The integration of artificial intelligence (AI) into healthcare is transforming clinical decision-making, patient outcomes, and workflows. AI inference, applying trained models to new data, is central to this evolution, with cloud-based infrastructures enabling scalable AI deployment. The Open Medical Inference (OMI) platform democratizes AI access through open protocols and standardized data formats for seamless, interoperable healthcare data exchange. By integrating standards like FHIR and DICOMweb, OMI ensures interoperability between healthcare institutions and AI services while fostering ethical AI use through a governance framework addressing privacy, transparency, and fairness.OMI's implementation is structured into work packages, each addressing technical and ethical aspects. These include expanding the Medical Informatics Initiative (MII) Core Dataset for medical imaging, developing infrastructure for AI inference, and creating an open-source DICOMweb adapter for legacy systems. Standardized data formats ensure interoperability, while the AI Governance Framework promotes trust and responsible AI use.The project aims to establish an interoperable AI network across healthcare institutions, connecting existing infrastructures and AI services to enhance clinical outcomes. · OMI develops open protocols and standardized data formats for seamless healthcare data exchange.. · Integration with FHIR and DICOMweb ensures interoperability between healthcare systems and AI services.. · A governance framework addresses privacy, transparency, and fairness in AI usage.. · Work packages focus on expanding datasets, creating infrastructure, and enabling legacy system integration.. · The project aims to create a scalable, secure, and interoperable AI network in healthcare.. · Pelka O, Sigle S, Werner P et al. Democratizing AI in Healthcare with Open Medical Inference (OMI): Protocols, Data Exchange, and AI Integration. Rofo 2025; DOI 10.1055/a-2651-6653.

The limited availability of annotated data presents a major challenge for applying deep learning methods to medical image analysis. Few-shot learning methods aim to recognize new classes from only a small number of labeled examples. These methods are typically studied under the standard few-shot learning setting, where all classes in a task are new. However, medical applications such as pathology classification from chest X-rays often require learning new classes while simultaneously leveraging knowledge of previously known ones, a scenario more closely aligned with generalized few-shot classification. Despite its practical relevance, few-shot learning has been scarcely studied in this context. In this work, we present MetaChest, a large-scale dataset of 479,215 chest X-rays collected from four public databases. MetaChest includes a meta-set partition specifically designed for standard few-shot classification, as well as an algorithm for generating multi-label episodes. We conduct extensive experiments evaluating both a standard transfer learning approach and an extension of ProtoNet across a wide range of few-shot multi-label classification tasks. Our results demonstrate that increasing the number of classes per episode and the number of training examples per class improves classification performance. Notably, the transfer learning approach consistently outperforms the ProtoNet extension, despite not being tailored for few-shot learning. We also show that higher-resolution images improve accuracy at the cost of additional computation, while efficient model architectures achieve comparable performance to larger models with significantly reduced resource requirements.

Generalist multimodal AI systems such as large language models (LLMs) and vision language models (VLMs) are increasingly accessed by clinicians and patients alike for medical image interpretation through widely available consumer-facing chatbots. Most evaluations claiming expert level performance are on public datasets containing common pathologies. Rigorous evaluation of frontier models on difficult diagnostic cases remains limited. We developed a pilot benchmark of 50 expert-level "spot diagnosis" cases across multiple imaging modalities to evaluate the performance of frontier AI models against board-certified radiologists and radiology trainees. To mirror real-world usage, the reasoning modes of five popular frontier AI models were tested through their native web interfaces, viz. OpenAI o3, OpenAI GPT-5, Gemini 2.5 Pro, Grok-4, and Claude Opus 4.1. Accuracy was scored by blinded experts, and reproducibility was assessed across three independent runs. GPT-5 was additionally evaluated across various reasoning modes. Reasoning quality errors were assessed and a taxonomy of visual reasoning errors was defined. Board-certified radiologists achieved the highest diagnostic accuracy (83%), outperforming trainees (45%) and all AI models (best performance shown by GPT-5: 30%). Reliability was substantial for GPT-5 and o3, moderate for Gemini 2.5 Pro and Grok-4, and poor for Claude Opus 4.1. These findings demonstrate that advanced frontier models fall far short of radiologists in challenging diagnostic cases. Our benchmark highlights the present limitations of generalist AI in medical imaging and cautions against unsupervised clinical use. We also provide a qualitative analysis of reasoning traces and propose a practical taxonomy of visual reasoning errors by AI models for better understanding their failure modes, informing evaluation standards and guiding more robust model development.

In this work, we propose FFDP, a set of IO-aware non-GEMM fused kernels supplemented with a distributed framework for image registration at unprecedented scales. Image registration is an inverse problem fundamental to biomedical and life sciences, but algorithms have not scaled in tandem with image acquisition capabilities. Our framework complements existing model parallelism techniques proposed for large-scale transformer training by optimizing non-GEMM bottlenecks and enabling convolution-aware tensor sharding. We demonstrate unprecedented capabilities by performing multimodal registration of a 100 micron ex-vivo human brain MRI volume at native resolution - an inverse problem more than 570x larger than a standard clinical datum in about a minute using only 8 A6000 GPUs. FFDP accelerates existing state-of-the-art optimization and deep learning registration pipelines by upto 6 - 7x while reducing peak memory consumption by 20 - 59%. Comparative analysis on a 250 micron dataset shows that FFDP can fit upto 64x larger problems than existing SOTA on a single GPU, and highlights both the performance and efficiency gains of FFDP compared to SOTA image registration methods.

We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method enables causal interventions on target attributes, consistently propagating their effects to causal dependents without altering the core identity of the image. In contrast to prior approaches that rely on prompt engineering without explicit causal structure, Causal-Adapter leverages structural causal modeling augmented with two attribute regularization strategies: prompt-aligned injection, which aligns causal attributes with textual embeddings for precise semantic control, and a conditioned token contrastive loss to disentangle attribute factors and reduce spurious correlations. Causal-Adapter achieves state-of-the-art performance on both synthetic and real-world datasets, with up to 91\% MAE reduction on Pendulum for accurate attribute control and 87\% FID reduction on ADNI for high-fidelity MRI image generation. These results show that our approach enables robust, generalizable counterfactual editing with faithful attribute modification and strong identity preservation.

Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence by enabling rich cross-modal reasoning. Despite their success in general domains, applying these models to medical imaging remains challenging due to the limited availability of diverse imaging modalities and multilingual clinical data. Most existing medical VLMs are trained on a subset of imaging modalities and focus primarily on high-resource languages, thus limiting their generalizability and clinical utility. To address these limitations, we introduce a novel Vietnamese-language multimodal medical dataset comprising 1,567,062 paired CT-PET images and corresponding 2,757 full-length clinical reports. This dataset is designed to fill two pressing gaps in medical AI development: (1) the lack of PET/CT imaging data in existing VLMs training corpora, which hinders the development of models capable of handling functional imaging tasks; and (2) the underrepresentation of low-resource languages, particularly the Vietnamese language, in medical vision-language research. To the best of our knowledge, this is the first dataset to provide comprehensive PET/CT-report pairs in Vietnamese. We further introduce a training framework to enhance VLMs' learning, including data augmentation and expert-validated test sets. We conduct comprehensive experiments benchmarking state-of-the-art VLMs on downstream tasks, including medical report generation and visual question answering. The experimental results show that incorporating our dataset significantly improves the performance of existing VLMs. We believe this dataset and benchmark will serve as a pivotal step in advancing the development of more robust VLMs for medical imaging, particularly in low-resource languages, and improving their clinical relevance in Vietnamese healthcare.

Precise confidence estimation in deep learning is vital for high-stakes fields like medical imaging, where overconfident misclassifications can have serious consequences. This work evaluates the effectiveness of Temperature Scaling (TS), a post-hoc calibration technique, in improving the reliability of convolutional neural networks (CNNs) for brain tumor classification. We develop a custom CNN and train it on a merged brain MRI dataset. To simulate real-world uncertainty, five types of image noise are introduced: Gaussian, Poisson, Salt & Pepper, Speckle, and Uniform. Model performance is evaluated using precision, recall, F1-score, accuracy, negative log-likelihood (NLL), and expected calibration error (ECE), both before and after calibration. Results demonstrate that TS significantly reduces ECE and NLL under all noise conditions without degrading classification accuracy. This underscores TS as an effective and computationally efficient approach to enhance decision confidence of medical AI systems, hence making model outputs more reliable in noisy or uncertain settings.

Adolescent idiopathic scoliosis (AIS) is a common spinal deformity affecting approximately 2.2% of boys and 4.8% of girls worldwide. The Cobb angle serves as the gold standard for AIS severity assessment, yet traditional manual measurements suffer from significant observer variability, compromising diagnostic accuracy. Despite prior automation attempts, existing methods use simplified spinal models and predetermined curve patterns that fail to address clinical complexity. We present a novel deep learning framework for AIS assessment that simultaneously predicts both superior and inferior endplate angles with corresponding midpoint coordinates for each vertebra, preserving the anatomical reality of vertebral wedging in progressive AIS. Our approach combines an HRNet backbone with Swin-Transformer modules and biomechanically informed constraints for enhanced feature extraction. We employ Singular Value Decomposition (SVD) to analyze angle predictions directly from vertebral morphology, enabling flexible detection of diverse scoliosis patterns without predefined curve assumptions. Using 630 full-spine anteroposterior radiographs from patients aged 10-18 years with rigorous dual-rater annotation, our method achieved 83.45% diagnostic accuracy and 2.55{\deg} mean absolute error. The framework demonstrates exceptional generalization capability on out-of-distribution cases. Additionally, we introduce the Vertebral Wedging Index (VWI), a novel metric quantifying vertebral deformation. Longitudinal analysis revealed VWI's significant prognostic correlation with curve progression while traditional Cobb angles showed no correlation, providing robust support for early AIS detection, personalized treatment planning, and progression monitoring.

Magnetic resonance imaging (MRI) quality assessment is crucial for clinical decision-making, yet remains challenging due to data scarcity and protocol variability. Traditional approaches face fundamental trade-offs: signal-based methods like MRIQC provide quantitative metrics but lack semantic understanding, while deep learning approaches achieve high accuracy but sacrifice interpretability. To address these limitations, we introduce the Multimodal MRI Quality Assessment (MMRQA) framework, pioneering the integration of multimodal large language models (MLLMs) with acquisition-aware signal processing. MMRQA combines three key innovations: robust metric extraction via MRQy augmented with simulated artifacts, structured transformation of metrics into question-answer pairs using Qwen, and parameter-efficient fusion through Low-Rank Adaptation (LoRA) of LLaVA-OneVision. Evaluated on MR-ART, FastMRI, and MyConnectome benchmarks, MMRQA achieves state-of-the-art performance with strong zero-shot generalization, as validated by comprehensive ablation studies. By bridging quantitative analysis with semantic reasoning, our framework generates clinically interpretable outputs that enhance quality control in dynamic medical settings.

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and their deficiencies in extracting local detailed information. To address high computational costs and inadequate local detail information, we reassess the design of feature extraction modules and propose a new deep-learning network called LamFormer for fine-grained segmentation tasks across multiple organs. LamFormer is a novel U-shaped network that employs Linear Attention Mamba (LAM) in an enhanced pyramid encoder to capture multi-scale long-range dependencies. We construct the Parallel Hierarchical Feature Aggregation (PHFA) module to aggregate features from different layers of the encoder, narrowing the semantic gap among features while filtering information. Finally, we design the Reduced Transformer (RT), which utilizes a distinct computational approach to globally model up-sampled features. RRT enhances the extraction of detailed local information and improves the network's capability to capture long-range dependencies. LamFormer outperforms existing segmentation methods on seven complex and diverse datasets, demonstrating exceptional performance. Moreover, the proposed network achieves a balance between model performance and model complexity.