Medical AI brings together our reporting on machine learning for clinical and biomedical problems, from diagnosis and prognosis to medical image analysis and decision support. Because mistakes in this domain carry a human cost, we pay close attention to evaluation, calibration, uncertainty, and the gap between benchmark numbers and bedside reliability. Expect grounded explainers of recent research rather than uncritical product announcements.
This article explains a published computational biology paper. CelloType is a research tool for analyzing tissue images in spatial omics experiments, it is not a diagnostic device and is not used to make decisions about an individual patient’s care. Any…
This article explains a published engineering paper about an automated image segmentation method. It is not medical advice, it does not diagnose anything, and it is not a substitute for a radiologist, a radiation oncologist, or a qualified clinician reviewing…
MedDINOv3 Adapts A Vision Foundation Model For CT And MRI Segmentation Read More »
Segmenting organs and lesions in medical images is one of those tasks that sounds simple until you have to automate it at scale. Manual segmentation by a radiologist is accurate but slow and inconsistent from one reader to the next,…
D-Net Pairs Dynamic Large Kernels With a Pixel Level Salience Layer Read More »
Picture a hospital archive full of cone beam CT scans of people’s jaws, thousands of them, and almost none of them labeled voxel by voxel with where the enamel ends and the pulp begins. That is the actual starting point…
U-Mamba2-SSL Segments Teeth and Pulp From Unlabeled CBCT Read More »
Retinal disease does not announce itself early. Age related macular degeneration, diabetic retinopathy, and glaucoma can all progress for years before a patient notices anything wrong, and by the time vision loss is obvious a meaningful amount of it can…
Cancer grading sounds like a simple counting exercise. Look at how abnormal the cells are, assign a number, done. In practice grading is closer to reading a crowded room and trying to describe its social structure at three different zoom…
AMGF-GNN: Adaptive Multi-Graph Fusion for Tumor Grading in Pathology Images Read More »
This article explains a published engineering paper about an automated image segmentation method. It is not medical advice, it does not diagnose anything, and it is not a substitute for a colonoscopy, a radiologist’s read, or a conversation with a…
CMFDNet Tackles Blurry Polyp Boundaries With A Cross Mamba Decoder Read More »
This article explains a published research paper. It is not medical advice, diagnosis, or treatment guidance. The segmentation model discussed here is a research prototype, not an approved clinical device. Anyone with a health concern about a breast finding should…
Towards Trustworthy Breast Tumor Segmentation in Ultrasound Using AI Uncertainty Read More »
Convolutional networks are good at spotting tumors, cataracts and the subtle atrophy patterns that show up in Alzheimer scans. They have been good at this for years. What they are not good at, on their own, is telling a physician…
Knowledge Distillation Helps Medical AI Explain Its Choices Read More »
Ejection fraction is one of the most commonly used numbers in cardiology, a single percentage describing how much blood the left ventricle pumps out with each heartbeat. Getting it right depends on accurately tracing the boundary of the left ventricle,…
Why HSS-Net Splits Echo Video Segmentation Into Two Speeds Read More »