To explore the efficacy of a deep learning (DL) model in predicting perineural invasion (PNI) in prostate cancer (PCa) by conducting multiparametric MRI (mpMRI)-based tumor heterogeneity analysis. This retrospective study included 397 patients with PCa from two medical centers. The patients were divided into training, internal validation (in-vad), and independent external validation (ex-vad) cohorts (n = 173, 74, and 150, respectively). mpMRI-based habitat analysis, comprising T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient sequences, was performed followed by DL, deep feature selection, and filtration to compute a radscore. Subsequently, six models were constructed: one clinical model, four habitat models (habitats 1, 2, 3, and whole-tumor), and one combined model. Receiver operating characteristic curve analysis was performed to evaluate the models' ability to predict PNI. The four habitat models exhibited robust performance in predicting PNI, with area under the curve (AUC) values of 0.862-0.935, 0.802-0.957, and 0.859-0.939 in the training, in-vad, and ex-vad cohorts, respectively. The clinical model had AUC values of 0.832, 0.818, and 0.789 in the training, in-vad, and ex-vad cohorts, respectively. The combined model outperformed the clinical and habitat models, with AUC, sensitivity, and specificity values of 0.999, 1, and 0.955 for the training cohort. Decision curve analysis and clinical impact curve analysis indicated favorable clinical applicability and utility of the combined model. DL models constructed through mpMRI-based habitat analysis accurately predict the PNI status of PCa.

Brain tumors remain among the most lethal human diseases, where early detection and accurate classification are critical for effective diagnosis and treatment planning. Although deep learning-based computer-aided diagnostic (CADx) systems have shown remarkable progress. However, conventional convolutional neural networks (CNNs) and Transformers face persistent challenges, including high computational cost, sensitivity to minor contrast variations, structural heterogeneity, and texture inconsistencies in MRI data. Therefore, a novel hybrid framework, CE-RS-SBCIT, is introduced, integrating residual and spatial learning-based CNNs with transformer-driven modules. The proposed framework exploits local fine-grained and global contextual cues through four core innovations: (i) a smoothing and boundary-based CNN-integrated Transformer (SBCIT), (ii) tailored residual and spatial learning CNNs, (iii) a channel enhancement (CE) strategy, and (iv) a novel spatial attention mechanism. The developed SBCIT employs stem convolution and contextual interaction transformer blocks with systematic smoothing and boundary operations, enabling efficient global feature modeling. Moreover, Residual and spatial CNNs, enhanced by auxiliary transfer-learned feature maps, enrich the representation space, while the CE module amplifies discriminative channels and mitigates redundancy. Furthermore, the spatial attention mechanism selectively emphasizes subtle contrast and textural variations across tumor classes. Extensive evaluation on challenging MRI datasets from Kaggle and Figshare, encompassing glioma, meningioma, pituitary tumors, and healthy controls, demonstrates superior performance, achieving 98.30% accuracy, 98.08% sensitivity, 98.25% F1-score, and 98.43% precision.

The aim of this study was to develop machine learning (ML) models to explore the relationship between chronic pulmonary embolism (PE) burden and severe pulmonary hypertension (PH) in surgical chronic thromboembolic pulmonary hypertension (CTEPH). CTEPH patients with a preoperative CT pulmonary angiogram and pulmonary endarterectomy between 01/2017 and 06/2022 were included. A mean pulmonary artery pressure of > 50 mmHg was classified as severe. CTs were scored by a blinded radiologist who recorded chronic pulmonary embolism extent in detail, and measured the right ventricle (RV), left ventricle (LV), main pulmonary artery (PA) and ascending aorta (Ao) diameters. XGBoost models were developed to identify CTEPH feature importance and compared to a logistic regression model. There were 184 patients included; 54.9% were female, and 21.7% had severe PH. The average age was 57 ± 15 years. PE burden alone was not helpful in identifying severe PH. The RV/LV ratio logistic regression model performed well (AUC 0.76) with a cutoff of 1.4. A baseline ML model (Model 1) including only the RV, LV, Pa and Ao measures and their ratios yielded an average AUC of 0.66 ± 0.10. The addition of demographics and statistics summarizing the CT findings raised the AUC to 0.75 ± 0.08 (F1 score 0.41). While measures of PE burden had little bearing on PH severity independently, the RV/LV ratio, extent of disease in various segments, total webs observed, and patient demographics improved performance of machine learning models in identifying severe PH. Question Can machine learning methods applied to CT-based cardiac measurements and detailed maps of chronic thromboembolism type and distribution predict pulmonary hypertension (PH) severity? Findings The right-to-left ventricle (RV/LV) ratio was predictive of PH severity with an optimal cutoff of 1.4, and detailed accounts of chronic thromboembolic burden improved model performance. Clinical relevance The identification of a CT-based RV/LV ratio cutoff of 1.4 gives radiologists, clinicians, and patients a point of reference for chronic thromboembolic PH severity. Detailed chronic thromboembolic burden data are useful but cannot be used alone to predict PH severity.

Magnetic resonance imaging (MRI) is essential for diagnosing lumbar foraminal stenosis (LFS). However, access remains limited in China due to uneven equipment distribution, high costs, and long waiting times. Therefore, this study developed a lightweight deep learning (DL) model using sagittal CT images to classify LFS severity as a potential clinical alternative where MRI is unavailable. A retrospective study included 868 sagittal CT images from 177 patients (2016-2025). Data were split at the patient level into training (n = 125), validation (n = 31), and test sets (n = 21), with annotations, based on the Lee grading system, provided by two spine surgeons. Two DL models were developed: DL1 (EfficientNet-B0) and DL2 (MobileNetV3-Large-100), both of which incorporated a Faster R-CNN with a ResNet-50-based region-of-interest (ROI) detector. Diagnostic performance was benchmarked against spine surgeons with different levels of clinical experience. DL1 achieved 82.35% diagnostic accuracy (matching the senior spine surgeon's 83.33%), with DL2 at 80.39% (mean 81.37%), both exceeding the junior spine surgeon's 62.75%. DL1 demonstrated near-perfect diagnostic agreement with the senior spine surgeon, as validated by Cohen's kappa analysis (κ = 0.815; 95% CI: 0.723-0.907), whereas DL2 showed substantial consistency (κ = 0.799; 95% CI: 0.703-0.895). Inter-model agreement yielded κ = 0.782 (95% CI: 0.682-0.882). The DL models achieved a mean diagnostic accuracy of 81.37%, comparable to that of the senior spine surgeon (83.33%) in grading LFS severity on sagittal CT. However, given the limited sample size and absence of external validation, their applicability and generalisability to other populations and in multi-centre, large-scale datasets remain uncertain.

In this study, as a proof-of-concept, we aim to initiate the development of Radiology Foundation Model, termed as RadFM. We consider three perspectives: dataset construction, model design, and thorough evaluation, concluded as follows: (i), we contribute 4 multimodal datasets with 13M 2D images and 615K 3D scans. When combined with a vast collection of existing datasets, this forms our training dataset, termed as Medical Multi-modal Dataset, MedMD. (ii), we propose an architecture that enables to integrate text input with 2D or 3D medical scans, and generates responses for diverse radiologic tasks, including diagnosis, visual question answering, report generation, and rationale diagnosis; (iii), beyond evaluation on 9 existing datasets, we propose a new benchmark, RadBench, comprising three tasks aiming to assess foundation models comprehensively. We conduct both automatic and human evaluations on RadBench. RadFM outperforms former accessible multi-modal foundation models, including GPT-4V. Additionally, we adapt RadFM for diverse public benchmarks, surpassing various existing SOTAs.

Intracranial hypertension (IH) is a life-threatening complication that may occur after acute brain injury. Early recognition of IH allows prompt interventions that improve outcomes. Even if invasive intracranial monitoring is considered the gold standard for the most severely injured patients, scarce availability of resources, the need for advanced skills, and potential for complications often limit its utilization. On the other hand, different non-invasive methods to evaluate acutely brain-injured patients for elevated intracranial pressure have been investigated. Clinical examination and neuroradiology represent the cornerstone of a patient's evaluation in the intensive care unit (ICU). However, multimodal neuromonitoring, employing widely used different tools, such as brain ultrasound, automated pupillometry, and skull micro-deformation recordings, increase the possibility for continuous or semi-continuous intracranial pressure monitoring. Furthermore, artificial intelligence (AI) has been investigated to as a tool to predict elevated intracranial pressure, shedding light on new diagnostic and treatment horizons with the potential to improve patient outcomes. This narrative review, based on a systematic literature search, summarizes the best available evidence on the use of non-invasive monitoring tools and methods for the assessment of intracranial pressure.

To differentiate interstitial lung diseases (ILDs) with fibrotic and inflammatory patterns using high-resolution computed tomography (HRCT) and a radiomics-based artificial intelligence (AI) pipeline. This single-center study included 84 patients: 50 with idiopathic pulmonary fibrosis (IPF)-representative of fibrotic pattern-and 34 with cellular non-specific interstitial pneumonia (NSIP) secondary to connective tissue disease (CTD)-as an example of mostly inflammatory pattern. For a secondary objective, we analyzed 50 additional patients with COVID-19 pneumonia. We performed semi-automatic segmentation of ILD regions using a deep learning model followed by manual review. From each segmented region, 103 radiomic features were extracted. Classification was performed using an XGBoost model with 1000 bootstrap repetitions and SHapley Additive exPlanations (SHAP) were applied to identify the most predictive features. The model accurately distinguished a fibrotic ILD pattern from an inflammatory ILD one, achieving an average test set accuracy of 0.91 and AUROC of 0.98. The classification was driven by radiomic features capturing differences in lung morphology, intensity distribution, and textural heterogeneity between the two disease patterns. In differentiating cellular NSIP from COVID-19, the model achieved an average accuracy of 0.89. Inflammatory ILDs exhibited more uniform imaging patterns compared to the greater variability typically observed in viral pneumonia. Radiomics combined with explainable AI offers promising diagnostic support in distinguishing fibrotic from inflammatory ILD patterns and differentiating inflammatory ILDs from viral pneumonias. This approach could enhance diagnostic precision and provide quantitative support for personalized ILD management.

T1-weighted structural MRI has advanced our understanding of Parkinson's disease (PD), yet its diagnostic utility in clinical settings remains unclear. To assess the diagnostic performance of T1-weighted MRI gray matter (GM) metrics in distinguishing PD patients from healthy controls and to identify limitations affecting clinical applicability. A systematic review and meta-analysis were conducted on studies reporting sensitivity, specificity, or AUC for PD classification using T1-weighted MRI. Of 2906 screened records, 26 met inclusion criteria, and 10 provided sufficient data for quantitative synthesis. The risk of bias and heterogeneity were evaluated, and sensitivity analyses were performed by excluding influential studies. Pooled estimates showed a sensitivity of 0.71 (95 % CI: 0.70-0.72), specificity of 0.889 (95 % CI: 0.86-0.92), and overall accuracy of 0.909 (95 % CI: 0.89-0.93). These metrics improved after excluding outliers, reducing heterogeneity (I² = 95.7 %-0 %). Frequently reported regions showing structural alterations included the substantia nigra, striatum, thalamus, medial temporal cortex, and middle frontal gyrus. However, region-specific diagnostic metrics could not be consistently synthesized due to methodological variability. Machine learning approaches, particularly support vector machines and neural networks, showed enhanced performance with appropriate validation. T1-weighted MRI gray matter metrics demonstrate moderate accuracy in differentiating PD from controls but are not yet suitable as standalone diagnostic tools. Greater methodological standardization, external validation, and integration with clinical and biological data are needed to support precision neurology and clinical translation.

Achieving robust performance and fairness across diverse patient populations remains a challenge in developing clinically deployable deep learning models for diagnostic imaging. Synthetic data generation has emerged as a promising strategy to address limitations in dataset scale and diversity. We introduce RoentGen-v2, a text-to-image diffusion model for chest radiographs that enables fine-grained control over both radiographic findings and patient demographic attributes, including sex, age, and race/ethnicity. RoentGen-v2 is the first model to generate clinically plausible images with demographic conditioning, facilitating the creation of a large, demographically balanced synthetic dataset comprising over 565,000 images. We use this large synthetic dataset to evaluate optimal training pipelines for downstream disease classification models. In contrast to prior work that combines real and synthetic data naively, we propose an improved training strategy that leverages synthetic data for supervised pretraining, followed by fine-tuning on real data. Through extensive evaluation on over 137,000 chest radiographs from five institutions, we demonstrate that synthetic pretraining consistently improves model performance, generalization to out-of-distribution settings, and fairness across demographic subgroups. Across datasets, synthetic pretraining led to a 6.5% accuracy increase in the performance of downstream classification models, compared to a modest 2.7% increase when naively combining real and synthetic data. We observe this performance improvement simultaneously with the reduction of the underdiagnosis fairness gap by 19.3%. These results highlight the potential of synthetic imaging to advance equitable and generalizable medical deep learning under real-world data constraints. We open source our code, trained models, and synthetic dataset at https://github.com/StanfordMIMI/RoentGen-v2 .

The objective of this study was to identify risk factors for enema reduction failure and to establish a combined model that integrates deep learning (DL) features and clinical features for predicting surgical intervention in intussusception in children younger than 8 months of age. A retrospective study with a prospective validation cohort of intussusception. The retrospective data were collected from two hospitals in south east China between January 2017 and December 2022. The prospective data were collected between January 2023 and July 2024. A total of 415 intussusception cases in patients younger than 8 months were included in the study. 280 cases collected from Centre 1 were randomly divided into two groups at a 7:3 ratio: the training cohort (n=196) and the internal validation cohort (n=84). 85 cases collected from Centre 2 were designed as external validation cohort. Pretrained DL networks were used to extract deep transfer learning features, with least absolute shrinkage and selection operator regression selecting the non-zero coefficient features. The clinical features were screened by univariate and multivariate logistic regression analyses. We constructed a combined model that integrated the selected two types of features, along with individual clinical and DL models for comparison. Additionally, the combined model was validated in a prospective cohort (n=50) collected from Centre 1. In the internal and external validation cohorts, the combined model (area under curve (AUC): 0.911 and 0.871, respectively) demonstrated better performance for predicting surgical intervention in intussusception in children younger than 8 months of age than the clinical model (AUC: 0.776 and 0.740, respectively) and the DL model (AUC: 0.828 and 0.793, respectively). In the prospective validation cohort, the combined model also demonstrated impressive performance with an AUC of 0.890. The combined model, integrating DL and clinical features, demonstrated stable predictive accuracy, suggesting its potential for improving clinical therapeutic strategies for intussusception.