have begun to bridge this gap, yet they often rely on limited spatio-temporal data and focus on isolated clinical tasks, thereby hindering the development of a comprehensive representation for cardiac/health evaluation.</div><div>To overcome these limitations, we introduce <em>ViTa</em>, a step toward foundation models that delivers a comprehensive representation of the heart and a precise interpretation of individual disease risk. Leveraging data from 42,000 UK Biobank participants, ViTa integrates 3D+T cine stacks from short-axis and long-axis views, enabling a complete capture of the cardiac cycle. These imaging data are then fused with detailed tabular patient-level factors, enabling context-aware insights. This multi-modal paradigm supports a wide spectrum of downstream tasks, including cardiac phenotype and physiological feature prediction, segmentation, and classification of cardiac/metabolic diseases within a single unified framework. By learning a shared latent representation that bridges rich imaging features and patient context, ViTa moves beyond traditional, task-specific models toward a universal, patient-specific understanding of cardiac health, highlighting its potential to advance clinical utility and scalability in cardiac analysis. <span><span><sup>2</sup></span></span></div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103756"},"PeriodicalIF":11.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852186","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}

引用次数: 0