A new annotation-free framework uses foundation model guidance to reconstruct and segment uterine fibroids from routine multi-planar MRI, narrowing the gap with fully supervised target-domain training.

Transcript INTRO Welcome to Medical AI Digest Podcast. Today, a paper from Circulation. MAIN Today we’re looking at a multinational, multimodal study titled “Contrastive Machine Learning to Quantify…

Transcript INTRO Welcome to Medical AI Digest Podcast. Today, a paper from NPJ digital medicine. MAIN The paper is titled “Advanced machine learning-based screening for primary aldosteronism with…

A multicenter MRI-based AI model, BCALN-Net, showed strong performance for preoperative assessment of axillary lymph node status in breast cancer.

A new multimodal large language model, GVHD-MLLM, was developed to support early warning, diagnosis, and severity grading of chronic ocular graft-versus-host disease after allo-HSCT.

A missing-aware multimodal model improved overall survival prediction in unresectable stage II-III non-small cell lung cancer while retaining patients with incomplete data.

A multicenter study in NPJ digital medicine presents POCC, an interpretable machine learning model designed to predict kidney failure risk in children with CAKUT at 1, 3, and…

Guo, Deng, Tan et al. describe a voice-controlled framework that links conversational AI with super-resolution ultrasound imaging, reconstruction, quantitative analysis, and reporting.

This week’s medical AI papers were less about benchmark wins and more about operational ambition: agents in EHRs, foundation models for ultrasound, federated EHR science, and imaging tools…

AI4Doctor is a clinical large language model designed around electronic medical records, aiming to move beyond exam-style knowledge toward episode-grounded clinical reasoning, documentation, and consultation support.