Gliomas are the most prevalent type of primary brain tumors, and their accurate segmentation from MRI is critical for diagnosis, treatment planning, and longitudinal monitoring. However, the scarcity of high-quality annotated imaging data in Sub-Saharan Africa (SSA) poses a significant challenge for deploying advanced segmentation models in clinical workflows. This study introduces a robust and computationally efficient deep learning framework tailored for resource-constrained settings. We leveraged a 3D Attention UNet architecture augmented with residual blocks and enhanced through transfer learning from pre-trained weights on the BraTS 2021 dataset. Our model was evaluated on 95 MRI cases from the BraTS-Africa dataset, a benchmark for glioma segmentation in SSA MRI data. Despite the limited data quality and quantity, our approach achieved Dice scores of 0.76 for the Enhancing Tumor (ET), 0.80 for Necrotic and Non-Enhancing Tumor Core (NETC), and 0.85 for Surrounding Non-Functional Hemisphere (SNFH). These results demonstrate the generalizability of the proposed model and its potential to support clinical decision making in low-resource settings. The compact architecture, approximately 90 MB, and sub-minute per-volume inference time on consumer-grade hardware further underscore its practicality for deployment in SSA health systems. This work contributes toward closing the gap in equitable AI for global health by empowering underserved regions with high-performing and accessible medical imaging solutions.

Understanding 3D medical image volumes is critical in the medical field, yet existing 3D medical convolution and transformer-based self-supervised learning (SSL) methods often lack deep semantic comprehension. Recent advancements in multimodal large language models (MLLMs) provide a promising approach to enhance image understanding through text descriptions. To leverage these 2D MLLMs for improved 3D medical image understanding, we propose Med3DInsight, a novel pretraining framework that integrates 3D image encoders with 2D MLLMs via a specially designed plane-slice-aware transformer module. Additionally, our model employs a partial optimal transport based alignment, demonstrating greater tolerance to noise introduced by potential noises in LLM-generated content. Med3DInsight introduces a new paradigm for scalable multimodal 3D medical representation learning without requiring human annotations. Extensive experiments demonstrate our state-of-the-art performance on two downstream tasks, i.e., segmentation and classification, across various public datasets with CT and MRI modalities, outperforming current SSL methods. Med3DInsight can be seamlessly integrated into existing 3D medical image understanding networks, potentially enhancing their performance. Our source code, generated datasets, and pre-trained models will be available at https://github.com/Qybc/Med3DInsight.

Automated ultrasound (US) image analysis remains a longstanding challenge due to anatomical complexity and the scarcity of annotated data. Although large-scale pretraining has improved data efficiency in many visual domains, its impact in US is limited by a pronounced domain shift from other imaging modalities and high variability across clinical applications, such as chest, ovarian, and endoscopic imaging. To address this, we propose UltraSam, a SAM-style model trained on a heterogeneous collection of publicly available segmentation datasets, originally developed in isolation. UltraSam is trained under the prompt-conditioned segmentation paradigm, which eliminates the need for unified labels and enables generalization to a broad range of downstream tasks. We compile US-43d, a large-scale collection of 43 open-access US datasets comprising over 282,000 images with segmentation masks covering 58 anatomical structures. We explore adaptation and fine-tuning strategies for SAM and systematically evaluate transferability across downstream tasks, comparing against state-of-the-art pretraining methods. We further propose prompted classification, a new use case where object-specific prompts and image features are jointly decoded to improve classification performance. In experiments on three diverse public US datasets, UltraSam outperforms existing SAM variants on prompt-based segmentation and surpasses self-supervised US foundation models on downstream (prompted) classification and instance segmentation tasks. UltraSam demonstrates that SAM-style training on diverse, sparsely annotated US data enables effective generalization across tasks. By unlocking the value of fragmented public datasets, our approach lays the foundation for scalable, real-world US representation learning. We release our code and pretrained models at https://github.com/CAMMA-public/UltraSam and invite the community to further this effort by continuing to contribute high-quality datasets.

The diffusion MRI Neurite Exchange Imaging model offers a promising framework for probing gray matter microstructure by estimating parameters such as compartment sizes, diffusivities, and inter-compartmental water exchange time. However, existing protocols require long scan times. This study proposes a reduced acquisition scheme for the Connectome 2.0 scanner that preserves model accuracy while substantially shortening scan duration. We developed a data-driven framework using explainable artificial intelligence with a guided recursive feature elimination strategy to identify an optimal 8-feature subset from a 15-feature protocol. The performance of this optimized protocol was validated in vivo and benchmarked against the full acquisition and alternative reduction strategies. Parameter accuracy, preservation of anatomical contrast, and test-retest reproducibility were assessed. The reduced protocol yielded parameter estimates and cortical maps comparable to the full protocol, with low estimation errors in synthetic data and minimal impact on test-retest variability. Compared to theory-driven and heuristic reduction schemes, the optimized protocol demonstrated superior robustness, reducing the deviation in water exchange time estimates by over two-fold. In conclusion, this hybrid optimization framework enables viable imaging of neurite exchange in 14 minutes without loss of parameter fidelity. This approach supports the broader application of exchange-sensitive diffusion magnetic resonance imaging in neuroscience and clinical research, and offers a generalizable method for designing efficient acquisition protocols in biophysical parameter mapping.

Recent advances in large vision-language models (LVLMs) have demonstrated strong performance on general-purpose medical tasks. However, their effectiveness in specialized domains such as dentistry remains underexplored. In particular, panoramic X-rays, a widely used imaging modality in oral radiology, pose interpretative challenges due to dense anatomical structures and subtle pathological cues, which are not captured by existing medical benchmarks or instruction datasets. To this end, we introduce MMOral, the first large-scale multimodal instruction dataset and benchmark tailored for panoramic X-ray interpretation. MMOral consists of 20,563 annotated images paired with 1.3 million instruction-following instances across diverse task types, including attribute extraction, report generation, visual question answering, and image-grounded dialogue. In addition, we present MMOral-Bench, a comprehensive evaluation suite covering five key diagnostic dimensions in dentistry. We evaluate 64 LVLMs on MMOral-Bench and find that even the best-performing model, i.e., GPT-4o, only achieves 41.45% accuracy, revealing significant limitations of current models in this domain. To promote the progress of this specific domain, we also propose OralGPT, which conducts supervised fine-tuning (SFT) upon Qwen2.5-VL-7B with our meticulously curated MMOral instruction dataset. Remarkably, a single epoch of SFT yields substantial performance enhancements for LVLMs, e.g., OralGPT demonstrates a 24.73% improvement. Both MMOral and OralGPT hold significant potential as a critical foundation for intelligent dentistry and enable more clinically impactful multimodal AI systems in the dental field. The dataset, model, benchmark, and evaluation suite are available at https://github.com/isbrycee/OralGPT.

Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal fusion, primarily the significant semantic gap between abstract textual prompts and fine-grained medical visual features, as well as the resulting feature dispersion. To address these issues, we revisit the problem from the perspective of semantic aggregation. Specifically, we propose an Expectation-Maximization (EM) Aggregation mechanism and a Text-Guided Pixel Decoder. The former mitigates feature dispersion by dynamically clustering features into compact semantic centers to enhance cross-modal correspondence. The latter is designed to bridge the semantic gap by leveraging domain-invariant textual knowledge to effectively guide deep visual representations. The synergy between these two mechanisms significantly improves the model's generalization ability. Extensive experiments on public cardiac and fundus datasets demonstrate that our method consistently outperforms existing SOTA approaches across multiple domain generalization benchmarks.

Chest radiographs (CXRs) are among the most common tests in medicine. Automated image interpretation may reduce radiologists\' workload and expand access to diagnostic expertise. Deep learning multi-task and foundation models have shown strong performance for CXR interpretation but are vulnerable to shortcut learning, where models rely on spurious and off-target correlations rather than clinically relevant features to make decisions. We introduce RoentMod, a counterfactual image editing framework that generates anatomically realistic CXRs with user-specified, synthetic pathology while preserving unrelated anatomical features of the original scan. RoentMod combines an open-source medical image generator (RoentGen) with an image-to-image modification model without requiring retraining. In reader studies with board-certified radiologists and radiology residents, RoentMod-produced images appeared realistic in 93\% of cases, correctly incorporated the specified finding in 89-99\% of cases, and preserved native anatomy comparable to real follow-up CXRs. Using RoentMod, we demonstrate that state-of-the-art multi-task and foundation models frequently exploit off-target pathology as shortcuts, limiting their specificity. Incorporating RoentMod-generated counterfactual images during training mitigated this vulnerability, improving model discrimination across multiple pathologies by 3-19\% AUC in internal validation and by 1-11\% for 5 out of 6 tested pathologies in external testing. These findings establish RoentMod as a broadly applicable tool for probing and correcting shortcut learning in medical AI. By enabling controlled counterfactual interventions, RoentMod enhances the robustness and interpretability of CXR interpretation models and provides a generalizable strategy for improving foundation models in medical imaging.

Fetal diffusion-weighted magnetic resonance imaging (dMRI) represents a promising modality for the assessment of white matter fiber organization, microstructure and development during pregnancy. Over the past two decades, research using this technology has significantly increased, but no consensus has yet been established on how to best implement and standardize the use of fetal dMRI across clinical and research settings. This scoping review aims to synthesize the various methodological approaches for the analysis of fetal dMRI brain data and their applications. We identified a total of 54 relevant articles and analyzed them across five primary domains: (1) datasets, (2) acquisition protocols, (3) image preprocessing/denoising, (4) image processing/modeling, and (5) brain atlas construction. The review of these articles reveals a predominant reliance on Diffusion Tensor Imaging (DTI) (n=37) to study fiber properties, and deterministic tractography approaches to investigate fiber organization (n=23). However, there is an emerging trend towards the adoption of more advanced techniques that address the inherent limitations of fetal dMRI (e.g. maternal and fetal motion, intensity artifacts, fetus's fast and uneven development), particularly through the application of artificial intelligence-based approaches (n=8). In our view, the results suggest that the potential of fetal brain dMRI is hindered by the methodological heterogeneity of the proposed solutions and the lack of publicly available data and tools. Nevertheless, clinical applications demonstrate its utility in studying brain development in both healthy and pathological conditions.

Colorectal cancer frequently metastasizes to the liver, significantly reducing long-term survival. While surgical resection is the only potentially curative treatment for colorectal liver metastasis (CRLM), patient outcomes vary widely depending on tumor characteristics along with clinical and genomic factors. Current prognostic models, often based on limited clinical or molecular features, lack sufficient predictive power, especially in multifocal CRLM cases. We present a fully automated framework for surgical outcome prediction from pre- and post-contrast MRI acquired before surgery. Our framework consists of a segmentation pipeline and a radiomics pipeline. The segmentation pipeline learns to segment the liver, tumors, and spleen from partially annotated data by leveraging promptable foundation models to complete missing labels. Also, we propose SAMONAI, a novel zero-shot 3D prompt propagation algorithm that leverages the Segment Anything Model to segment 3D regions of interest from a single point prompt, significantly improving our segmentation pipeline's accuracy and efficiency. The predicted pre- and post-contrast segmentations are then fed into our radiomics pipeline, which extracts features from each tumor and predicts survival using SurvAMINN, a novel autoencoder-based multiple instance neural network for survival analysis. SurvAMINN jointly learns dimensionality reduction and hazard prediction from right-censored survival data, focusing on the most aggressive tumors. Extensive evaluation on an institutional dataset comprising 227 patients demonstrates that our framework surpasses existing clinical and genomic biomarkers, delivering a C-index improvement exceeding 10%. Our results demonstrate the potential of integrating automated segmentation algorithms and radiomics-based survival analysis to deliver accurate, annotation-efficient, and interpretable outcome prediction in CRLM.

<i>"Just Accepted" papers have undergone full peer review and have been accepted for publication in <i>Radiology: Artificial Intelligence</i>. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content.</i> Purpose To assess the effectiveness of an explainable deep learning (DL) model, developed using multiparametric MRI (mpMRI) features, in improving diagnostic accuracy and efficiency of radiologists for classification of focal liver lesions (FLLs). Materials and Methods FLLs ≥ 1 cm in diameter at mpMRI were included in the study. nn-Unet and Liver Imaging Feature Transformer (LIFT) models were developed using retrospective data from one hospital (January 2018-August 2023). nnU-Net was used for lesion segmentation and LIFT for FLL classification. External testing was performed on data from three hospitals (January 2018-December 2023), with a prospective test set obtained from January 2024 to April 2024. Model performance was compared with radiologists and impact of model assistance on junior and senior radiologist performance was assessed. Evaluation metrics included the Dice similarity coefficient (DSC) and accuracy. Results A total of 2131 individuals with FLLs (mean age, 56 ± [SD] 12 years; 1476 female) were included in the training, internal test, external test, and prospective test sets. Average DSC values for liver and tumor segmentation across the three test sets were 0.98 and 0.96, respectively. Average accuracy for features and lesion classification across the three test sets were 93% and 97%, respectively. LIFT-assisted readings improved diagnostic accuracy (average 5.3% increase, <i>P</i> < .001), reduced reading time (average 34.5 seconds decrease, <i>P</i> < .001), and enhanced confidence (average 0.3-point increase, <i>P</i> < .001) of junior radiologists. Conclusion The proposed DL model accurately detected and classified FLLs, improving diagnostic accuracy and efficiency of junior radiologists. ©RSNA, 2025.