To evaluate the performance of large language models (LLMs) in automatically generating whole-organ MRI score (WORMS)-based structured MRI reports and predicting osteoarthritis (OA) severity for the knee. A total of 160 consecutive patients suspected of OA were included. Knee MRI reports were reviewed by three radiologists to establish the WORMS reference standard for 39 key features. GPT-4o and GPT-4o-mini were prompted using in-context knowledge (ICK) and chain-of-thought (COT) to generate WORMS-based structured reports from original reports and to automatically predict the OA severity. Four Orthopedic surgeons reviewed original and LLM-generated reports to conduct pairwise preference and difficulty tests, and their review times were recorded. GPT-4o demonstrated perfect performance in extracting the laterality of the knee (accuracy = 100%). GPT-4o outperformed GPT-4o mini in generating WORMS reports (Accuracy: 93.9% vs 76.2%, respectively). GPT-4o achieved higher recall (87.3% s 46.7%, p < 0.001), while maintaining higher precision compared to GPT-4o mini (94.2% vs 71.2%, p < 0.001). For predicting OA severity, GPT-4o outperformed GPT-4o mini across all prompt strategies (best accuracy: 98.1% vs 68.7%). Surgeons found it easier to extract information and gave more preference to LLM-generated reports over the original reports (both p < 0.001) while spending less time on each report (51.27 ± 9.41 vs 87.42 ± 20.26 s, p < 0.001). GPT-4o generated expert multi-feature, WORMS-based reports from original free-text knee MRI reports. GPT-4o with COT achieved high accuracy in categorizing OA severity. Surgeons reported greater preference and higher efficiency when using LLM-generated reports. The perfect performance of generating WORMS-based reports and the high efficiency and ease of use suggest that integrating LLMs into clinical workflows could greatly enhance productivity and alleviate the documentation burden faced by clinicians in knee OA. GPT-4o successfully generated WORMS-based knee MRI reports. GPT-4o with COT prompting achieved impressive accuracy in categorizing knee OA severity. Greater preference and higher efficiency were reported for LLM-generated reports.

Osteoporosis screening should be systematic in the group of over 50-year-old females with a radius fracture. We tested a phantom combined with machine learning model and studied osteoporosis-related variables. This machine learning model for screening osteoporosis using plain radiographs requires further investigation in larger cohorts to assess its potential as a replacement for DXA measurements in settings where DXA is not available. The main purpose of this study was to improve osteoporosis screening, especially in post-menopausal patients with fragility wrist fractures. The secondary objective was to increase understanding of the connection between osteoporosis and aging, as well as other risk factors. We collected data on 83 females > 50 years old with a distal radius fracture treated at Oulu University Hospital in 2019-2020. The data included basic patient information, WHO FRAX tool, blood tests, X-ray imaging of the fractured wrist, and DXA scanning of the non-fractured forearm, both hips, and the lumbar spine. Machine learning was used in combination with a custom phantom. Eighty-five percent of the study population had osteopenia or osteoporosis. Only 28.4% of patients had increased bone resorption activity measured by ICTP values. Total radius BMD correlated with other osteoporosis-related variables (age r =  - 0.494, BMI r = 0.273, FRAX osteoporotic fracture risk r =  - 0.419, FRAX hip fracture risk r =  - 0.433, hip BMD r = 0.435, and lumbar spine BMD r = 0.645), but the ultra distal (UD) radius BMD did not. Our custom phantom combined with a machine learning model showed potential for screening osteoporosis, with the class-wise accuracies for "Osteoporotic vs. osteopenic & normal bone" of 76% and 75%, respectively. We suggest osteoporosis screening for all females over 50 years old with wrist fractures. We found that the total radius BMD correlates with the central BMD. Due to the limited sample size in the phantom and machine learning parts of the study, further research is needed to make a clinically useful tool for screening osteoporosis.

<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> Artificial Intelligence (AI) has demonstrated strong potential in automating medical imaging tasks, with potential applications across disease diagnosis, prognosis, treatment planning, and posttreatment surveillance. However, privacy concerns surrounding patient data remain a major barrier to the widespread adoption of AI in clinical practice, as large and diverse training datasets are essential for developing accurate, robust, and generalizable AI models. Federated Learning offers a privacy-preserving solution by enabling collaborative model training across institutions without sharing sensitive data. Instead, model parameters, such as model weights, are exchanged between participating sites. Despite its potential, federated learning is still in its early stages of development and faces several challenges. Notably, sensitive information can still be inferred from the shared model parameters. Additionally, postdeployment data distribution shifts can degrade model performance, making uncertainty quantification essential. In federated learning, this task is particularly challenging due to data heterogeneity across participating sites. This review provides a comprehensive overview of federated learning, privacy-preserving federated learning, and uncertainty quantification in federated learning. Key limitations in current methodologies are identified, and future research directions are proposed to enhance data privacy and trustworthiness in medical imaging applications. ©RSNA, 2025.

Urodynamic studies (UDS) are essential for evaluating lower urinary tract function but are limited by patient discomfort, lack of standardization and diagnostic variability. Advances in technology aim to address these challenges and improve diagnostic accuracy and patient comfort. AUM offers physiological assessment by allowing natural bladder filling and monitoring during daily activities. Compared to conventional UDS, AUM demonstrates higher sensitivity for detecting detrusor overactivity and underlying pathophysiology. However, it faces challenges like motion artifacts, catheter-related discomfort, and difficulty measuring continuous bladder volume. Emerging devices such as Urodynamics Monitor and UroSound offer more patient-friendly alternatives. These tools have the potential to improve diagnostic accuracy for bladder pressure and voiding metrics but remain limited and still require further validation and testing. Ultrasound-based modalities, including dynamic ultrasonography and shear wave elastography, provide real-time, noninvasive assessment of bladder structure and function. These modalities are promising but will require further development of standardized protocols. AI and machine learning models enhance diagnostic accuracy and reduce variability in UDS interpretation. Applications include detecting detrusor overactivity and distinguishing bladder outlet obstruction from detrusor underactivity. However, further validation is required for clinical adoption. Advances in AUM, wearable technologies, ultrasonography, and AI demonstrate potential for transforming UDS into a more accurate, patient-centered tool. Despite significant progress, challenges like technical complexity, standardization, and cost-effectiveness must be addressed to integrate these innovations into routine practice. Nonetheless, these technologies provide the possibility of a future of improved diagnosis and treatment of lower urinary tract dysfunction.

Bone fracture risk assessment for osteoporotic patients is essential for implementing early countermeasures and preventing discomfort and hospitalization. Current methodologies, such as Fracture Risk Assessment Tool (FRAX), provide a risk assessment over a 5- to 10-year period rather than evaluating the bone's current health status. The database was collected by Ajou University Medical Center from 2017 to 2021. It included 9,260 patients, aged 55 to 99, comprising 242 femur fracture (FX) cases and 9,018 non-fracture (NFX) cases. To model the association of the bone's current health status with prevalent FXs, three prediction algorithms-extreme gradient boosting (XGB), support vector machine, and multilayer perceptron-were trained using two-dimensional dual-energy X-ray absorptiometry (2D-DXA) analysis results and subsequently benchmarked. The XGB classifier, which proved most effective, was then further refined using synthetic data generated by the adaptive synthetic oversampler to balance the FX and NFX classes and enhance boundary sharpness for better classification accuracy. The XGB model trained on raw data demonstrated good prediction capabilities, with an area under the curve (AUC) of 0.78 and an F1 score of 0.71 on test cases. The inclusion of synthetic data improved classification accuracy in terms of both specificity and sensitivity, resulting in an AUC of 0.99 and an F1 score of 0.98. The proposed methodology demonstrates that current bone health can be assessed through post-processed results from 2D-DXA analysis. Moreover, it was also shown that synthetic data can help stabilize uneven databases by balancing majority and minority classes, thereby significantly improving classification performance.

Lung cancer is a leading cause of cancer-related deaths globally, where early detection and accurate diagnosis are critical for improving survival rates. While deep learning, particularly convolutional neural networks (CNNs), has revolutionized medical image analysis by detecting subtle patterns indicative of early-stage lung cancer, its adoption faces challenges. These models are often computationally expensive and require significant resources, making them unsuitable for resource constrained environments. Additionally, their lack of transparency hinders trust and broader adoption in sensitive fields like healthcare. Knowledge distillation addresses these challenges by transferring knowledge from large, complex models (teachers) to smaller, lightweight models (students). We propose a knowledge distillation-based approach for lung cancer detection, incorporating explainable AI (XAI) techniques to enhance model transparency. Eight CNNs, including ResNet50, EfficientNetB0, EfficientNetB3, and VGG16, are evaluated as teacher models. We developed and trained a lightweight student model, Distilled Custom Student Network (DCSNet) using ResNet50 as the teacher. This approach not only ensures high diagnostic performance in resource-constrained settings but also addresses transparency concerns, facilitating the adoption of AI-driven diagnostic tools in healthcare.

Cardiac image segmentation is an important step in many cardiac image analysis and modeling tasks such as motion tracking or simulations of cardiac mechanics. While deep learning has greatly advanced segmentation in clinical settings, there is limited work on pre-clinical imaging, notably in porcine models, which are often used due to their anatomical and physiological similarity to humans. However, differences between species create a domain shift that complicates direct model transfer from human to pig data. Recently, foundation models trained on large human datasets have shown promise for robust medical image segmentation; yet their applicability to porcine data remains largely unexplored. In this work, we investigate whether foundation models can generate sufficiently accurate pseudo-labels for pig cardiac CT and propose a simple self-training approach to iteratively refine these labels. Our method requires no manually annotated pig data, relying instead on iterative updates to improve segmentation quality. We demonstrate that this self-training process not only enhances segmentation accuracy but also smooths out temporal inconsistencies across consecutive frames. Although our results are encouraging, there remains room for improvement, for example by incorporating more sophisticated self-training strategies and by exploring additional foundation models and other cardiac imaging technologies.

Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.

In neuroimaging research, the utilization of multi-centric analyses is crucial for obtaining sufficient sample sizes and representative clinical populations. Data harmonization techniques are typically part of the pipeline in multi-centric studies to address systematic biases and ensure the comparability of the data. However, most multi-centric studies require centralized data, which may result in exposing individual patient information. This poses a significant challenge in data governance, leading to the implementation of regulations such as the GDPR and the CCPA, which attempt to address these concerns but also hinder data access for researchers. Federated learning offers a privacy-preserving alternative approach in machine learning, enabling models to be collaboratively trained on decentralized data without the need for data centralization or sharing. In this paper, we present Fed-ComBat, a federated framework for batch effect harmonization on decentralized data. Fed-ComBat extends existing centralized linear methods, such as ComBat and distributed as d-ComBat, and nonlinear approaches like ComBat-GAM in accounting for potentially nonlinear and multivariate covariate effects. By doing so, Fed-ComBat enables the preservation of nonlinear covariate effects without requiring centralization of data and without prior knowledge of which variables should be considered nonlinear or their interactions, differentiating it from ComBat-GAM. We assessed Fed-ComBat and existing approaches on simulated data and multiple cohorts comprising healthy controls (CN) and subjects with various disorders such as Parkinson's disease (PD), Alzheimer's disease (AD), and autism spectrum disorder (ASD). The results of our study show that Fed-ComBat performs better than centralized ComBat when dealing with nonlinear effects and is on par with centralized methods like ComBat-GAM. Through experiments using synthetic data, Fed-ComBat demonstrates a superior ability to reconstruct the target unbiased function, achieving a 35% improvement (RMSE=0.5952) compared to d-ComBat (RMSE=0.9162) and a 12% improvement compared to our proposal to federate ComBat-GAM, d-ComBat-GAM (RMSE=0.6751). Additionally, Fed-ComBat achieves comparable results to centralized methods like ComBat-GAM for MRI-derived phenotypes without requiring prior knowledge of potential nonlinearities.

Stereotactic radiosurgery (SRS) is a non-invasive technique that is transforming the management of benign intracranial lesions through its precision and preservation of healthy tissues. It is effective for meningiomas, trigeminal neuralgia (TN), pituitary adenomas, vestibular schwannomas, and arteriovenous malformations. SRS ensures high tumor control rates, particularly for Grade I meningiomas and vestibular schwannomas. For refractory TN, it provides initial pain relief > 80 %. The advent of technologies such as PET-MRI, hypofractionation, and artificial intelligence is further improving treatment precision, but challenges remain, including the management of late side effects and standardization of practice.