Medical Imaging Foundation Models

Ask about this topic

Overview

Medical imaging foundation models aim to learn reusable features from large collections of images, scans, and sometimes paired clinical reports, then apply them to tasks such as diagnosis, segmentation, measurement, and report generation. Common approaches include self-supervised learning, masked-image prediction, vision-language contrastive learning, and generative models, with both 2D and volumetric methods for modalities such as radiology, MRI, ultrasound, pathology, and retinal imaging. Researchers adapt these models through fine-tuning, lightweight adapters such as LoRA, frozen-feature probes, or prompts, and assess them on classification, segmentation, and cross-center benchmarks. A central tension is whether broad pretraining reliably helps specific clinical tasks: results vary by modality and task, and robustness to shifts in scanners, populations, and institutions remains essential to establish before deployment.

Latest papers

CardsList

235 papers21 papers in the last four weeks, down 28% on the four weeks before. 0.1% of all new papers.

Apr 13, 2026

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obtain. Self-supervised learning (SSL) can address this by leveraging the vast amounts of unlabeled data produced in clinical workflows to train robust foundation models that adapt out-of-domain with minimal supervision. However, the development of foundation models for brain MRI has been limited by small pretraining datasets and in-domain benchmarking focused on high-quality, research-grade data. To address this gap, we organized the FOMO25 challenge as a satellite event at MICCAI 2025. FOMO25 provided participants with a large pretraining dataset, FOMO60K, and evaluated models on data sourced directly from clinical workflows in few-shot and out-of-domain settings. Tasks covered infarct classification, meningioma segmentation, and brain age regression, and considered both models trained on FOMO60K (method track) and any data (open track). Nineteen foundation models from sixteen teams were evaluated using a standardized containerized pipeline. Results show that (a) self-supervised pretraining improves generalization on clinical data under domain shift, with the strongest models trained out-of-domain surpassing supervised baselines trained in-domain. (b) No single pretraining objective benefits all tasks: MAE favors segmentation, hybrid reconstruction-contrastive objectives favor classification, and (c) strong performance was achieved by small pretrained models, and improvements from scaling model size and training duration did not yield reliable benefits.

Asbjørn Munk, Stefano Cerri, Vardan Nersesjan +81

Medical Imaging Foundation ModelsSelf-Supervised Pre-TrainingDomain GeneralizationMedical Image BenchmarksFew-Shot Medical Image Segmentation
AskPDF
Apr 10, 2026

RobustMedSAM: Degradation-Resilient Medical Image Segmentation via Robust Foundation Model Adaptation

Medical image segmentation models built on Segment Anything Model (SAM) achieve strong performance on clean benchmarks, yet their reliability often degrades under realistic image corruptions such as noise, blur, motion artifacts, and modality-specific distortions. Existing approaches address either medical-domain adaptation or corruption robustness, but not both jointly. In SAM, we find that these capabilities are concentrated in complementary modules: the image encoder preserves medical priors, while the mask decoder governs corruption robustness. Motivated by this observation, we propose RobustMedSAM, which adopts module-wise checkpoint fusion by initializing the image encoder from MedSAM and the mask decoder from RobustSAM under a shared ViT-B architecture. We then fine-tune only the mask decoder on 35 medical datasets from MedSegBench, spanning six imaging modalities and 12 corruption types, while freezing the remaining components to preserve pretrained medical representations. We additionally investigate an SVD-based parameter-efficient variant for limited encoder adaptation. Experiments on both in-distribution and out-of-distribution benchmarks show that RobustMedSAM improves degraded-image Dice from 0.613 to 0.719 (+0.106) over SAM, demonstrating that structured fusion of complementary pretrained models is an effective and practical approach for robust medical image segmentation.

Jieru Li, Matthew Chen, Micky C. Nnamdi +3

Georgia Institute of Technology

Medical Image SegmentationMedical Imaging Foundation ModelsImage Corruption Robustness
AskPDF
Apr 10, 2026

M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model

Medical foundation models (MFMs) aim to learn universal representations from multimodal medical images that can generalize effectively to diverse downstream clinical tasks. However, most existing MFMs suffer from information ambiguity that blends multimodal representations in a single embedding space, leading to the degradation of modality specificity and diversity. In this paper, we propose M-IDoL, a self-supervised MFM that introduces Information Decomposition for multimodal representation Learning via two objectives: i) maximizing inter-modality entropy by dispersing multimodal representations into separable Mixture-of-Experts (MoE) subspaces to achieve representation specificity across modalities; and ii) minimizing intra-modality uncertainty by performing fine-grained semantic discrimination within each MoE subspace to enrich representation diversity per modality. By pre-training on 1.15 million medical images, M-IDoL i) delivers superior generalization across 21 downstream clinical tasks, outperforming 20 foundation models on five imaging modalities (e.g., X-ray, fundus, OCT, dermoscopy and pathology), and ii) learns modality-specific and diverse representations, showing clearer separation of feature clusters across modalities and finer-grained feature discrimination within each modality.

Yihang Liu, Longzhen Yang, Jiaxiong Yang +3

School of Computer Science and Technique, Tongji University, Shanghai 201804, China. · School of Communications and Electronic Engineering, East China Normal University, Shanghai 200241, China.

Medical Imaging Foundation ModelsMedical Image Representation LearningMultimodal PretrainingMultimodal Disentangled Representation Learning
AskPDF
Apr 9, 2026

Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images

Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variability. While automated segmentation is a foundational step for quantitative risk assessment, traditional fully supervised convolutional architectures frequently require large amounts of pixel-level annotations and struggle with domain shifts common in medical imaging. In this work, we propose a label-efficient segmentation framework that leverages the robust semantic priors of a pretrained DINOv3 foundational vision transformer backbone. By integrating this backbone with a Dense Prediction Transformer (DPT)-style decoder, our model hierarchically reassembles multi-scale features to combine global semantic representations with fine-grained spatial details. Evaluated on a clinical dataset of 7,777 annotated frames from 112 patients, our method achieves state-of-the-art performance compared to established fully supervised baselines, including U-Net, U-Net++, DeepLabV3, and MAnet. Specifically, we obtain a Dice score of 0.945 and improved boundary adherence, reducing the 95th-percentile Hausdorff Distance by 11.4% relative to the strongest convolutional baseline. Furthermore, we conduct an extensive efficiency analysis demonstrating that our DINOv3-based approach retains significantly higher performance under data starvation regimes, maintaining strong results even when trained on only 25% of the data. These results suggest that leveraging large-scale self-supervised foundations provides a promising and data-efficient solution for medical image segmentation in data-constrained clinical environments. Project Repository: https://github.com/FrancescaFati/MESA

Francesca Fati, Alberto Rota, Adriana V. Gregory +9

Mayo Clinic · Politecnico di Milano · Istituto Europeo di Oncologia

Medical Image SegmentationUltrasound Image SegmentationSemantic SegmentationMedical Imaging Foundation Models
AskPDF
Apr 9, 2026

Weight Group-wise Post-Training Quantization for Medical Foundation Model

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on terminal medical devices. Quantization, a technique that compresses models into low-bit versions, is a solution to this challenge. In this paper, we propose a post-training quantization algorithm, Permutation-COMQ. It eliminates the need for backpropagation by using simple dot products and rounding operations, thereby removing hyperparameter tuning and simplifying the process. Additionally, we introduce a weight-aware strategy that reorders the weight within each layer to address the accuracy degradation induced by channel-wise scaling during quantization, while preserving channel structure. Experiments demonstrate that our method achieves the best results in 2-bit, 4-bit, and 8-bit quantization.

Yineng Chen, Peng Huang, Aozhong Zhang +9

University at Albany, SUNY · Southwest Jiaotong University · Purdue University +1

Post-Training QuantizationLow-Bit QuantizationNeural Network QuantizationWeight-Only QuantizationMedical Imaging Foundation Models
AskPDF
Apr 7, 2026

Analogical Reasoning as a Doctor: A Foundation Model for Gastrointestinal Endoscopy Diagnosis

Gastrointestinal diseases impose a growing global health burden, and endoscopy is a primary tool for early diagnosis. However, routine endoscopic image interpretation still suffers from missed lesions and limited efficiency. Although AI-assisted diagnosis has shown promise, existing models often lack generalizability, adaptability, robustness, and scalability because of limited medical data, domain shift, and heterogeneous annotations. To address these challenges, we develop RATNet, a foundation model for gastrointestinal endoscopy imaging based on analogical reasoning. RATNet acquires and transfers knowledge from heterogeneous expert annotations across five gastrointestinal endoscopy datasets through a cyclic pre-training strategy. Its architecture consists of an encoder, a relevance-knowledge acquisition and transfer (RAT) module, a projector, and a multi-task head, and supports fine-tuning, linear probing, and zero-shot transfer. Evaluations show that RATNet outperforms existing foundation models, including GastroNet and GastroVision, across six scenarios: diagnosis of common gastrointestinal diseases, few-shot learning for rare diseases, zero-shot transfer to new medical sites, robustness under long-tailed disease distributions, adaptation to novel diseases, and privacy-preserving deployment via federated learning. Its advantage comes from an analogical reasoning mechanism that matches image-derived posterior knowledge to a learned prior knowledge base and transfers relative knowledge to guide diagnosis, improving generalization and resistance to bias. RATNet is open and cost-effective, supports automatic integration of heterogeneous annotations without manual label unification, and reduces data acquisition costs, making it a practical foundation for intelligent gastrointestinal diagnosis, especially in resource-limited settings.

Peixi Peng, Housheng Xie, Yanling Wei +5

Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University · Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China. · Daping Hospital, Army Medical University +3

Medical Imaging Foundation ModelsMedical DiagnosisEndoscopyMedical Image ClassificationCross-Domain Transfer LearningAnalogical Reasoning
AskPDF
Apr 6, 2026

MedGemma 1.5 Technical Report

We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/medgemma.

Andrew Sellergren, Chufan Gao, Fereshteh Mahvar +39

Medical Imaging Foundation Models3D Medical ImagingMedical Image LocalizationHistopathology Image ClassificationLongitudinal Medical Image Analysis
AskPDF
Apr 5, 2026

Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks

There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on building generalist vision-language systems capable of tasks such as question answering and report generation. However, training reliable vision-language systems requires paired image-text data at a scale that remains unavailable in CT. Moreover, adapting the underlying visual representations to downstream tasks typically requires partial or full backbone fine-tuning, a computationally demanding process inaccessible to many research groups. Instead, foundation models should prioritise learning robust visual representations that enable efficient transfer to new tasks with minimal labelled data and without backbone fine-tuning. We present VoxelFM, a 3D CT foundation model trained with self-distillation using the DINO framework, which learns semantically rich features without language supervision. We evaluated VoxelFM across seven categories of clinically relevant downstream tasks using frozen backbone representations with lightweight probes: classification, regression, survival analysis, instance retrieval, localisation, segmentation, and report generation. VoxelFM matched or outperformed four existing CT foundation models across all task categories. Despite receiving no language supervision during pre-training, VoxelFM surpassed models explicitly trained with language-alignment objectives, including on report generation. Our results indicate that current CT foundation models perform significantly better as feature extractors for lightweight probes rather than as vision encoders for vision-language models. Model weights and training code are publicly available.

Rubén Moreno-Aguado, Alba Magallón, Victor Moreno +2

Bioengineering Department and Imperial-X, Imperial College London, London, UK · Department of Computer Science, University of Manchester, Manchester, UK · Oncology Data Analytics Program, Catalan Institute of Oncology, Barcelona, Spain +6

Medical Imaging Foundation ModelsMedical Image Representation LearningComputed TomographySelf-Supervised Visual Representation Learning
AskPDF
Apr 2, 2026

Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

The rapid growth of medical imaging has fueled the development of Foundation Models (FMs) to reduce the growing, unsustainable workload on radiologists. While recent FMs have shown the power of large-scale pre-training to CT and MRI analysis, there remains significant room to optimize how these models learn from complex radiological volumes. Building upon the Curia framework, this work introduces Curia-2, which significantly improves the original pre-training strategy and representation quality to better capture the specificities of radiological data. The proposed methodology enables scaling the architecture up to billion-parameter Vision Transformers, marking a first for multi-modal CT and MRI FMs. Furthermore, we formalize the evaluation of these models by extending and restructuring CuriaBench into two distinct tracks: a 2D track tailored for slice-based vision models and a 3D track for volumetric benchmarking. Our results demonstrate that Curia-2 outperforms all FMs on vision-focused tasks and fairs competitively to vision-language models on clinically complex tasks such as finding detection. Weights will be made publicly available to foster further research.

Antoine Saporta, Baptiste Callard, Corentin Dancette +5

Raidium, 27 rue du Faubourg Saint-Jacques, 75014 Paris, France. · Department of Vascular and Oncological Interventional Radiology, Hôpital Européen Georges Pompidou, AP-HP, Paris, France · Faculté de Santé, Université Paris-Cité, Paris, France.

Medical Imaging Foundation ModelsMedical ImagingMedical Image Representation LearningMedical Image Benchmarks
AskPDF
Apr 1, 2026

AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation

Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundation models in clinical settings remains challenging due to computational constraints. We propose AdaLoRA-QAT, a two-stage fine-tuning framework that combines adaptive low-rank encoder adaptation with full quantization-aware training. Adaptive rank allocation improves parameter efficiency, while selective mixed-precision INT8 quantization preserves structural fidelity crucial for clinical reliability. Evaluated across large-scale CXR datasets, AdaLoRA-QAT achieves 95.6% Dice, matching full-precision SAM decoder fine-tuning while reducing trainable parameters by 16.6\times and yielding 2.24\times model compression. A Wilcoxon signed-rank test confirms that quantization does not significantly degrade segmentation accuracy. These results demonstrate that AdaLoRA-QAT effectively balances accuracy, efficiency, and structural trust-worthiness, enabling compact and deployable foundation models for medical image segmentation. Code and pretrained models are available at: https://prantik-pdeb.github.io/adaloraqat.github.io/

Prantik Deb, Srimanth Dhondy, N. Ramakrishna +3

International Institute of Information Technology (IIIT-H), Hyderabad, India · Nizam’s Institute of Medical Sciences (NIMS), Hyderabad, India · The Alan Turing Institute, London and University College London, United Kingdom

Medical Image SegmentationMedical Imaging Foundation ModelsQuantization-Aware LoRAQuantization-Aware TrainingMixed-Precision Quantization
AskPDF
Mar 31, 2026

Segmentation of Gray Matters and White Matters from Brain MRI data

Accurate segmentation of brain tissues such as gray matter and white matter from magnetic resonance imaging is essential for studying brain anatomy, diagnosing neurological disorders, and monitoring disease progression. Traditional methods, such as FSL FAST, produce tissue probability maps but often require task-specific adjustments and face challenges with diverse imaging conditions. Recent foundation models, such as MedSAM, offer a prompt-based approach that leverages large-scale pretraining. In this paper, we propose a modified MedSAM model designed for multi-class brain tissue segmentation. Our preprocessing pipeline includes skull stripping with FSL BET, tissue probability mapping with FSL FAST, and converting these into 2D axial, sagittal, coronal slices with multi-class labels (background, gray matter, and white matter). We extend MedSAM's mask decoder to three classes, freezing the pre-trained image encoder and fine-tuning the prompt encoder and decoder. Experiments on the IXI dataset achieve Dice scores up to 0.8751. This work demonstrates that foundation models like MedSAM can be adapted for multi-class medical image segmentation with minimal architectural modifications. Our findings suggest that such models can be extended to more diverse medical imaging scenarios in future work.

Chang Sun, Rui Shi, Tsukasa Koike +3

Department of Computer Science and Engineering, Waseda University, Shinjuku, Tokyo, Japan · Department of Neurosurgery, Teraoka Memorial Hospital, Fukuyama, Hiroshima, Japan · Department of Radiology, Nippon Medical School Hospital, Tokyo, Japan +1

Medical Image SegmentationMedical Imaging Foundation ModelsPromptable Image Segmentation
AskPDF
Mar 30, 2026

DinoDental: Benchmarking DINOv3 as a Unified Vision Encoder for Dental Image Analysis

The scarcity and high cost of expert annotations in dental imaging present a significant challenge for the development of AI in dentistry. DINOv3, a state-of-the-art, self-supervised vision foundation model pre-trained on 1.7 billion images, offers a promising pathway to mitigate this issue. However, its reliability when transferred to the dental domain, with its unique imaging characteristics and clinical subtleties, remains unclear. To address this, we introduce DinoDental, a unified benchmark designed to systematically evaluate whether DINOv3 can serve as a reliable, off-the-shelf encoder for comprehensive dental image analysis without requiring domain-specific pre-training. Constructed from multiple public datasets, DinoDental covers a wide range of tasks, including classification, detection, and instance segmentation on both panoramic radiographs and intraoral photographs. We further analyze the model's transfer performance by scaling its size and input resolution, and by comparing different adaptation strategies, including frozen features, full fine-tuning, and the parameter-efficient Low-Rank Adaptation (LoRA) method. Our experiments show that DINOv3 can serve as a strong unified encoder for dental image analysis across both panoramic radiographs and intraoral photographs, remaining competitive across tasks while showing particularly clear advantages for intraoral image understanding and boundary-sensitive dense prediction. Collectively, DinoDental provides a systematic framework for comprehensively evaluating DINOv3 in dental analysis, establishing a foundational benchmark to guide efficient and effective model selection and adaptation for the dental AI community.

Kun Tang, Xinquan Yang, Mianjie Zheng +6

Shenzhen University. · Shenzhen University General Hospital. · Chongqing University.

Medical Image AnalysisVision Foundation Model AdaptationDental ImagingMedical Imaging Foundation ModelsMedical Image BenchmarksMedical Image Classification
AskPDF
Mar 29, 2026

RAP: Retrieve, Adapt, and Prompt-Fit for Training-Free Few-Shot Medical Image Segmentation

Few-shot medical image segmentation (FSMIS) has achieved notable progress, yet most existing methods mainly rely on semantic correspondences from scarce annotations while under-utilizing a key property of medical imagery: anatomical targets exhibit repeatable high-frequency morphology (e.g., boundary geometry and spatial layout) across patients and acquisitions. We propose RAP, a training-free framework that retrieves, adapts, and prompts Segment Anything Model 2 (SAM2) for FSMIS. First, RAP retrieves morphologically compatible supports from an archive using DINOv3 features to reduce brittleness in single-support choice. Second, it adapts the retrieved support mask to the query by fitting boundary-aware structural cues, yielding an anatomy-consistent pre-mask under domain shifts. Third, RAP converts the pre-mask into prompts by sampling positive points via Voronoi partitioning and negative points via sector-based sampling, and feeds them into SAM2 for final refinement without any fine-tuning. Extensive experiments on multiple medical segmentation benchmarks show that RAP consistently surpasses prior FSMIS baselines and achieves state-of-the-art performance. Overall, RAP demonstrates that explicit structural fitting combined with retrieval-augmented prompting offers a simple and effective route to robust training-free few-shot medical segmentation.

Zhihao Mao, Bangpu Chen

School of Computer Science, China University of Geosciences, Wuhan, China

Medical Image SegmentationFew-Shot Medical Image SegmentationPromptable Image SegmentationMedical Imaging Foundation Models
AskPDF
Mar 29, 2026

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Zhongying Deng, Cheng Tang, Ziyan Huang +124

Medical ImagingMedical Imaging Foundation Models
AskPDF
Mar 26, 2026

Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study

Accurate lesion segmentation is essential in medical image analysis, yet most existing methods are designed for specific anatomical sites or imaging modalities, limiting their generalizability. Recent vision-language foundation models enable concept-driven segmentation in natural images, offering a promising direction for more flexible medical image analysis. However, concept-prompt-based lesion segmentation, particularly with the latest Segment Anything Model 3 (SAM3), remains underexplored. In this work, we present a systematic evaluation of SAM3 for lesion segmentation. We assess its performance using geometric bounding boxes and concept-based text and image prompts across multiple modalities, including multiparametric MRI, CT, ultrasound, dermoscopy, and endoscopy. To improve robustness, we incorporate additional prior knowledge, such as adjacent-slice predictions, multiparametric information, and prior annotations. We further compare different fine-tuning strategies, including partial module tuning, adapter-based methods, and full-model optimization. Experiments on 13 datasets covering 11 lesion types demonstrate that SAM3 achieves strong cross-modality generalization, reliable concept-driven segmentation, and accurate lesion delineation. These results highlight the potential of concept-based foundation models for scalable and practical medical image segmentation. Code and trained models will be released at: https://github.com/apple1986/lesion-sam3

Guoping Xu, Jayaram K. Udupa, Yubing Tong +5

The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA · Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA · Division of Digestive and Liver Diseases, Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA

Medical Image SegmentationPromptable Image SegmentationCross-Modality Medical Image SegmentationText-Guided Image SegmentationMedical Imaging Foundation Models
AskPDF
Mar 24, 2026

Sparse Autoencoders for Interpretable Medical Image Representation Learning

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to investigate Sparse Autoencoders (SAEs) for replacing opaque FM image representations with human-interpretable, sparse features. We train SAEs on embeddings from BiomedParse (biomedical) and DINOv3 (general-purpose) using 909,873 CT and MRI 2D image slices from the TotalSegmentator dataset. We find that learned sparse features: (a) reconstruct original embeddings with high fidelity (R2 up to 0.941) and recover up to 87.8% of downstream performance using only 10 features (99.4% dimensionality reduction), (b) preserve semantic fidelity in image retrieval tasks, (c) correspond to specific concepts that can be expressed in language using large language model (LLM)-based auto-interpretation. (d) bridge clinical language and abstract latent representations in zero-shot language-driven image retrieval. Our work indicates SAEs are a promising pathway towards interpretable, concept-driven medical vision systems. Code repository: https://github.com/pwesp/sail.

Philipp Wesp, Robbie Holland, Vasiliki Sideri-Lampretsa +1

Stanford Center for Artificial Intelligence in Medicine and Imaging, Stanford University, Stanford, CA, USA · Department of Radiology, Stanford University, Stanford, CA, USA · Chair of AI in Healthcare and Medicine, Technical University of Munich, Munich, Germany +1

Medical Image RetrievalExplainable Medical Image AnalysisMedical Image Representation LearningSparse AutoencodersMedical Imaging Foundation Models
AskPDF
Mar 24, 2026

Bi-CRCL: Bidirectional Conservative-Radical Complementary Learning with Pre-trained Foundation Models for Class-incremental Medical Image Analysis

Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is particularly challenging due to heterogeneous data and privacy constraints that prevent memory replay. Although pretrained foundation models (PFMs) have advanced general-domain CIL, their potential in medical imaging remains underexplored, where domain-specific adaptation is essential yet difficult due to anatomical complexity and inter-institutional heterogeneity. To address this gap, we conduct a systematic benchmark of recent PFM-based CIL methods and propose Bidirectional Conservative-Radical Complementary Learning (Bi-CRCL), a dual-learner framework inspired by complementary learning systems. Bi-CRCL integrates a conservative learner that preserves prior knowledge through stability-oriented updates and a radical learner that rapidly adapts to new categories via plasticity-oriented learning. A bidirectional interaction mechanism enables forward transfer and backward consolidation, allowing continual integration of new knowledge while mitigating catastrophic forgetting. During inference, outputs from both learners are adaptively fused for robust predictions. Experiments on five medical imaging datasets demonstrate consistent improvements over state-of-the-art methods under diverse settings, including cross-dataset shifts and varying task configurations.

Xinyao Wu, Zhe Xu, Cheng Chen +3

Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China. · Department of Radiation Oncology, Columbia University Irving Medical Center and Data Science Institute, Columbia University, New York, NY, USA. · Department of Electrical and Electronic Engineering and School of Biomedical Engineering, The University of Hong Kong, Hong Kong, China. +2

Class-Incremental LearningMedical Image AnalysisMedical Image ClassificationCatastrophic ForgettingMedical Imaging Foundation Models
AskPDF
Mar 24, 2026

Automatic Segmentation of 3D CT scans with SAM2 using a zero-shot approach

Foundation models for image segmentation have shown strong generalization in natural images, yet their applicability to 3D medical imaging remains limited. In this work, we study the zero-shot use of Segment Anything Model 2 (SAM2) for automatic segmentation of volumetric CT data, without any fine-tuning or domain-specific training. We analyze how SAM2 should be applied to CT volumes and identify its main limitation: the lack of inherent volumetric awareness. To address this, we propose a set of inference-alone architectural and procedural modifications that adapt SAM2's video-based memory mechanism to 3D data by treating CT slices as ordered sequences. We conduct a systematic ablation study on a subset of 500 CT scans from the TotalSegmentator dataset to evaluate prompt strategies, memory propagation schemes and multi-pass refinement. Based on these findings, we select the best-performing configuration and report final results on a bigger sample of the TotalSegmentator dataset comprising 2,500 CT scans. Our results show that, even with frozen weights, SAM2 can produce coherent 3D segmentations when its inference pipeline is carefully structured, demonstrating the feasibility of a fully zero-shot approach for volumetric medical image segmentation.

Miquel Lopez Escoriza, Pau Amargant Alvarez

Department of Computer Science, EPFL, Switzerland

3D Medical Image SegmentationZero-Shot Medical Image SegmentationSemantic SegmentationMedical Imaging Foundation ModelsPromptable Image Segmentation
AskPDF
Mar 19, 2026

Towards Interpretable Foundation Models for Retinal Fundus Images

Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, a critical issue in high-stakes domains such as medical imaging. We propose DualIFM, a foundation model that is interpretable-by-design via a BagNet backbone whose small receptive fields generate class evidence maps that are faithful to the model's decision-making process. Additionally, DualIFM incorporates a 2D2D projection layer during pretraining that enables direct visualization of the representation space, providing a dataset-level view of the learned structure including meaningful clinical clusters as well as potential spurious correlations. We trained DualIFM on over 800,000 color fundus photographs from various sources to learn generalizable representations for different downstream tasks. Our model achieves performance comparable to RETFound, which has 16×16\times more parameters, while providing interpretable predictions on out-of-distribution data. These results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging. Code and pretrained models are available at github.com/berenslab/interpretable_FM.

Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi +1

Hertie Institute for AI in Brain Health, University of Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany

Fundus ImagingMedical Imaging Foundation ModelsSelf-Supervised Visual Representation LearningMedical ImagingExplainable Medical Image AnalysisMedical Image Representation Learning+1
AskPDF
Mar 18, 2026

Understanding Task Aggregation for Generalizable Ultrasound Foundation Models

Foundation models promise to unify multiple clinical tasks within a single framework, but recent ultrasound studies report that unified models can underperform task-specific baselines. We hypothesize that this degradation arises not from model capacity limitations, but from task aggregation strategies that ignore interactions between task heterogeneity and available training data scale. In this work, we systematically analyze when heterogeneous ultrasound tasks can be jointly learned without performance loss, establishing practical criteria for task aggregation in unified clinical imaging models. We introduce M2DINO, a multi-organ, multi-task framework built on DINOv3 with task-conditioned Mixture-of-Experts blocks for adaptive capacity allocation. We systematically evaluate 27 ultrasound tasks spanning segmentation, classification, detection, and regression under three paradigms: task-specific, clinically-grouped, and all-task unified training. Our results show that aggregation effectiveness depends strongly on training data scale. While clinically-grouped training can improve performance in data-rich settings, it may induce substantial negative transfer in low-data settings. In contrast, all-task unified training exhibits more consistent performance across clinical groups. We further observe that task sensitivity varies by task type in our experiments: segmentation shows the largest performance drops compared with regression and classification. These findings provide practical guidance for ultrasound foundation models, emphasizing that aggregation strategies should jointly consider training data availability and task characteristics rather than relying on clinical taxonomy alone.

Fangyijie Wang, Tanya Akumu, Vien Ngoc Dang +5

Research Ireland Centre for Research Training in Machine Learning · School of Medicine, University College Dublin, Dublin, Ireland · Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain +4

Medical Imaging Foundation ModelsMulti-Task Learning
AskPDF
Mar 18, 2026

DeepCORO-CLIP: A Multi-View Foundation Model for Comprehensive Coronary Angiography Video-Text Analysis and External Validation

Coronary angiography is the reference standard for evaluating coronary artery disease, yet visual interpretation remains variable between readers. Existing artificial intelligence methods typically analyze single frames or projections and focus mainly on stenosis, limiting comprehensive coronary assessment. We present DeepCORO-CLIP, a multi-view foundation model trained with video-text contrastive learning on 203,808 angiography videos from 28,117 patients across 32,473 studies at the Montreal Heart Institute and externally validated on 4,249 studies from the University of California, San Francisco. DeepCORO-CLIP integrates multiple projections with attention-based pooling for study-level assessment across diagnostic, prognostic, and disease progression tasks. For significant stenosis detection, the model achieved an AUROC of 0.888 internally and 0.89 on external validation. Mean absolute error against core laboratory quantitative coronary angiography was 13.6%, lower than clinical reports at 19.0%. The model also performed strongly for chronic total occlusion, intracoronary thrombus, and coronary calcification detection. Transfer learning enabled prediction of one-year major adverse cardiovascular events with AUROC 0.79 and estimation of left ventricular ejection fraction with mean absolute error 7.3%. Embeddings also captured disease progression across serial examinations. With a mean inference time of 4.2 seconds in hospital deployment, DeepCORO-CLIP provides a foundation for automated coronary angiography interpretation at the point of care. Code, sample data, model weights, and deployment infrastructure are publicly released.

Sarra Harrabi, Yichen Wu, Geoffrey H. Tison +6

Division of Cardiology, Department of Medicine, Montreal Heart Institute, 5000 Belanger Street, QC, H1T 1C8 Canada · HeartWise.ai, 5000 Belanger Street, QC, H1T 1C8 Canada · McGill, Faculty of Engineering, Montreal, Quebec, Canada. +7

Coronary AngiographyMedical Imaging Foundation ModelsMedical ImagingMedical VLMs
AskPDF
Mar 18, 2026

LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation

Precise localization and delineation of brain tumors using magnetic resonance imaging (MRI) are essential for planning therapy and guiding surgical decisions. To address this, we propose LoGSAM, a parameter-efficient, detection-driven framework that transforms radiologist dictation into text prompts for foundation-model-based localization and segmentation. Radiologist speech is first transcribed and translated using a pretrained Whisper ASR model, followed by negation-aware clinical NLP to extract tumor-specific textual prompts. These prompts guide text-conditioned tumor localization via a LoRA-adapted vision-language detection model, Grounding DINO (GDINO). The predicted bounding boxes are used as prompts for MedSAM to generate pixel-level tumor masks without any additional fine-tuning. On BRISC 2025, LoGSAM attains a Dice score of 80.32%, reaching 98.6% of a fully fine-tuned GDINO + MedSAM baseline while training fewer than 5% of its parameters, indicating a favorable accuracy/parameter trade-off. In addition, we evaluate the full pipeline using German dictations from a board-certified radiologist on unseen MRI scans, achieving 91.7% case-level class-extraction accuracy. These results highlight the feasibility of constructing a modular speech-to-segmentation pipeline from pretrained foundation models with minimal parameter updates.

Mohammad Robaitul Islam Bhuiyan, Sheethal Bhat, Melika Qahqaie +4

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Siemens Healthineers, Erlangen, Germany

Image SegmentationMedical Imaging Foundation ModelsText-Guided Image SegmentationMedical Image SegmentationMedical Image GroundingBrain Tumor Segmentation
AskPDF
Mar 15, 2026

Adaptation of Foundation Models in Medical Image Analysis: Mechanisms, Evidence, and Deployment Considerations

Foundation models, pretrained on diverse data, objectives, or modalities for reuse across downstream tasks, are increasingly applied to medical image analysis. Their performance depends not only on pretraining but also on how they are adapted to specific tasks, data regimes, and deployment settings. Whereas previous reviews have considered adaptation within broader syntheses, this review focuses specifically on post-pretraining interventions applied to existing FMs. Using a structured narrative review with a systematic, auditable workflow, we identified 719 eligible reports representing 705 independent studies. Of these, 473 provided controlled comparative evidence: 322 formally published studies formed the primary synthesis and 151 preprint-only studies a sensitivity layer. Adaptation was organized into five non-mutually exclusive families: parameter-level, representation-level, objective-level, data-centric, and architectural/sequence-level adaptation, with model use and update regime analyzed separately. Controlled comparisons showed no consistent ranking among frozen, parameter-efficient, partial, or full updating, or across broader adaptation families; outcomes varied by task, data regime, comparator, and evaluation setting. Clinical-readiness evidence remained limited: 173/705 studies (24.5%) had confirmed independent external validation, 10 (1.4%) reported calibration or uncertainty evidence, and 97/322 formally published comparative studies (30.1%) included a qualifying externally validated arm. Overall, FM adaptation is a context-dependent design space rather than a hierarchy of preferred strategies.

Karma Phuntsho, Abdullah, Kyungmi Lee +2

James Cook University, 14-88 McGregor Rd, Smithfield, 4878, Queensland, Australia

Medical Imaging Foundation ModelsVision Foundation Model Adaptation
AskPDF
Mar 14, 2026

Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision

Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approaches. Existing self-supervised methods rely on low-level reconstruction or contrastive objectives that fail to capture the anatomical semantics critical for medical image analysis, limiting transfer to downstream tasks. We present MASS (MAsk-guided Self-Supervised learning), which treats in-context segmentation as the pretext task for learning general-purpose medical imaging representations. MASS's key insight is that automatically generated class-agnostic masks provide sufficient structural supervision for learning semantically rich representations. By training on thousands of diverse mask proposals spanning anatomical structures and pathological findings, MASS learns what semantically defines medical structures: the holistic combination of appearance, shape, spatial context, and anatomical relationships. We demonstrate effectiveness across data regimes: from small-scale pretraining on individual datasets (20-200 scans) to large-scale multi-modal pretraining on 5K CT, MRI, and PET volumes, all without annotations. MASS demonstrates: (i) few-shot segmentation on novel structures, (ii) matching full supervision with only 20-40% labeled data while outperforming self-supervised baselines by over 20 in Dice score in low-data regimes, and (iii) frozen-encoder classification on unseen pathologies that matches full supervised training with thousands of samples. Mask-guided self-supervised pretraining captures broadly generalizable knowledge, opening a path toward 3D medical imaging foundation models without expert annotations. Code is available: https://github.com/Stanford-AIMI/MASS.

Yunhe Gao, Yabin Zhang, Chong Wang +5

Stanford University

Medical Image Representation LearningSelf-Supervised Pre-Training3D Medical ImagingMedical Imaging Foundation ModelsFew-Shot Medical Image Segmentation
AskPDF
Mar 13, 2026

SAIF: A Stability-Aware Inference Framework for Medical Image Segmentation with Segment Anything Model

Segment Anything Model (SAM) enable scalable medical image segmentation but suffer from inference-time instability when deployed as a frozen backbone. In practice, bounding-box prompts often contain localization errors, and fixed threshold binarization introduces additional decision uncertainty. These factors jointly cause high prediction variance, especially near object boundaries, degrading reliability. We propose the Stability-Aware Inference Framework (SAIF), a training-free and plug-and-play inference framework that improves robustness by explicitly modeling prompt and threshold uncertainty. SAIF constructs a joint uncertainty space via structured box perturbations and threshold variations, evaluates each hypothesis using decision stability and boundary consistency, and introduces a stability-consistency score to filter unstable candidates and perform stability-weighted fusion in probability space. Experiments on Synapse, CVC-ClinicDB, Kvasir-SEG, and CVC-300 demonstrate that SAIF consistently improves segmentation accuracy and robustness, achieving state-of-the-art performance without retraining or architectural modification. Our anonymous code is released at https://anonymous.4open.science/r/SAIF.

Ke Wu, Shiqi Chen, Yiheng Zhong +5

Xi’an Jiaotong-Liverpool University, Suzhou, China · University College London, London, United Kingdom · Anhui Jianzhu University, Hefei, China

Medical Image SegmentationPromptable Image SegmentationSegmentation Uncertainty EstimationMedical Imaging Foundation Models
AskPDF
Mar 12, 2026

Developing Foundation Models for Universal Segmentation from 3D Whole-Body Positron Emission Tomography

Positron emission tomography (PET) is a key nuclear medicine imaging modality that visualizes radiotracer distributions to quantify in vivo physiological and metabolic processes, playing an irreplaceable role in disease management. Despite its clinical importance, the development of deep learning models for quantitative PET image analysis remains severely limited, driven by both the inherent segmentation challenge from PET's paucity of anatomical contrast and the high costs of data acquisition and annotation. To bridge this gap, we develop generalist foundational models for universal segmentation from 3D whole-body PET imaging. We first build the largest and most comprehensive PET dataset to date, comprising 11041 3D whole-body PET scans with 59831 segmentation masks for model development. Based on this dataset, we present SegAnyPET, an innovative foundational model with general-purpose applicability to diverse segmentation tasks. Built on a 3D architecture with a prompt engineering strategy for mask generation, SegAnyPET enables universal and scalable organ and lesion segmentation, supports efficient human correction with minimal effort, and enables a clinical human-in-the-loop workflow. Extensive evaluations on multi-center, multi-tracer, multi-disease datasets demonstrate that SegAnyPET achieves strong zero-shot performance across a wide range of segmentation tasks, highlighting its potential to advance the clinical applications of molecular imaging.

Yichi Zhang, Le Xue, Wenbo Zhang +16

Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China. · Shanghai Academy of Artificial Intelligence for Science, Shanghai, China. · Department of Nuclear Medicine and PET Center, Huashan Hospital, Fudan University, Shanghai, China. +6

Medical Imaging Foundation Models3D Medical Image SegmentationZero-Shot Medical Image SegmentationPromptable Image Segmentation
AskPDF
Mar 11, 2026

Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI

Foundation models (FMs) show great promise for robust downstream performance across medical imaging tasks and modalities, including cardiac magnetic resonance (CMR), following task-specific adaptation. However, adaptation using single-site data may lead to suboptimal performance and increased model bias, while centralized fine-tuning on clinical data is often infeasible due to privacy constraints. Federated fine-tuning offers a privacy-preserving alternative; yet conventional approaches struggle under heterogeneous, non-IID multi-center data and incur substantial communication overhead when adapting large models. In this work, we study federated FM fine-tuning for 3D CMR disease detection and propose Med-DualLoRA, a client-aware parameter-efficient fine-tuning (PEFT) federated framework that disentangles globally shared and local low-rank adaptations (LoRA) through additive decomposition. Global and local LoRA modules are trained locally, but only the global component is shared and aggregated across sites, keeping local adapters private. This design improves personalization while significantly reducing communication cost, and experiments show that adapting only two transformer blocks preserves performance while further improving efficiency. We evaluate our method on a multi-center state-of-the-art cine 3D CMR FM fine-tuned for disease detection using ACDC and combined M&Ms datasets, treating each vendor as a federated client. Med-DualLoRA achieves statistically significant improved performance (balanced accuracy 0.768, specificity 0.612) compared to other federated PEFT baselines, while maintaining communication efficiency. Our approach provides a scalable solution for local federated adaptation of medical FMs under realistic clinical constraints.

Joan Perramon-Llussà, Amelia Jiménez-Sánchez, Grzegorz Skorupko +4

Artificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Spain · Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain

Federated Fine-TuningMedical Imaging Foundation ModelsFederated LearningLow-Rank AdaptationCardiac MRI
AskPDF
Mar 11, 2026

Prompting with the human-touch: evaluating model-sensitivity of foundation models for musculoskeletal CT segmentation

Promptable Foundation Models (FMs), initially introduced for natural image segmentation, have also revolutionized medical image segmentation. The increasing number of models, along with evaluations varying in datasets, metrics, and compared models, makes direct performance comparison between models difficult and complicates the selection of the most suitable model for specific clinical tasks. In our study, 11 promptable FMs are tested using non-iterative 2D and 3D prompting strategies on a private and public dataset focusing on bone and implant segmentation in four anatomical regions (wrist, shoulder, hip and lower leg). The Pareto-optimal models are identified and further analyzed using human prompts collected through a dedicated observer study. Our findings are: 1) The segmentation performance varies a lot between FMs and prompting strategies; 2) The Pareto-optimal models in 2D are SAM and SAM2.1, in 3D nnInteractive and Med-SAM2; 3) Localization accuracy and rater consistency vary with anatomical structures, with higher consistency for simple structures (wrist bones) and lower consistency for complex structures (pelvis, tibia, implants); 4) The segmentation performance drops using human prompts, suggesting that performance reported on "ideal" prompts extracted from reference labels might overestimate the performance in a human-driven setting; 5) All models were sensitive to prompt variations. While two models demonstrated intra-rater robustness, it did not scale to inter-rater settings. We conclude that the selection of the most optimal FM for a human-driven setting remains challenging, with even high-performing FMs being sensitive to variations in human input prompts. Our code base for prompt extraction and model inference is available: https://github.com/CarolineMagg/segmentation-FM-benchmark/

Caroline Magg, Maaike A. ter Wee, Johannes G. G. Dobbe +4

Quantitative Healthcare Analysis (QurAI) Group, University of Amsterdam, Science Park 900, Amsterdam, 1098 XH, The Netherlands · Department Biomedical Engineering and Physics, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands · Department Orthopaedics, Amsterdam UMC, Meibergdreef 9, Amsterdam, 1105 AZ, The Netherlands

Medical Image SegmentationMedical Imaging Foundation ModelsPromptable Image Segmentation3D Medical Image SegmentationPrompt RobustnessMedical Image Benchmarks
AskPDF
Mar 11, 2026

DINOv3 with Test-Time Calibration for Automated Carotid Intima-Media Thickness Measurement on CUBS v1

Carotid intima-media thickness (CIMT) measured from B-mode ultrasound is an established vascular biomarker for atherosclerosis and cardiovascular risk stratification. Although a wide range of computerized methods have been proposed for carotid boundary delineation and CIMT estimation, robust and transferable deep models that jointly address segmentation and measurement remain underexplored, particularly in the era of vision foundation models. Motivated by recent advances in adapting DINOv3 to medical segmentation and exploiting DINOv3 in test-time optimization pipelines, we investigate a DINOv3-based framework for carotid intima-media complex segmentation and subsequent CIMT measurement on the Carotid Ultrasound Boundary Study (CUBS) v1 dataset. Our pipeline predicts the intima-media band at a fixed image resolution, extracts upper and lower boundaries column-wise, corrects for image resizing using the per-image calibration factor provided by CUBS, and reports CIMT in physical units. Across three patient-level test splits, our method achieved a mean test Dice of 0.7739 ±\pm 0.0037 and IoU of 0.6384 ±\pm 0.0044. The mean CIMT absolute error was 181.16 ±\pm 11.57 μμm, with a mean Pearson correlation of 0.480 ±\pm 0.259. In a held-out validation subset (n=28n=28), test-time threshold calibration reduced the mean absolute CIMT error from 141.0 μμm at the default threshold to 101.1 μμm at the measurement-optimized threshold, while simultaneously reducing systematic bias toward zero. Relative to the error ranges reported in the original CUBS benchmark for classical computerized methods, these results place a DINOv3-based approach within the clinically relevant ∼\sim0.1 mm measurement regime. Together, our findings support the feasibility of using vision foundation models for interpretable, calibration-aware CIMT measurement.

Zhenpeng Zhang, Jinwei Lu, Yurui Dong +1

School of Basic Medical Sciences, Fudan University, Shanghai 200032, China · Fudan University, Shanghai, China · Institute of Medical Genetics and Genomics, Fudan University, Shanghai 200032, China

Medical ImagingUltrasound Image SegmentationMedical Image SegmentationMedical Imaging Foundation Models
AskPDF
Mar 10, 2026

MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification

Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and weak supervision. Mammography, in particular, is characterized by large images, variable multi-view studies and predominantly breast-level labels, making end-to-end fine-tuning computationally expensive and often impractical. We propose Multiple Instance Learning on Precomputed Features (MIL-PF), a scalable framework that combines frozen foundation encoders with a lightweight MIL head for mammography classification. By precomputing the semantic representations and training only a small task-specific aggregation module (40k parameters), the method enables efficient experimentation and adaptation without retraining large backbones. The architecture explicitly models the global tissue context and the sparse local lesion signals through attention-based aggregation. MIL-PF achieves state-of-the-art classification performance at clinical scale while substantially reducing training complexity. We release the code for full reproducibility.

Nikola Jovišić, Milica Škipina, Nicola Dall'Asen +1

Institute for AI R&D of Serbia, Serbia · Faculty of Technical Sciences, University of Novi Sad, Serbia · University of Trento, Italy +2

Mammography Image ClassificationMedical Image ClassificationMultiple Instance LearningVision Foundation Model AdaptationMedical Imaging Foundation Models
AskPDF