Computerized Classification of Prostate Cancer Gleason Scores from Whole Slide Images

Hongming Xu, Sunho Park, Tae Hyun Hwang

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

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 present an automatic technique for Gleason grading of prostate cancer from HE stained whole slide pathology images using a set of novel completed and statistical local binary pattern (CSLBP) descriptors. First, the technique divides the whole slide image (WSI) 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 extracted from salient image tiles to characterize different Gleason patterns. Finally, the CSLBP texture features computed from all tiles are integrated and utilized by the multi-class support vector machine (SVM) that assigns patient slides with different Gleason scores such as 6, 7, or $\geq$≥ 8. Experiments have been performed on 312 different patient cases selected from the cancer genome atlas (TCGA) and have achieved superior performances over state-of-the-art texture descriptors and baseline methods including deep learning models for prostate cancer Gleason grading.

Original languageEnglish (US)
Article number8836110
Pages (from-to)1871-1882
Number of pages12
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume17
Issue number6
DOIs
StatePublished - Nov 1 2020

Keywords

  • Prostate cancer
  • image classification
  • medical image analysis
  • texture features

ASJC Scopus subject areas

  • Biotechnology
  • Genetics
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Computerized Classification of Prostate Cancer Gleason Scores from Whole Slide Images'. Together they form a unique fingerprint.

Cite this