Graph neural networks look deceptively sturdy on paper. Stack a few convolution layers, pool the node embeddings, feed the result to a classifier, and you get strong numbers on clean benchmark data. The trouble starts once the input graph stops…
HPGRL: How Hierarchical Prototypes Make Graph Classification Resist Noise 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 team from ShanghaiTech University, Henan Provincial People’s Hospital, and Shanghai United Imaging Intelligence built a hierarchical framework that classifies 23 brain disorders across three diagnostic levels, cuts the performance gap between coarse and fine-grained predictions to just 2%, and…