This episode explores a study from the University of Texas Southwestern Medical Center and MD Anderson Cancer Center in the United States that clinically validates an FDA-cleared AI tool for measuring total cardiac volume on non-contrast, non-gated chest CT. Across 307 patients with paired echocardiography, the AI discriminated normal from abnormal cardiac volume with an AUC of 0.81 in men and 0.77 in women, and far outperformed routine radiologist sensitivity for cardiomegaly. The tool offers a tunable, reproducible opportunistic screening layer on chest CT's already being performed.

Radiology Advances, 2026, 3, umag013. Fan et al.

This episode explores a study from the Emory Sports Performance and Research Center and the University of Lausanne that determined how few annotated MRI exams are needed to train a reliable deep learning model for thigh muscle segmentation. Using the nnU-Net framework with incrementally larger training sets, the researchers found that just 20 high-quality annotated subjects produced clinically acceptable segmentation across 14 thigh muscles, with biomarker agreement virtually indistinguishable from expert manual segmentation. All tools and trained models have been made openly available.

Optimizing MRI annotation workflows for high-accuracy deep learning thigh muscle segmentation in athletes. Slutsky-Ganesh et al. Radiology Advances, 2026, 3, umag005

This episode discusses a study from UCLA in the United States that used federated learning to train a deep learning model for automatic segmentation and quantification of visceral and subcutaneous abdominal fat in children using free-breathing 3D MRI. By leveraging a larger adult dataset alongside a small pediatric cohort, the model achieved strong agreement with expert manual segmentation in under three seconds per patient.

Cross-cohort federated learning for pediatric abdominal adipose tissue segmentation and quantification using free-breathing 3D MRI. Zhang et al. Radiology Advances, 2026, 3, umag002

This episode reviews a proof-of-concept study from Mayo Clinic Minnesota on the use of ferumoxytol-enhanced MRI for detecting gastrointestinal bleeding after a comprehensive conventional workup has been negative. We examine how this blood pool agent's prolonged intravascular half-life addresses the diagnostic challenge of slow and intermittent GI bleeding, and discuss the clinical implications for patient management.

Feasibility of ferumoxytol-enhanced MRI for detection of gastrointestinal bleeding when conventional evaluation is negative. Wells et al. Radiology Advances, 2026, 3, umaf043.

This episode reviews a study from the ROADMAP Group evaluating deep reinforcement learning for automatic aortic landmark localization in Stanford Type B aortic dissection — examining whether AI can match expert human performance for a task critical to treatment planning and long-term surveillance.

Deep reinforcement learning for automatic anatomic CT landmark localization in Stanford Type B aortic dissection. Baeumler et al. Radiology Advances, 2026, 3, umag006.

This episode explores a technological advance from Johns Hopkins in the United States that improves diagnostic ultrasound for breast masses. By combining short-lag spatial coherence imaging with an objective metric called generalized contrast-to-noise ratio, the researchers achieved a dramatic boost in diagnostic accuracy—especially in dense breast tissue—while reducing variability among radiologists and avoiding misclassification of cancers.

Generalized contrast-to-noise ratio applied to short-lag
spatial coherence ultrasound differentiates breast cysts
from solid masses. Sharma et al. Radiology Advances, 2025, 2(6), umaf037.

This episode highlights a study from Korea using deep learning to generate synthetic contrast-enhanced brain MRI images—without injecting contrast agents. The model accurately segmented the choroid plexus and matched real contrast-enhanced scans in volume analysis, offering a potentially safer, scalable tool for neuroimaging.

Automated synthetic contrast-enhanced MRI improves
choroid plexus segmentation in Parkinsonian syndromes. Ambaye et al. Radiology Advances, 2025, 2(6), umaf042

This episode explores a study from Radiology Advances tackling one of AI's toughest challenges in medical imaging: consistent pancreas segmentation across CT scans. The authors benchmarked multiple models against multi-reader human consensus and introduced a new metric, Fractional Threshold (FT), to measure robustness. Their human-in-the-loop workflow flagged just 5% of cases for expert review, matching human reliability while cutting annotation time 23-fold.
Benchmarking Robustness of Automated CT Pancreas Segmentation: Achieving Human-Level Reliability Through Human-in-the-Loop Optimization. Oviedo et al. Radiology Advances, Volume 2, Issue 6, November 2025, umaf040,