A Multisociety Syllabus for AI in Radiology Education

Original Title: Uncertainty-aware and causal test-time adaptive foundation model for robust colorectal cancer pathology diagnosis Journal: NPJ digital medicine DOI: 10.1038/s41746-025-02149-1 Overview Colorectal cancer remains a major global health challenge, requiring precise histopathological analysis for effective treatment. While computational pathology has advanced with the use of large-scale foundation models, these systems frequently encounter obstacles when deployed in real-world clinical settings. Key issues include domain shifts caused by variations in staining protocols and scanner hardware, as well as the tendency for models to provide overconfident yet incorrect predictions. This paper introduces UAD-FM, an uncertainty-aware and causally adaptive foundation model designed to address these limitations. The framework integrates a variational Bayesian approach…

Original Title: Deep learning-enabled accurate assessment of gait impairments in Parkinson's disease using smartphone videos Journal: NPJ digital medicine DOI: 10.1038/s41746-025-02150-8 Overview Parkinson's disease affects millions globally, with gait impairments serving as a primary source of disability. Traditional assessment relies on the Unified Parkinson’s Disease Rating Scale, which is often subjective and lacks the sensitivity to detect minor changes. This study introduces a deep learning framework that utilizes videos recorded by a single smartphone from lateral perspectives to evaluate gait. The system employs a Siamese contrastive network architecture to fuse information from both sides of the body. In testing, the model achieved a micro-average area under the receiver operating characteristic…

Original Title: Telerobotic surgery: a comprehensive two-decade evolution and the integration of emerging technologies Journal: International journal of surgery (London, England) DOI: 10.1097/JS9.0000000000003484 Overview OverviewTelerobotic surgery has progressed from early conceptual stages to a sophisticated clinical reality over the last two decades. Initially envisioned by NASA in 1972 for orbital missions, the field achieved a major milestone in 2001 with the first transatlantic laparoscopic cholecystectomy, which operated over 14,000 kilometers with a transmission latency of 155 milliseconds. Since then, the technology has expanded across multiple medical disciplines. In urology, robotic systems were utilized in 42% of radical prostatectomies in the United States by 2006. More recently, the integration of high-speed…

AI Regulation Inaction: A Health Policy Crisis One-Sentence Summary This editorial argues that the rapid advancement of AI in healthcare, combined with political upheaval paralyzing federal agencies, creates a dangerous regulatory vacuum, highlighting the urgent need for a functional public sector to establish safety guardrails. Overview This article addresses the growing gap between the rapid adoption of artificial intelligence in health and healthcare and the lagging development of governmental oversight. The author posits that the widespread availability of large language models has accelerated AI integration across all sectors. However, the policies and standards necessary to govern this technology have not kept pace. This challenge is compounded by a described period…

Optimizing Federated Learning for Prostate MRI One-Sentence Summary This simulation study demonstrates that fine-tuning federated learning configurations enhances AI performance for prostate cancer detection on MRI, enabling collaboration between institutions without sharing patient data. Overview Training accurate medical AI models requires large, diverse datasets, which are difficult for a single hospital to collect. Federated learning (FL) offers a solution by allowing multiple institutions to collaboratively train a model without centralizing patient data. This study investigated how to best configure an FL network for two tasks using prostate MRI: segmenting the prostate gland and detecting clinically significant prostate cancer. Researchers simulated a network of clients (hospitals) and compared models trained locally,…

Original Title: Deep learning facilitated discovery of prognosis biomarkers and their ligands to improve liver cancer treatment Journal: International journal of surgery (London, England) DOI: 10.1097/JS9.0000000000003455 Overview The DLCP framework improves clinical prognosis for hepatocellular carcinoma by integrating genomics, transcriptomics, and epigenetics directly with survival outcomes. Analyzing 371 patients from The Cancer Genome Atlas, the model successfully stratified the cohort into 298 low-risk and 76 high-risk individuals, demonstrating significant survival differences with a P-value below 0.001. These results were confirmed through validation in an independent cohort of 232 patients. Key molecular signatures, including mutations in EIF2B4 and HCCS, were found to occur exclusively in the high-risk group. The analysis further…