Automatic Classification of Prostate Cancer Gleason Scores from Digitized Whole Slide Tissue Biopsies

Abstract

Histological Gleason grading of tumor patterns is one of the most powerful prognostic predictors in prostate cancer. However, manual analysis and grading performed by pathologists are typically subjective and time-consuming. In this paper, we propose an automatic technique for Gleason grading of prostate cancer from H&E stained whole slide biopsy images using a set of novel completed and statistical local bi-nary pattern (CSLBP) descriptors. First the technique divides the whole slide image into a set of small image tiles, where salient tumor tiles with high nuclei densities are selected for analysis. The CSLBP texture features that encode pixel intensity variations from circularly surrounding neighborhoods are then extracted from salient image tiles to characterize different Gleason patterns. Finally, CSLBP texture features computed from all tiles are integrated and utilized by the multi-class support vector machine (SVM) that assigns patient biopsy with different Gleason score of 6, 7 or [≥]8. Experiments have been performed on 312 different patient cases selected from the cancer genome atlas (TCGA) and have achieved more than 79% classification accuracies, which is superior to state-of-the-art textural descriptors for prostate cancer Gleason grading.