Rearrange Anatomy Inputs Like LEGO Bricks: Applying InSSS-P and a Mobile-Dense Hybrid Network to Distill Vascular Significance From Retina OCT-Angiography

Medical deep neural networks (DNNs) trained upon coarse image inputs are inherently insensible to fine-grained anatomic features. To enhance DNN perception on delicate microvascular structures, we proposed using a straightforward angiographic mobile-de…