The diagnosis of unruptured intracranial aneurysms from time-of-flight Magnetic Resonance Angiography (TOF-MRA) images is a challenging clinical problem. The the paper “Aneurysm Pose Estimation with Deep Learning” goes beyond the mere detection of each aneurysm and also estimates its size and the orientation of its main axis for an immediate visualization in appropriate reformatted cut planes. It relies on an approximate but fast annotation and a one-stage deep learning approach inspired by YOLO for 3D patches. See the gitlab repository for code, annotations and more. Youssef Assis received a MICCAI STAR award for this work.
Visual Registration with Physically Coherent Models
