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

Hongming Xu, Sunho Park, Tae Hyun Hwang

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
JournalUnknown Journal
DOIs
StatePublished - May 9 2018
Externally publishedYes

Keywords

  • Feature classification
  • Medical image analysis
  • Prostate cancer
  • Texture descriptor

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • Immunology and Microbiology(all)
  • Neuroscience(all)
  • Pharmacology, Toxicology and Pharmaceutics(all)

Fingerprint Dive into the research topics of 'Automatic Classification of Prostate Cancer Gleason Scores from Digitized Whole Slide Tissue Biopsies'. Together they form a unique fingerprint.

Cite this