A diagnostic medical foundation model (MedFM) is an artificial intelligence (AI) system engineered to accurately determine diagnoses across various medical imaging modalities and specialties. To train MedFM, we created the PubMed Central Medical Images Dataset (PMCMID), the largest annotated medical image dataset to date, comprising 16,126,659 images from 3,021,780 medical publications. Using AI- and ontology-based methods, we identified 4,482,237 medical images (e.g., clinical photos, X-rays, ultrasounds) and generated comprehensive annotations. To optimize MedFMs performance and assess biases, 13,266 images were manually annotated to establish a multimodal benchmark. MedFM achieved physician-level performance in diagnosis tasks spanning radiology, dermatology, and infectious diseases without requiring specific training. Additionally, we developed the Image2Paper app, allowing clinicians to upload medical images and retrieve relevant literature. The correct diagnoses appeared within the top ten results in 88.4% and at least one relevant differential diagnosis in 93.0%. MedFM and PMCMID were made publicly available. FundingResearch reported here was partially supported by the National Cancer Institute (NCI) (R01 CA260271), the Saudi Company for Artificial Intelligence (SCAI) Authority, and the German Federal Ministry for Economic Affairs and Climate Action (BMWK) under the project DAKI-FWS (01MK21009E). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Detecting breast cancer early is of the utmost importance to effectively treat the millions of women afflicted by breast cancer worldwide every year. Although mammography is the primary imaging modality for screening breast cancer, there is an increasing interest in adding magnetic resonance imaging (MRI) to screening programmes, particularly for women at high risk. Recent guidelines by the European Society of Breast Imaging (EUSOBI) recommended breast MRI as a supplemental screening tool for women with dense breast tissue. However, acquiring and reading MRI scans requires significantly more time from expert radiologists. This highlights the need to develop new automated methods to detect cancer accurately using MRI and Artificial Intelligence (AI), which have the potential to support radiologists in breast MRI interpretation and classification and help detect cancer earlier. For this reason, the ODELIA consortium has made this multi-centre dataset publicly available to assist in developing AI tools for the detection of breast cancer on MRI.

This paper presents MSLesSeg, a new, publicly accessible MRI dataset designed to advance research in Multiple Sclerosis (MS) lesion segmentation. The dataset comprises 115 scans of 75 patients including T1, T2 and FLAIR sequences, along with supplementary clinical data collected across different sources. Expert-validated annotations provide high-quality lesion segmentation labels, establishing a reliable human-labeled dataset for benchmarking. Part of the dataset was shared with expert scientists with the aim to compare the last automatic AI-based image segmentation solutions with an expert-biased handmade segmentation. In addition, an AI-based lesion segmentation of MSLesSeg was developed and technically validated against the last state-of-the-art methods. The dataset, the detailed analysis of researcher contributions, and the baseline results presented here mark a significant milestone for advancing automated MS lesion segmentation research.

Clinical decision-making routinely demands reasoning over heterogeneous data, yet existing multimodal language models (MLLMs) remain largely vision-centric and fail to generalize across clinical specialties. To bridge this gap, we introduce QoQ-Med-7B/32B, the first open generalist clinical foundation model that jointly reasons across medical images, time-series signals, and text reports. QoQ-Med is trained with Domain-aware Relative Policy Optimization (DRPO), a novel reinforcement-learning objective that hierarchically scales normalized rewards according to domain rarity and modality difficulty, mitigating performance imbalance caused by skewed clinical data distributions. Trained on 2.61 million instruction tuning pairs spanning 9 clinical domains, we show that DRPO training boosts diagnostic performance by 43% in macro-F1 on average across all visual domains as compared to other critic-free training methods like GRPO. Furthermore, with QoQ-Med trained on intensive segmentation data, it is able to highlight salient regions related to the diagnosis, with an IoU 10x higher than open models while reaching the performance of OpenAI o4-mini. To foster reproducibility and downstream research, we release (i) the full model weights, (ii) the modular training pipeline, and (iii) all intermediate reasoning traces at https://github.com/DDVD233/QoQ_Med.

Medical image challenges have played a transformative role in advancing the field, catalyzing algorithmic innovation and establishing new performance standards across diverse clinical applications. Image registration, a foundational task in neuroimaging pipelines, has similarly benefited from the Learn2Reg initiative. Building on this foundation, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark designed to assess and advance unsupervised brain MRI registration. Distinct from prior challenges that leveraged anatomical label maps for supervision, LUMIR removes this dependency by providing over 4,000 preprocessed T1-weighted brain MRIs for training without any label maps, encouraging biologically plausible deformation modeling through self-supervision. In addition to evaluating performance on 590 held-out test subjects, LUMIR introduces a rigorous suite of zero-shot generalization tasks, spanning out-of-domain imaging modalities (e.g., FLAIR, T2-weighted, T2*-weighted), disease populations (e.g., Alzheimer's disease), acquisition protocols (e.g., 9.4T MRI), and species (e.g., macaque brains). A total of 1,158 subjects and over 4,000 image pairs were included for evaluation. Performance was assessed using both segmentation-based metrics (Dice coefficient, 95th percentile Hausdorff distance) and landmark-based registration accuracy (target registration error). Across both in-domain and zero-shot tasks, deep learning-based methods consistently achieved state-of-the-art accuracy while producing anatomically plausible deformation fields. The top-performing deep learning-based models demonstrated diffeomorphic properties and inverse consistency, outperforming several leading optimization-based methods, and showing strong robustness to most domain shifts, the exception being a drop in performance on out-of-domain contrasts.

Accurate measurement of hallux valgus angle (HVA) and intermetatarsal angle (IMA) is essential for diagnosing hallux valgus and determining appropriate treatment strategies. Traditional manual measurement methods, while standardized, are time-consuming, labor-intensive, and subject to evaluator bias. Recent advancements in deep learning have been applied to hallux valgus angle estimation, but the development of effective algorithms requires large, well-annotated datasets. Existing X-ray datasets are typically limited to cropped foot regions images, and only one dataset containing very few samples is publicly available. To address these challenges, we introduce HVAngleEst, the first large-scale, open-access dataset specifically designed for hallux valgus angle estimation. HVAngleEst comprises 1,382 X-ray images from 1,150 patients and includes comprehensive annotations, such as foot localization, hallux valgus angles, and line segments for each phalanx. This dataset enables fully automated, end-to-end hallux valgus angle estimation, reducing manual labor and eliminating evaluator bias.

Periventricular white matter injury (PWMI) is the most frequent magnetic resonance imaging (MRI) finding in infants with Cerebral Palsy (CP). We aim to detect CP and identify subtle, sparse PWMI lesions in infants under two years of age with immature brain structures. Based on the characteristic that the responsible lesions are located within five target regions, we first construct a multi-modal dataset including 243 cases with the mask annotations of five target regions for delineating anatomical structures on T1-Weighted Imaging (T1WI) images, masks for lesions on T2-Weighted Imaging (T2WI) images, and categories (CP or Non-CP). Furthermore, we develop a bidirectional projection-based multi-modal fusion transformer (BiP-MFT), incorporating a Bidirectional Projection Fusion Module (BPFM) for integrating the features between five target regions on T1WI images and lesions on T2WI images. Our BiP-MFT achieves subject-level classification accuracy of 0.90, specificity of 0.87, and sensitivity of 0.94. It surpasses the best results of nine comparative methods, with 0.10, 0.08, and 0.09 improvements in classification accuracy, specificity and sensitivity respectively. Our BPFM outperforms eight compared feature fusion strategies using Transformer and U-Net backbones on our dataset. Ablation studies on the dataset annotations and model components justify the effectiveness of our annotation method and the model rationality. The proposed dataset and codes are available at https://github.com/Kai-Qi/BiP-MFT.

Artificial intelligence (AI)-based chest X-ray (CXR) interpretation assistants have demonstrated significant progress and are increasingly being applied in clinical settings. However, contemporary medical AI models often adhere to a simplistic input-to-output paradigm, directly processing an image and an instruction to generate a result, where the instructions may be integral to the model's architecture. This approach overlooks the modeling of the inherent diagnostic reasoning in chest X-ray interpretation. Such reasoning is typically sequential, where each interpretive stage considers the images, the current task, and the contextual information from previous stages. This oversight leads to several shortcomings, including misalignment with clinical scenarios, contextless reasoning, and untraceable errors. To fill this gap, we construct CXRTrek, a new multi-stage visual question answering (VQA) dataset for CXR interpretation. The dataset is designed to explicitly simulate the diagnostic reasoning process employed by radiologists in real-world clinical settings for the first time. CXRTrek covers 8 sequential diagnostic stages, comprising 428,966 samples and over 11 million question-answer (Q&A) pairs, with an average of 26.29 Q&A pairs per sample. Building on the CXRTrek dataset, we propose a new vision-language large model (VLLM), CXRTrekNet, specifically designed to incorporate the clinical reasoning flow into the VLLM framework. CXRTrekNet effectively models the dependencies between diagnostic stages and captures reasoning patterns within the radiological context. Trained on our dataset, the model consistently outperforms existing medical VLLMs on the CXRTrek benchmarks and demonstrates superior generalization across multiple tasks on five diverse external datasets. The dataset and model can be found in our repository (https://github.com/guanjinquan/CXRTrek).

Multimodal Large Language Models (MLLMs) are of great application across many domains, such as multimodal understanding and generation. With the development of diffusion models (DM) and unified MLLMs, the performance of image generation has been significantly improved, however, the study of image screening is rare and its performance with MLLMs is unsatisfactory due to the lack of data and the week image aesthetic reasoning ability in MLLMs. In this work, we propose a complete solution to address these problems in terms of data and methodology. For data, we collect a comprehensive medical image screening dataset with 1500+ samples, each sample consists of a medical image, four generated images, and a multiple-choice answer. The dataset evaluates the aesthetic reasoning ability under four aspects: \textit{(1) Appearance Deformation, (2) Principles of Physical Lighting and Shadow, (3) Placement Layout, (4) Extension Rationality}. For methodology, we utilize long chains of thought (CoT) and Group Relative Policy Optimization with Dynamic Proportional Accuracy reward, called DPA-GRPO, to enhance the image aesthetic reasoning ability of MLLMs. Our experimental results reveal that even state-of-the-art closed-source MLLMs, such as GPT-4o and Qwen-VL-Max, exhibit performance akin to random guessing in image aesthetic reasoning. In contrast, by leveraging the reinforcement learning approach, we are able to surpass the score of both large-scale models and leading closed-source models using a much smaller model. We hope our attempt on medical image screening will serve as a regular configuration in image aesthetic reasoning in the future.

We propose a cascaded 3D diffusion model framework to synthesize high-fidelity 3D PET/CT volumes directly from demographic variables, addressing the growing need for realistic digital twins in oncologic imaging, virtual trials, and AI-driven data augmentation. Unlike deterministic phantoms, which rely on predefined anatomical and metabolic templates, our method employs a two-stage generative process. An initial score-based diffusion model synthesizes low-resolution PET/CT volumes from demographic variables alone, providing global anatomical structures and approximate metabolic activity. This is followed by a super-resolution residual diffusion model that refines spatial resolution. Our framework was trained on 18-F FDG PET/CT scans from the AutoPET dataset and evaluated using organ-wise volume and standardized uptake value (SUV) distributions, comparing synthetic and real data between demographic subgroups. The organ-wise comparison demonstrated strong concordance between synthetic and real images. In particular, most deviations in metabolic uptake values remained within 3-5% of the ground truth in subgroup analysis. These findings highlight the potential of cascaded 3D diffusion models to generate anatomically and metabolically accurate PET/CT images, offering a robust alternative to traditional phantoms and enabling scalable, population-informed synthetic imaging for clinical and research applications.