20 March 2014 Prostate malignancy grading using gland-related shape descriptors
Author Affiliations +
Abstract
A proof-of-principle study was accomplished assessing the descriptive potential of two simple geometric measures (shape descriptors) applied to sets of segmented glands within images of 125 prostate cancer tissue sections. Respective measures addressing glandular shapes were (i) inverse solidity and (ii) inverse compactness. Using a classifier based on logistic regression, Gleason grades 3 and 4/5 could be differentiated with an accuracy of approx. 95%. Results suggest not only good discriminatory properties, but also robustness against gland segmentation variations. False classifications in part were caused by inadvertent Gleason grade assignments, as a-posteriori re-inspections had turned out.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ulf-Dietrich Braumann, Patrick Scheibe, Markus Loeffler, Glen Kristiansen, Nicolas Wernert, "Prostate malignancy grading using gland-related shape descriptors", Proc. SPIE 9041, Medical Imaging 2014: Digital Pathology, 90410M (20 March 2014); doi: 10.1117/12.2043225; https://doi.org/10.1117/12.2043225
PROCEEDINGS
13 PAGES


SHARE
Back to Top