Brain micro-vasculature imaging: An unsupervised deep learning algorithm for segmenting mouse brain volume probed by high-resolution phase-contrast X-ray tomography

High-throughput synchrotron-based tomographic microscopy at third genera- tion light sources allows to probe cm-sized samples at micrometer-resolution. In this work, we present an approach to image a full mouse brain. With Indian- ink as a contrast agent, it was possible to obtain 3D distribution of microvessels while a computational framework automatically extracted the morphological and geometrical embedding of the putative vascular systems. Results demon- strate the potentiality of the proposed methodology to visualize and quantify in 3D details of the brain tissue with an image quality and resolution previously unachievable.