Towards Patient-Individual PI-Rads v2 Sector Map: Cnn for Automatic Segmentation of Prostatic Zones From T2-Weighted MRI

• Published in: Proceedings (International Symposium on Biomedical Imaging) pp. 696 - 700
• Main Authors: Meyer, Anneke, Rakr, Marko, Schindele, Daniel, Blaschke, Simon, Schostak, Martin, Fedorov, Andriy, Hansen, Christian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2019
• Subjects: computer-aided diagnosis; deep convolutional neural networks; Image resolution; Image segmentation; Magnetic resonance imaging; Medical treatment; MRI; PI-RADS v2 sector map; Planning; prostate zone segmentation; therapy planning; Three-dimensional displays; Training
• ISSN: 1945-8452
• DOI: 10.1109/ISBI.2019.8759572

Automatic segmentation of the prostate, its inner and surrounding structures is highly desired for various applications. Several works have been presented for segmentation of anatomical zones of the prostate that are limited to the transition and peripheral zone. Following the spatial division according to the PI-RADS v2 sector map, we present a multi-class segmentation method that additionally targets the anterior fibromuscular stroma and distal prostatic urethra to improve computer-aided detection methods and enable a more precise therapy planning. We propose a multi-class segmentation with an anisotropic convolutional neural network that generates a topologically correct division of the prostate into these four structures. We evaluated our method on a dataset of T2-weighted axial MRI scans (n=98 subjects) and obtained results in the range of inter-rater variability for the majority of the zones.