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.
Brain network analysis usually works like this. Take a resting state fMRI scan, split the brain into a fixed number of regions using an anatomical atlas such as AAL with its 116 regions, measure how correlated each region’s activity is…
Glaucoma causes progressive damage to the optic nerve and often develops without any early symptoms. This makes early glaucoma detection incredibly vital because existing treatments can only halt or slow down the damage rather than reversing it. Most traditional AI…
SGF-MRI uses a fast auxiliary MRI sequence to guide reconstruction of slower scans, speeding up brain and knee MRI while preserving diagnostic detail.
How SGF-MRI Speeds Up Brain and Knee MRI Scans Read More »
TriDeNT is a three-branch self-supervised framework that lets H&E pathology models learn from immunohistochemistry and spatial transcriptomics data they will never see at deployment — with performance gains up to 101%.
TriDeNT Taught a Pathology Model to Learn From Data It Will Never See Again Read More »
HCEP tackles open-set emotion recognition: teaching multimodal AI to admit when an expression matches no known category instead of forcing a wrong label.
Teaching AI to Say “I Don’t Know”: HCEP and the Open-Set Emotion Recognition Problem Read More »
KEDR separates shared disease knowledge from modality-specific visual detail so medical AI can still diagnose reliably when one scan is missing.
Missing Modality Medical Imaging: When a Scan Is Absent, Can AI Still Diagnose You? Read More »
A radiologist looking at a brain scan does not jump straight to naming an exact disease subtype. The process moves in stages. First comes a broad question, is there a vascular problem at all. If the answer is yes, the…
HP2L Diagnoses 23 Brain Disorders Like a Radiologist Read More »
A research team from the University of Minnesota and Harvard built a semi-supervised estimator that handles the most realistic and frustrating scenario in real-world health data — when both the treatment a patient received and the health outcome that followed…
AngioGraphCAD models coronary arteries as graphs, letting a graph neural network assess lesion-level risk the way cardiologists reason — one lesion at a time.
A team from Balgrist University Hospital and ETH Zurich built an instance-specific self-supervised framework that registers bone surfaces across imaging modalities by learning a continuous neural distance field from the preoperative scan and using thousands of neural hypothesis generation heads…