Medical image analysis最新文献

{"title":"Deep generation of personalized connectomes based on individual attributes","authors":"Yuanzhe Liu ,&nbsp;Caio Seguin ,&nbsp;Sina Mansour L․ ,&nbsp;Ye Ella Tian ,&nbsp;Maria A. Di Biase ,&nbsp;Andrew Zalesky","doi":"10.1016/j.media.2025.103761","DOIUrl":"10.1016/j.media.2025.103761","url":null,"abstract":"<div><div>An individual’s connectome is unique. Interindividual variation in connectome architecture associates with disease status, cognition, lifestyle factors, and other personal attributes. While models to predict personal attributes from a person’s connectome are abundant, the inverse task—inferring connectome architecture from an individual’s personal profile—has not been widely studied. Here, we introduce a deep model to generate a person’s entire connectome exclusively based on their age, sex, body phenotypes, cognition, and lifestyle factors. Using the richly phenotyped UK Biobank connectome cohort (N=8,086), we demonstrate that our model can generate network architectures that closely recapitulate connectomes mapped empirically using diffusion MRI and tractography. We find that age, sex, and body phenotypes exert the strongest influence on the connectome generation process, with an impact approximately four times greater than that of cognition and lifestyle factors. Regional differences in the importance of measures were observed, including an increased importance of cognition in the association cortex relative to the visual system. We further show that generated connectomes can improve the training of machine learning models and reduce their predictive errors. Our work demonstrates the feasibility of inferring brain connectivity from an individual’s personal data and enables future applications of connectome generation such as data augmentation and anonymous data sharing.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103761"},"PeriodicalIF":11.8,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829842","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":"OCELOT 2023: Cell detection from cell–tissue interaction challenge","authors":"JaeWoong Shin ,&nbsp;Jeongun Ryu ,&nbsp;Aaron Valero Puche ,&nbsp;Jinhee Lee ,&nbsp;Biagio Brattoli ,&nbsp;Wonkyung Jung ,&nbsp;Soo Ick Cho ,&nbsp;Kyunghyun Paeng ,&nbsp;Chan-Young Ock ,&nbsp;Donggeun Yoo ,&nbsp;Zhaoyang Li ,&nbsp;Wangkai Li ,&nbsp;Huayu Mai ,&nbsp;Joshua Millward ,&nbsp;Zhen He ,&nbsp;Aiden Nibali ,&nbsp;Lydia Anette Schoenpflug ,&nbsp;Viktor Hendrik Koelzer ,&nbsp;Xu Shuoyu ,&nbsp;Ji Zheng ,&nbsp;Sérgio Pereira","doi":"10.1016/j.media.2025.103751","DOIUrl":"10.1016/j.media.2025.103751","url":null,"abstract":"<div><div>Pathologists routinely alternate between different magnifications when examining Whole-Slide Images, allowing them to evaluate both broad tissue morphology and intricate cellular details to form comprehensive diagnoses. However, existing deep learning-based cell detection models struggle to replicate these behaviors and learn the interdependent semantics between structures at different magnifications. A key barrier in the field is the lack of datasets with multi-scale overlapping cell and tissue annotations. The OCELOT 2023 challenge was initiated to gather insights from the community to validate the hypothesis that understanding cell and tissue (cell–tissue) interactions is crucial for achieving human-level performance, and to accelerate the research in this field. The challenge dataset includes overlapping cell detection and tissue segmentation annotations from six organs, comprising 673 pairs sourced from 306 The Cancer Genome Atlas (TCGA) Whole-Slide Images with hematoxylin and eosin staining, divided into training, validation, and test subsets. Participants presented models that significantly enhanced the understanding of cell–tissue relationships. Top entries achieved up to a 7.99 increase in F1-score on the test set compared to the baseline cell-only model that did not incorporate cell–tissue relationships. This is a substantial improvement in performance over traditional cell-only detection methods, demonstrating the need for incorporating multi-scale semantics into the models. This paper provides a comparative analysis of the methods used by participants, highlighting innovative strategies implemented in the OCELOT 2023 challenge.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103751"},"PeriodicalIF":11.8,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144812184","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":"DMP-Net: Deep semantic prior compressed spectral reconstruction method towards intraoperative imaging of brain tissue","authors":"Chipeng Cao ,&nbsp;Jie Li ,&nbsp;Pan Wang ,&nbsp;Chun Qi","doi":"10.1016/j.media.2025.103750","DOIUrl":"10.1016/j.media.2025.103750","url":null,"abstract":"<div><div>In the diagnosis and surgical resection of brain tumors, hyperspectral imaging, as a non-invasive detection technology, can effectively characterize the morphological structure and the physicochemical differences in cellular metabolism of different tissues. However, live tissues typically exhibit certain motion characteristics, and traditional hyperspectral imaging systems struggle to meet the demands for real-time and rapid imaging. The snapshot compressive spectral imaging (CSI) system can quickly acquire spatial spectral information of the lesion area in a single exposure and, combined with reconstruction algorithms, effectively restore the high-dimensional spectral information of brain tissue. High-quality reconstruction results are crucial for ensuring the reliability of spectral analysis of brain tissue. To improve the reconstruction performance of the CSI system, this paper proposes a compressive spectral reconstruction method based on deep semantic prior regularization. The predicted results of the deep convolutional prior model are used as the initial spectral estimate to establish a regularization term for the reconstruction process. This is combined with the Alternating Direction Method of Multipliers (ADMM) to optimize the solution for high-dimensional spectral images of brain tissue. The results show that using the CSI system for intraoperative brain tissue imaging can rapidly acquire spatial spectral information of the lesion area. By optimizing the reconstruction process with the deep convolutional prior model, this method not only better preserves the structural consistency of spectral images from different patients but also fully considers the spectral differences of different types of brain tumors, achieving higher reconstruction quality. This provides strong support for the precise localization and resection of brain tumors. The source code and related data of the proposed method can be downloaded at <span><span>https://github.com/ccp1025/DMP-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103750"},"PeriodicalIF":11.8,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828087","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":"CLIK-Diffusion: Clinical Knowledge-informed Diffusion Model for Tooth Alignment","authors":"Yulong Dou ,&nbsp;Han Wu ,&nbsp;Changjian Li ,&nbsp;Chen Wang ,&nbsp;Tong Yang ,&nbsp;Min Zhu ,&nbsp;Dinggang Shen ,&nbsp;Zhiming Cui","doi":"10.1016/j.media.2025.103746","DOIUrl":"10.1016/j.media.2025.103746","url":null,"abstract":"<div><div>Traditional semi-automatic methods for tooth alignment involve laborious manual procedures and heavily depend on the expertise of dentists, which often leads to inefficient and prolonged treatment durations. Although many automatic methods have been proposed to assist especially the less experienced dentists, they often lack incorporating clinical insight and oversimplify the problem by estimating rigid transformation matrix for each tooth directly from dental point clouds. This over-simplification fails to capture nuanced requirements of orthodontic treatment, i.e., specific clinical rules for effective alignment of misaligned teeth. To address this, we propose CLIK-Diffusion, a <u>CLI</u>nical <u>K</u>nowledge-informed <u>Diffusion</u> model for automatic tooth alignment. CLIK-Diffusion formulates the complex problem of tooth alignment as a more manageable landmark transformation problem, which is further refined into a landmark coordinate generation task. Specifically, we first detect landmarks for each tooth by category, and then build our CLIK-Diffusion to learn distribution of normal occlusion. To further encourage the integration of essential clinical knowledge, we design hierarchical constraints from three perspectives: (1) dental-arch level: to constrain arrangement of teeth from a global level; (2) inter-tooth level: to ensure tight contact and avoid unnecessary collision between neighboring teeth; and (3) individual-tooth level: to guarantee correct orientation of each tooth. In this way, our designed CLIK-Diffusion is able to predict the post-orthodontic landmarks that align with clinical knowledge, and then estimate rigid transformation for each tooth based on coordinates of its pre- and post-orthodontic landmarks. We have evaluated our CLIK-Diffusion on various malocclusion cases collected in real-world clinics, and demonstrate its exceptional performance and strong applicability in orthodontic treatment, compared with other state-of-the-art methods. Our dataset and code is available at <span><span>https://github.com/ShanghaiTech-IMPACT/CLIK-Diffusion</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103746"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144772637","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":"Recurrent inference machine for medical image registration","authors":"Yi Zhang ,&nbsp;Yidong Zhao ,&nbsp;Hui Xue ,&nbsp;Peter Kellman ,&nbsp;Stefan Klein ,&nbsp;Qian Tao","doi":"10.1016/j.media.2025.103748","DOIUrl":"10.1016/j.media.2025.103748","url":null,"abstract":"<div><div>Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advances in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modeling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver for the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input.</div><div>We extensively evaluated RIIR on brain MRI, lung CT, and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only 5% of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103748"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144804418","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":"Contrastive learning and prior knowledge-induced feature extraction network for prediction of high-risk recurrence areas in Gliomas","authors":"Boya Wu ,&nbsp;Jianyun Cao ,&nbsp;Wei Xiong ,&nbsp;Yanchun Lv ,&nbsp;Guohua Zhao ,&nbsp;Xiaoyue Ma ,&nbsp;Ying Zhang ,&nbsp;Jiawei Zhang ,&nbsp;Junguo Bu ,&nbsp;Tao Xie ,&nbsp;Qianjin Feng ,&nbsp;Meiyan Huang","doi":"10.1016/j.media.2025.103740","DOIUrl":"10.1016/j.media.2025.103740","url":null,"abstract":"<div><div>Gliomas can easily recur even after standard treatments, and their recurrence may be related to insufficient radiation doses received by high-risk recurrence areas (HRA). Therefore, HRA prediction can help clinical experts in formulating effective radiotherapy plans. However, research on HRA prediction using early postoperative conventional MRI images with total resection is lacking. This gap is due to multifold challenges, including visually minimal differences between HRA and non-HRA and small dataset size caused by missing follow-up data. A contrastive learning and prior knowledge-induced feature extraction network (CLPKnet) to explore HRA-related features and achieve HRA prediction was proposed in this paper. First, a contrastive and multisequence learning-based encoder was proposed to effectively extract diverse features across multiple MRI sequences around the operative cavity. Specifically, a contrastive learning method was employed to pretrain the encoder, which enabled it to capture subtle differences between HRA and non-HRA regions while mitigating the challenges posed by the limited dataset size. Second, clinical prior knowledge was incorporated into the CLPKnet to guide the model in learning the patterns of glioma growth and improve its discriminative capability for identifying HRA regions. Third, a dual-focus fusion module was utilized to explore important sequential features and spatial regions and effectively fused multisequence features to provide complementary information associated with glioma recurrence. Fourth, to balance clinical needs and task difficulty, we used a patch-based prediction method to predict the recurrent probability. The CLPKnet was validated on a multicenter dataset from four hospitals, and a remarkable performance was achieved. Moreover, the interpretability and robustness of our method were evaluated to illustrate its effectiveness and credibility. Therefore, the CLPKnet displays a great application potential for HRA prediction. The codes will be available at <span><span>https://github.com/Meiyan88/CLPKnet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103740"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780232","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":"Learning from certain regions of interest in medical images via probabilistic positive-unlabeled networks","authors":"Le Yi,&nbsp;Lei Zhang,&nbsp;Kefu Zhao,&nbsp;Xiuyuan Xu","doi":"10.1016/j.media.2025.103745","DOIUrl":"10.1016/j.media.2025.103745","url":null,"abstract":"<div><div>The laborious annotation process and inherent image ambiguity exacerbate difficulties of data acquisition for medical image segmentation, leading to suboptimal performance in practice. This paper proposes a workaround against these challenges aiming to learn unbiased models solely from certainties. Concretely, during the labeling stage, only regions of interest confidently discerned by annotators are required to be labeled, not only increasing label quantity but also improving label quality. This approach formulates the positive-unlabeled (PU) segmentation problem and motivates to capture uncertainty in ambiguous regions. We thus delve into data-generating assumptions in the PU segmentation context and propose Probabilistic PU Segmentation Networks (ProPU-Nets) to tackle problems abovementioned. This framework employs the expectation–maximization algorithm to gradually estimate true masks, and more importantly, by encoding plausible segmentation variants in a latent space, uncertainty estimation can be naturally embedded into the PU segmentation framework. Benefitting from the framework’s unbiasedness, a semi-supervised PU segmentation method is also proposed, which can further excavate performance gains from unlabeled data. We conduct extensive experiments on LIDC, RIGA, and LA datasets, and comprehensively compared with state-of-the-art methods in label-efficient medical image segmentation. The results justify the method’s effectiveness and practical prospect.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103745"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144804416","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":"Interpretable multi-scale deep learning to detect malignancy in cell blocks and cytological smears of pleural effusion and identify aggressive endometrial cancer","authors":"Ching-Wei Wang ,&nbsp;Hikam Muzakky ,&nbsp;Yu-Pang Chung ,&nbsp;Po-Jen Lai ,&nbsp;Tai-Kuang Chao","doi":"10.1016/j.media.2025.103742","DOIUrl":"10.1016/j.media.2025.103742","url":null,"abstract":"<div><div>The pleura is a serous membrane that surrounds the surface of the lungs. The visceral surface secretes fluid into the serous cavity, while the parietal surface ensures that the fluid is properly absorbed. However, when this balance is disrupted, it leads to the formation of pleural Effusion. The most common malignant pleural effusion (MPE) caused by lung cancer or breast cancer, and benign pleural effusions (BPE) caused by Mycobacterium tuberculosis infection, heart failure, or infections related to pneumonia. Today, with the rapid advancement of treatment protocols, accurately diagnosing MPE has become increasingly important. Although cytology smears and cell blocks examinations of pleural effusion are the clinical gold standards for diagnosing MPE, the diagnostic accuracy of these tools can be affected by certain limitations, such as low sensitivity, diagnostic variability across different regions and significant inter-observer variability, leading to a certain proportion of misdiagnoses. This study presents a deep learning (DL) framework, namely Interpretable Multi-scale Attention DL with Self-Supervised Learning Feature Encoder (IMA-SSL), to identifyMPE or BPE using 194 Cytological smears whole-slide images (WSIs) and 188 cell blocks WSIs. The use of DL on WSIs of pleural effusion allows for preliminary results to be obtained in a short time, giving patients the opportunity for earlier diagnosis and treatment. The experimental results show that the proposed IMA-SSL consistently obtained superior performance and outperformed five state-of-the-art (SOTA) methods in malignancy prediction on both cell block and cytological smear datasets and also in identification of aggressive endometrial cancer (EC) using a public TCGA dataset. Fisher’s exact test confirmed a highly significant correlation between the outputs of the proposed model and the slide status in the EC and pleural effusion datasets (<span><math><mi>p &lt; 0.001</mi></math></span>), substantiating the model’s predictive reliability. The proposed method has the potential for practical clinical application in the foreseeable future. It can directly detect the presence of malignant tumor cells from cost-effective cell blocks and pleural effusion cytology smears and facilitate personalized cancer treatment decisions.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103742"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144804415","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":"Self-consistent recursive diffusion bridge for medical image translation","authors":"Fuat Arslan ,&nbsp;Bilal Kabas ,&nbsp;Onat Dalmaz ,&nbsp;Muzaffer Ozbey ,&nbsp;Tolga Çukur","doi":"10.1016/j.media.2025.103747","DOIUrl":"10.1016/j.media.2025.103747","url":null,"abstract":"<div><div>Denoising diffusion models (DDM) have gained recent traction in medical image translation given their high training stability and image fidelity. DDMs learn a multi-step denoising transformation that progressively maps random Gaussian-noise images provided as input onto target-modality images as output, while receiving indirect guidance from source-modality images via a separate static channel. This denoising transformation diverges significantly from the task-relevant source-to-target modality transformation, as source images are governed by a non-noise distribution. In turn, DDMs can suffer from suboptimal source-modality guidance and performance losses in medical image translation. Here, we propose a novel self-consistent recursive diffusion bridge (SelfRDB) that leverages direct source-modality guidance within its diffusion process for improved performance in medical image translation. Unlike DDMs, SelfRDB devises a novel forward process with the start-point taken as the target image, and the end-point defined based on the source image. Intermediate image samples across the process are expressed via a normal distribution whose mean is taken as a convex combination of start-end points, and whose variance is controlled by additive noise. Unlike regular diffusion bridges that prescribe zero noise variance at start-end points and high noise variance at mid-point of the process, we propose a novel noise scheduling with monotonically increasing variance towards the end-point in order to facilitate information transfer between the two modalities and boost robustness against measurement noise. To further enhance sampling accuracy in each reverse step, we propose a novel sampling procedure where the network recursively generates a transient-estimate of the target image until convergence onto a self-consistent solution. Comprehensive experiments in multi-contrast MRI and MRI-CT translation indicate that SelfRDB achieves state-of-the-art results in terms of image quality.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103747"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144780370","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":"MedCLIP-SAMv2: Towards universal text-driven medical image segmentation","authors":"Taha Koleilat ,&nbsp;Hojat Asgariandehkordi ,&nbsp;Hassan Rivaz ,&nbsp;Yiming Xiao","doi":"10.1016/j.media.2025.103749","DOIUrl":"10.1016/j.media.2025.103749","url":null,"abstract":"<div><div>Segmentation of anatomical structures and pathologies in medical images is essential for modern disease diagnosis, clinical research, and treatment planning. While significant advancements have been made in deep learning-based segmentation techniques, many of these methods still suffer from limitations in data efficiency, generalizability, and interactivity. As a result, developing robust segmentation methods that require fewer labeled datasets remains a critical challenge in medical image analysis. Recently, the introduction of foundation models like CLIP and Segment-Anything-Model (SAM), with robust cross-domain representations, has paved the way for interactive and universal image segmentation. However, further exploration of these models for data-efficient segmentation in medical imaging is an active field of research. In this paper, we introduce MedCLIP-SAMv2, a novel framework that integrates the CLIP and SAM models to perform segmentation on clinical scans using text prompts, in both zero-shot and weakly supervised settings. Our approach includes fine-tuning the BiomedCLIP model with a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss, and leveraging the Multi-modal Information Bottleneck (M2IB) to create visual prompts for generating segmentation masks with SAM in the zero-shot setting. We also investigate using zero-shot segmentation labels in a weakly supervised paradigm to enhance segmentation quality further. Extensive validation across four diverse segmentation tasks and medical imaging modalities (breast tumor ultrasound, brain tumor MRI, lung X-ray, and lung CT) demonstrates the high accuracy of our proposed framework. Our code is available at <span><span>https://github.com/HealthX-Lab/MedCLIP-SAMv2</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"107 ","pages":"Article 103749"},"PeriodicalIF":11.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144804417","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}