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.
Start with the kidney transplant case, because it is the one that motivated this whole project. When a transplanted kidney is rejected, pathologists grade the severity using the Banff classification, a system built around seventeen lesion scores. Ten of those…
Inside KongNet A Multi Headed Model for Nuclei Detection Read More »
Vision transformers earned their place in medical imaging because self attention lets a model connect a finding in one part of an image to context somewhere else entirely, the kind of long range reasoning a small convolution kernel cannot do…
FadeFormer: Graph Diffusion Sharpens Medical Image Classification Read More »
Ask a radiology resident to find the spleen on a single unfamiliar scan after seeing only one labeled example beforehand and you are asking for exactly the problem this paper takes on, except the resident here is a neural network.…
Prototype Guided Graph Reasoning for Few Shot Medical Segmentation Read More »
Gastric cancer killed 260,372 people in China in a single year according to the 2022 figures the authors cite, trailing only lung and liver cancer as a cause of cancer death in that country. Endoscopy is the frontline tool for…
ST3-Former Learns How Many Tokens an Endoscopy Image Actually Needs Read More »
A dermatologist looking at a mole under a dermoscope has maybe ninety seconds before the next patient walks in. Fair skin, a family history, a spot that changed shape last spring. The decision to biopsy or reassure rests on pattern…
Inside the EfficientNetV2L LightGBM Ensemble for Skin Lesion Grading Read More »
Autism has no blood test. There is no scan a doctor can order and no single marker to check off a list. Diagnosis instead rests on structured behavioral observation, developmental history and tools such as the Autism Diagnostic Observation Schedule,…
How AI Models Compare Across Autism Spectrum Disorder Detection Research Read More »
An aneurysm is a weak spot in an artery wall that balloons outward under blood pressure. When one forms near or inside the brain, it usually causes no symptoms at all, which is exactly what makes it dangerous. If it…
How AI Is Learning to Spot Brain Aneurysms Before They Rupture Read More »
Skin cancer is common enough that the World Health Organization attributes roughly one in three cancer diagnoses worldwide to it, and melanoma is the deadliest form. Caught early, the ten year survival rate for melanoma patients can exceed 93 percent.…
How a Mixture of Experts Network Learns to Balance Skin Images and Patient Metadata Read More »
Every cell is really a city of tiny neighborhoods. Mitochondria run the power grid. Lysosomes handle waste disposal. The nucleus holds the blueprints and the nucleolus builds the machinery that reads them. A protein has to reach the right neighborhood…
Why Even The Best Protein Localization Predictor Still Misses Where Proteins Actually Go Read More »
This article explains a published bioinformatics paper. ClairS is a research tool for detecting cancer mutations in sequencing data, it is not a diagnostic device and is not used on its own to make decisions about an individual patient’s care.…
Meet ClairS: The Long-Read Somatic Variant Caller Trained Without Real Tumors Read More »