Purpose: Radiation pneumonitis (RP) is a serious complication of intensity-modulated radiation therapy (IMRT) for breast cancer patients, underscoring the need for precise and explainable predictive models. This study presents an Explainable Dual-Omics Filtering (EDOF) model that integrates spatially localized dosiomic and radiomic features for voxel-level RP prediction. Methods: A retrospective cohort of 72 breast cancer patients treated with IMRT was analyzed, including 28 who developed RP. The EDOF model consists of two components: (1) dosiomic filtering, which extracts local dose intensity and spatial distribution features from planning dose maps, and (2) radiomic filtering, which captures texture-based features from pre-treatment CT scans. These features are jointly analyzed using the Explainable Boosting Machine (EBM), a transparent machine learning model that enables feature-specific risk evaluation. Model performance was assessed using five-fold cross-validation, reporting area under the curve (AUC), sensitivity, and specificity. Feature importance was quantified by mean absolute scores, and Partial Dependence Plots (PDPs) were used to visualize nonlinear relationships between RP risk and dual-omic features. Results: The EDOF model achieved strong predictive performance (AUC = 0.95 +- 0.01; sensitivity = 0.81 +- 0.05). The most influential features included dosiomic Intensity Mean, dosiomic Intensity Mean Absolute Deviation, and radiomic SRLGLE. PDPs revealed that RP risk increases beyond 5 Gy and rises sharply between 10-30 Gy, consistent with clinical dose thresholds. SRLGLE also captured structural heterogeneity linked to RP in specific lung regions. Conclusion: The EDOF framework enables spatially resolved, explainable RP prediction and may support personalized radiation planning to mitigate pulmonary toxicity.

In this intercontinental, confirmatory study, we include a retrospective cohort of 22,481 MRI examinations (21,288 patients; 46 cities in 22 countries) to train and externally validate the PI-CAI-2B model, i.e., an efficient, next-generation iteration of the state-of-the-art AI system that was developed for detecting Gleason grade group $\geq$2 prostate cancer on MRI during the PI-CAI study. Of these examinations, 20,471 cases (19,278 patients; 26 cities in 14 countries) from two EU Horizon projects (ProCAncer-I, COMFORT) and 12 independent centers based in Europe, North America, Asia and Africa, are used for training and internal testing. Additionally, 2010 cases (2010 patients; 20 external cities in 12 countries) from population-based screening (STHLM3-MRI, IP1-PROSTAGRAM trials) and primary diagnostic settings (PRIME trial) based in Europe, North and South Americas, Asia and Australia, are used for external testing. Primary endpoint is the proportion of AI-based assessments in agreement with the standard of care diagnoses (i.e., clinical assessments made by expert uropathologists on histopathology, if available, or at least two expert urogenital radiologists in consensus; with access to patient history and peer consultation) in the detection of Gleason grade group $\geq$2 prostate cancer within the external testing cohorts. Our statistical analysis plan is prespecified with a hypothesis of diagnostic interchangeability to the standard of care at the PI-RADS $\geq$3 (primary diagnosis) or $\geq$4 (screening) cut-off, considering an absolute margin of 0.05 and reader estimates derived from the PI-CAI observer study (62 radiologists reading 400 cases). Secondary measures comprise the area under the receiver operating characteristic curve (AUROC) of the AI system stratified by imaging quality, patient age and patient ethnicity to identify underlying biases (if any).

Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misinterpretation. We performed the first large-scale, systematic comparison of XAI methods on ~45,000 structural brain MRIs using a novel XAI validation framework. This framework establishes verifiable ground truth by constructing prediction tasks with known signal sources - from localized anatomical features to subject-specific clinical lesions - without artificially altering input images. Our analysis reveals systematic failures in two of the most widely used methods: GradCAM consistently failed to localize predictive features, while Layer-wise Relevance Propagation generated extensive, artifactual explanations that suggest incompatibility with neuroimaging data characteristics. Our results indicate that these failures stem from a domain mismatch, where methods with design principles tailored to natural images require substantial adaptation for neuroimaging data. In contrast, the simpler, gradient-based method SmoothGrad, which makes fewer assumptions about data structure, proved consistently accurate, suggesting its conceptual simplicity makes it more robust to this domain shift. These findings highlight the need for domain-specific adaptation and validation of XAI methods, suggest that interpretations from prior neuroimaging studies using standard XAI methodology warrant re-evaluation, and provide urgent guidance for practical application of XAI in neuroimaging.

This Perspective article explores the transformative role of artificial intelligence (AI) in predicting perioperative hypoxemia through the integration of deep learning (DL) with multimodal clinical data, including lung imaging, pulmonary function tests (PFTs), and arterial blood gas (ABG) analysis. Perioperative hypoxemia, defined as arterial oxygen partial pressure (PaO₂) <60 mmHg or oxygen saturation (SpO₂) <90%, poses significant risks of delayed recovery and organ dysfunction. Traditional diagnostic methods, such as radiological imaging and ABG analysis, often lack integrated predictive accuracy. AI frameworks, particularly convolutional neural networks (CNNs) and hybrid models like TD-CNNLSTM-LungNet, demonstrate exceptional performance in detecting pulmonary inflammation and stratifying hypoxemia risk, achieving up to 96.57% accuracy in pneumonia subtype differentiation and an AUC of 0.96 for postoperative hypoxemia prediction. Multimodal AI systems, such as DeepLung-Predict, unify CT scans, PFTs, and ABG parameters to enhance predictive precision, surpassing conventional methods by 22%. However, challenges persist, including dataset heterogeneity, model interpretability, and clinical workflow integration. Future directions emphasize multicenter validation, explainable AI (XAI) frameworks, and pragmatic trials to ensure equitable and reliable deployment. This AI-driven approach not only optimizes resource allocation but also mitigates financial burdens on healthcare systems by enabling early interventions and reducing ICU admission risks.

This article provides radiologists with practical recommendations for evaluating AI performance in radiology, ensuring alignment with clinical goals and patient safety. It outlines key performance metrics, including overlap metrics for segmentation, test-based metrics (e.g., sensitivity, specificity, and area under the receiver operating characteristic curve), and outcome-based metrics (e.g., precision, negative predictive value, F1-score, Matthews correlation coefficient, and area under the precision-recall curve). Key recommendations emphasize local validation using independent datasets, selecting task-specific metrics, and considering deployment context to ensure real-world performance matches claimed efficacy. Common pitfalls, such as overreliance on a single metric, misinterpretation in low-prevalence settings, and failure to account for clinical workflow, are addressed with mitigation strategies. Additional guidance is provided on threshold selection, prevalence-adjusted evaluation, and AI-generated image quality assessment. This guide equips radiologists to critically evaluate both commercially available and in-house developed AI tools, ensuring their safe and effective integration into clinical practice. CLINICAL RELEVANCE STATEMENT: This review provides guidance on selecting and interpreting AI performance metrics in radiology, ensuring clinically meaningful evaluation and safe deployment of AI tools. By addressing common pitfalls and promoting standardized reporting, it supports radiologists in making informed decisions, ultimately improving diagnostic accuracy and patient outcomes. KEY POINTS: Radiologists must evaluate performance metrics as they reflect acceptable performance in specific datasets but do not guarantee clinical utility. Independent evaluation tailored to the clinical setting is essential. Performance metrics must align with the intended task of the AI application-segmentation, detection, or classification-and be selected based on domain knowledge and clinical context. Sensitivity, specificity, area under the ROC curve, and accuracy must be interpreted with prevalence-dependent metrics (e.g., precision, F1 score, and Matthew's correlation coefficient) calculated for the target population to ensure safe and effective clinical use.

Distal myopathy represents a genetically heterogeneous group of skeletal muscle disorders with broad clinical manifestations, posing diagnostic challenges in radiology. To address this, we propose a novel multimodal attention-aware fusion architecture that combines features extracted from two distinct deep learning models, one capturing global contextual information and the other focusing on local details, representing complementary aspects of the input data. Uniquely, our approach integrates these features through an attention gate mechanism, enhancing both predictive performance and interpretability. Our method achieves a high classification accuracy on the BUSI benchmark and a proprietary distal myopathy dataset, while also generating clinically relevant saliency maps that support transparent decision-making in medical diagnosis. We rigorously evaluated interpretability through (1) functionally grounded metrics, coherence scoring against reference masks and incremental deletion analysis, and (2) application-grounded validation with seven expert radiologists. While our fusion strategy boosts predictive performance relative to single-stream and alternative fusion strategies, both quantitative and qualitative evaluations reveal persistent gaps in anatomical specificity and clinical usefulness of the interpretability. These findings highlight the need for richer, context-aware interpretability methods and human-in-the-loop feedback to meet clinicians' expectations in real-world diagnostic settings.

Osteoporosis (OP), a systemic skeletal disease characterized by compromised bone strength and elevated fracture susceptibility, represents a growing global health challenge that necessitates early detection and accurate risk stratification. With the exponential growth of multidimensional biomedical data in OP research, feature selection has become an indispensable machine learning paradigm that improves model generalizability. At the same time, it preserves clinical interpretability and enhances predictive accuracy. This perspective article systematically reviews the transformative role of feature selection methodologies across three critical domains of OP investigation: 1) multi-omics biomarker identification, 2) diagnostic pattern recognition, and 3) fracture risk prognostication. In biomarker discovery, advanced feature selection algorithms systematically refine high-dimensional multi-omics datasets (genomic, proteomic, metabolomic) to isolate key molecular signatures correlated with bone mineral density (BMD) trajectories and microarchitectural deterioration. For clinical diagnostics, these techniques enable efficient extraction of discriminative pattern from multimodal imaging data, including dual-energy X-ray absorptiometry (DXA), quantitative computed tomography (CT), and emerging dental radiographic biomarkers. In prognostic modeling, strategic variable selection optimizes prognostic accuracy by integrating demographic, biochemical, and biomechanical predictors while migrating overfitting in heterogeneous patient cohorts. Current challenges include heterogeneity in dataset quality and dimensionality, translational gaps between algorithmic outputs and clinical decision parameters, and limited reproducibility across diverse populations. Future directions should prioritize the development of adaptive feature selection frameworks capable of dynamic multi-omics data integration, coupled with hybrid intelligence systems that synergize machine-derived biomarkers with clinician expertise. Addressing these challenges requires coordinated interdisciplinary efforts to establish standardized validation protocols and create clinician-friendly decision support interfaces, ultimately bridging the gap between computational OP research and personalized patient care.

Recent advancements in large language models (LLMs) have led to multimodal LLMs (MLLMs), which integrate multiple data modalities beyond text. Although MLLMs show promise, there is a gap in the literature that empirically demonstrates their impact in healthcare. This paper summarizes the applications of MLLMs in healthcare, highlighting their potential to transform health practices. A rapid literature review was conducted in August 2024 using World Health Organization (WHO) rapid-review methodology and PRISMA standards, with searches across four databases (Scopus, Medline, PubMed and ACM Digital Library) and top-tier conferences-including NeurIPS, ICML, AAAI, MICCAI, CVPR, ACL and EMNLP. Articles on MLLMs healthcare applications were included for analysis based on inclusion and exclusion criteria. The search yielded 115 articles, 39 included in the final analysis. Of these, 77% appeared online (preprints and published) in 2024, reflecting the emergence of MLLMs. 80% of studies were from Asia and North America (mainly China and US), with Europe lagging. Studies split evenly between pre-built MLLMs evaluations (60% focused on GPT versions) and custom MLLMs/frameworks development with task-specific customizations. About 81% of studies examined MLLMs for diagnosis and reporting in radiology, pathology, and ophthalmology, with additional applications in education, surgery, and mental health. Prompting strategies, used in 80% of studies, improved performance in nearly half. However, evaluation practices were inconsistent with 67% reported accuracy. Error analysis was mostly anecdotal, with only 18% categorized failure types. Only 13% validated explainability through clinician feedback. Clinical deployment was demonstrated in just 3% of studies, and workflow integration, governance, and safety were rarely addressed. MLLMs offer substantial potential for healthcare transformation through multimodal data integration. Yet, methodological inconsistencies, limited validation, and underdeveloped deployment strategies highlight the need for standardized evaluation metrics, structured error analysis, and human-centered design to support safe, scalable, and trustworthy clinical adoption.

To explore the potential role of generative artificial intelligence (GenAI) in enhancing patient counseling following prenatal ultrasound diagnosis of fetal malformations, with an emphasis on clinical utility, patient comprehension, and ethical implementation. The detection of fetal anomalies during the mid-trimester ultrasound is emotionally distressing for patients and presents significant challenges in communication and decision-making. Generative AI tools, such as GPT-4 and similar models, offer novel opportunities to support clinicians in delivering accurate, empathetic, and accessible counseling while preserving the physician's central role. We present a narrative review and applied framework illustrating how GenAI can assist obstetricians before, during, and after the fetal anomaly scan. Use cases include lay summaries, visual aids, anticipatory guidance, multilingual translation, and emotional support. Tables and sample prompts demonstrate practical applications across a range of anomalies.

BackgroundConvolutional neural networks (CNNs) have emerged to reduce clinical resources and standardize auto-contouring of organs-at-risk (OARs). Although CNNs perform adequately for most patients, understanding when the CNN might fail is critical for effective and safe clinical deployment. However, the limitations of CNNs are poorly understood because of their black-box nature. Explainable artificial intelligence (XAI) can expose CNNs inner mechanisms for classification. Here, we investigate the inner mechanisms of CNNs for segmentation and explore a novel, computational approach to a-priori flag potentially insufficient parotid gland (PG) contours. MethodsFirst, 3D UNets were trained in three PG segmentation situations using (1) synthetic cases; (2) 1925 clinical computed tomography (CT) scans with typical and (3) more consistent contours curated through a previously validated auto-curation step. Then, we generated attribution maps for seven XAI methods, and qualitatively assessed them for congruency between simulated and clinical contours, and how much XAI agreed with expert reasoning. To objectify observations, we explored persistent homology intensity filtrations to capture essential topological characteristics of XAI attributions. Principal component (PC) eigenvalues of Euler characteristic profiles were correlated with spatial agreement (Dice-Sorensen similarity coefficient; DSC). Evaluation was done using sensitivity, specificity and the area under receiver operating characteristic (AUROC) curve on an external AAPM dataset, where as proof-of-principle, we regard the lowest 15% DSC as insufficient. ResultsPatternNet attributions (PNet-A) focused on soft-tissue structures, whereas guided backpropagation (GBP) highlighted both soft-tissue and high-density structures (e.g. mandible bone), which was congruent with synthetic situations. Both methods typically had higher/denser activations in better auto-contoured medial and anterior lobes. Curated models produced "cleaner" gradient class-activation mapping (GCAM) attributions. Quantitative analysis showed that PC{lambda}1 of guided GCAMs (GGCAM) Euler characteristic (EC) profile had good predictive value (sensitivity>0.85, specificity>0.9) of DSC for AAPM cases, with AUROC=0.66, 0.74, 0.94, 0.83 for GBP, GCAM, GGCAM and PNet-A. For for {lambda}1<-1.8e3 of GGCAMs EC-profile, 87% of cases were insufficient. ConclusionsGBP and PNet-A qualitatively agreed most with expert reasoning on directly (structure borders) and indirectly (proxies used for identifying structure borders) important features for PG segmentation. Additionally, this work investigated as proof-of-principle how topological data analysis could possibly be used for quantitative XAI signal analysis to a-priori mark potentially inadequate CNN-segmentations, using only features from inside the predicted PG. This work used PG as a well-understood segmentation paradigm and may extend to target volumes and other organs-at-risk.