Foundation models (FMs) represent a significant evolution in artificial intelligence (AI), impacting diverse fields. Within radiology, this evolution offers greater adaptability, multimodal integration, and improved generalizability compared with traditional narrow AI. Utilizing large-scale pre-training and efficient fine-tuning, FMs can support diverse applications, including image interpretation, report generation, integrative diagnostics combining imaging with clinical/laboratory data, and synthetic data creation, holding significant promise for advancements in precision medicine. However, clinical translation of FMs faces several substantial challenges. Key concerns include the inherent opacity of model decision-making processes, environmental and social sustainability issues, risks to data privacy, complex ethical considerations, such as bias and fairness, and navigating the uncertainty of regulatory frameworks. Moreover, rigorous validation is essential to address inherent stochasticity and the risk of hallucination. This international collaborative effort provides a comprehensive overview of the fundamentals, applications, opportunities, challenges, and prospects of FMs, aiming to guide their responsible and effective adoption in radiology and healthcare.

Accurate MR signal simulation, including microvascular structures and water diffusion, is crucial for MRI techniques like fMRI BOLD modeling and MR vascular Fingerprinting (MRF), which use susceptibility effects on MR signals for tissue characterization. However, integrating microvascular features and diffusion remains computationally challenging, limiting the accuracy of the estimates. Using advanced modeling and deep neural networks, we propose a novel simulation tool that efficiently accounts for susceptibility and diffusion effects. We used dimension reduction of magnetic field inhomogeneity matrices combined with deep learning methodology to accelerate the simulations while maintaining their accuracy. We validated our results through an in silico study against a reference method and in vivo MRF experiments. This approach accelerates MR signal generation by a factor of almost 13 000 compared to previously used simulation methods while preserving accuracy. The MR-WAVES method allows fast generation of MR signals accounting for microvascular structures and water-diffusion contribution.

This study aims to demonstrate the performance of machine learning algorithms to distinguish clinically significant prostate cancer (csPCa) from clinically insignificant prostate cancer (ciPCa) in prostate bi-parametric magnetic resonance imaging (MRI) using radiomics features. MRI images of patients who were diagnosed with cancer with histopathological confirmation following prostate MRI were collected retrospectively. Patients with a Gleason score of 3+3 were considered to have clinically ciPCa, and patients with a Gleason score of 3+4 and above were considered to have csPCa. Radiomics features were extracted from T2-weighted (T2W) images, apparent diffusion coefficient (ADC) images, and their corresponding Laplacian of Gaussian (LoG) filtered versions. Additionally, a third feature subset was created by combining the T2W and ADC images, enhancing the analysis with an integrated approach. Once the features were extracted, Pearson’s correlation coefficient and selection were performed using wrapper-based sequential algorithms. The models were then built using support vector machine (SVM) and logistic regression (LR) machine learning algorithms. The models were validated using a five-fold cross-validation technique. This study included 77 patients, 30 with ciPCA and 47 with csPCA. From each image, four images were extracted with LoG filtering, and 111 features were obtained from each image. After feature selection, 5 features were obtained from T2W images, 5 from ADC images, and 15 from the combined dataset. In the SVM model, area under the curve (AUC) values of 0.64 for T2W, 0.86 for ADC, and 0.86 for the combined dataset were obtained in the test set. In the LR model, AUC values of 0.79 for T2W, 0.86 for ADC, and 0.85 for the combined dataset were obtained. Machine learning models developed with radiomics can provide a decision support system to complement pathology results and help avoid invasive procedures such as re-biopsies or follow-up biopsies that are sometimes necessary today. This study demonstrates that machine learning models using radiomics features derived from bi-parametric MRI can discriminate csPCa from clinically insignificant PCa. These findings suggest that radiomics-based machine learning models have the potential to reduce the need for re-biopsy in cases of indeterminate pathology, assist in diagnosing pathology–radiology discordance, and support treatment decision-making in the management of PCa.

Idiopathic inflammatory myopathies (IIM) are a group of autoimmune rheumatic diseases characterized by proximal muscle weakness and extra muscular manifestations. Since 1975, these IIM have been classified into different clinical phenotypes. Each clinical phenotype is associated with a better or worse prognosis and a particular physiopathology. Machine learning (ML) is a fascinating field of knowledge with worldwide applications in different fields. In IIM, ML is an emerging tool assessed in very specific clinical contexts as a complementary tool for research purposes, including transcriptome profiles in muscle biopsies, differential diagnosis using magnetic resonance imaging (MRI), and ultrasound (US). With the cancer-associated risk and predisposing factors for interstitial lung disease (ILD) development, this systematic review evaluates 23 original studies using supervised learning models, including logistic regression (LR), random forest (RF), support vector machines (SVM), and convolutional neural networks (CNN), with performance assessed primarily through the area under the curve coupled with the receiver operating characteristic (AUC-ROC).

With the ongoing revolution of artificial intelligence (AI) in medicine, the impact of AI in radiology is more pronounced than ever. An increasing number of technical and clinical AI-focused studies are published each day. As these tools inevitably affect patient care and physician practices, it is crucial that radiologists become more familiar with the leading strategies and underlying principles of AI. Multimodal AI models can combine both imaging and clinical metadata and are quickly becoming a popular approach that is being integrated into the medical ecosystem. This narrative review covers major concepts of multimodal AI through the lens of recent literature. We discuss emerging frameworks, including graph neural networks, which allow for explicit learning from non-Euclidean relationships, and transformers, which allow for parallel computation that scales, highlighting existing literature and advocating for a focus on emerging architectures. We also identify key pitfalls in current studies, including issues with taxonomy, data scarcity, and bias. By informing radiologists and biomedical AI experts about existing practices and challenges, we hope to guide the next wave of imaging-based multimodal AI research.

Low-dose computed tomography (LDCT) reduces radiation exposure but often degrades image quality, potentially compromising diagnostic accuracy. Existing deep learning-based denoising methods focus primarily on pixel-level mappings, overlooking the potential benefits of high-level semantic guidance. Recent advances in vision-language models (VLMs) suggest that language can serve as a powerful tool for capturing structured semantic information, offering new opportunities to improve LDCT reconstruction. In this paper, we introduce LangMamba, a Language-driven Mamba framework for LDCT denoising that leverages VLM-derived representations to enhance supervision from normal-dose CT (NDCT). LangMamba follows a two-stage learning strategy. First, we pre-train a Language-guided AutoEncoder (LangAE) that leverages frozen VLMs to map NDCT images into a semantic space enriched with anatomical information. Second, we synergize LangAE with two key components to guide LDCT denoising: Semantic-Enhanced Efficient Denoiser (SEED), which enhances NDCT-relevant local semantic while capturing global features with efficient Mamba mechanism, and Language-engaged Dual-space Alignment (LangDA) Loss, which ensures that denoised images align with NDCT in both perceptual and semantic spaces. Extensive experiments on two public datasets demonstrate that LangMamba outperforms conventional state-of-the-art methods, significantly improving detail preservation and visual fidelity. Remarkably, LangAE exhibits strong generalizability to unseen datasets, thereby reducing training costs. Furthermore, LangDA loss improves explainability by integrating language-guided insights into image reconstruction and offers a plug-and-play fashion. Our findings shed new light on the potential of language as a supervisory signal to advance LDCT denoising. The code is publicly available on https://github.com/hao1635/LangMamba.

Aims: To develop a deep-learning (DL) framework that will allow fully automated longitudinal and circumferential co-registration of intravascular ultrasound (IVUS) and optical coherence tomography (OCT) images. Methods and results: Data from 230 patients (714 vessels) with acute coronary syndrome that underwent near-infrared spectroscopy (NIRS)-IVUS and OCT imaging in their non-culprit vessels were included in the present analysis. The lumen borders annotated by expert analysts in 61,655 NIRS-IVUS and 62,334 OCT frames, and the side branches and calcific tissue identified in 10,000 NIRS-IVUS frames and 10,000 OCT frames, were used to train DL solutions for the automated extraction of these features. The trained DL solutions were used to process NIRS-IVUS and OCT images and their output was used by a dynamic time warping algorithm to co-register longitudinally the NIRS-IVUS and OCT images, while the circumferential registration of the IVUS and OCT was optimized through dynamic programming. On a test set of 77 vessels from 22 patients, the DL method showed high concordance with the expert analysts for the longitudinal and circumferential co-registration of the two imaging sets (concordance correlation coefficient >0.99 for the longitudinal and >0.90 for the circumferential co-registration). The Williams Index was 0.96 for longitudinal and 0.97 for circumferential co-registration, indicating a comparable performance to the analysts. The time needed for the DL pipeline to process imaging data from a vessel was <90s. Conclusion: The fully automated, DL-based framework introduced in this study for the co-registration of IVUS and OCT is fast and provides estimations that compare favorably to the expert analysts. These features renders it useful in research in the analysis of large-scale data collected in studies that incorporate multimodality imaging to characterize plaque composition.

The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with real-world variations in medical imaging. Minor shifts in scanner hardware, lighting or demographics can erode accuracy, but currently reliability auditing to identify such catastrophic failure cases before deployment is a bespoke and time-consuming process. Practitioners lack accessible and interpretable tools to expose and repair hidden failure modes. Here we introduce ModelAuditor, a self-reflective agent that converses with users, selects task-specific metrics, and simulates context-dependent, clinically relevant distribution shifts. ModelAuditor then generates interpretable reports explaining how much performance likely degrades during deployment, discussing specific likely failure modes and identifying root causes and mitigation strategies. Our comprehensive evaluation across three real-world clinical scenarios - inter-institutional variation in histopathology, demographic shifts in dermatology, and equipment heterogeneity in chest radiography - demonstrates that ModelAuditor is able correctly identify context-specific failure modes of state-of-the-art models such as the established SIIM-ISIC melanoma classifier. Its targeted recommendations recover 15-25% of performance lost under real-world distribution shift, substantially outperforming both baseline models and state-of-the-art augmentation methods. These improvements are achieved through a multi-agent architecture and execute on consumer hardware in under 10 minutes, costing less than US$0.50 per audit.

Manual annotation of medical images is a labor-intensive and time-consuming process, posing a significant bottleneck in the development and deployment of robust medical imaging AI systems. This paper introduces a novel Human-AI collaborative framework for medical image segmentation that substantially reduces the annotation burden by eliminating the need for explicit manual pixel-level labeling. The core innovation lies in a preference learning paradigm, where human experts provide minimal, intuitive feedback -- simply indicating whether an AI-generated segmentation is better or worse than a previous version. The framework comprises four key components: (1) an adaptable foundation model (FM) for feature extraction, (2) label propagation based on feature similarity, (3) a clicking agent that learns from human better-or-worse feedback to decide where to click and with which label, and (4) a multi-round segmentation learning procedure that trains a state-of-the-art segmentation network using pseudo-labels generated by the clicking agent and FM-based label propagation. Experiments on three public datasets demonstrate that the proposed approach achieves competitive segmentation performance using only binary preference feedback, without requiring experts to directly manually annotate the images.

Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas. This broad definition of brain lesions includes areas of the brain that are irreversibly damaged, as well as areas of brain tissue that are deformed as a result of lesion growth or swelling. Despite the importance of differentiating between damaged and deformed tissue, existing lesion segmentation methods overlook this distinction, labeling both of them as a single anomaly. In this work, we introduce a diffusion model-based framework for analyzing and reversing the brain lesion process. Our pipeline first segments abnormal regions in the brain, then estimates and reverses tissue deformations by restoring displaced tissue to its original position, isolating the core lesion area representing the initial damage. Finally, we inpaint the core lesion area to arrive at an estimation of the pre-lesion healthy brain. This proposed framework reverses a forward lesion growth process model that is well-established in biomechanical studies that model brain lesions. Our results demonstrate improved accuracy in lesion segmentation, characterization, and brain labeling compared to traditional methods, offering a robust tool for clinical and research applications in brain lesion analysis. Since pre-lesion healthy versions of abnormal brains are not available in any public dataset for validation of the reverse process, we simulate a forward model to synthesize multiple lesioned brain images.