Automatic Gleason grading of prostate cancer using quantitative phase imaging and machine learning

Tan H. Nguyen, Shamira Sridharan, Virgilia MacIas, Andre Kajdacsy-Balla, Jonathan Melamed, Minh N. Do, Gabriel Popescua

Research output: Contribution to journalArticlepeer-review


We present an approach for automatic diagnosis of tissue biopsies. Our methodology consists of a quantitative phase imaging tissue scanner and machine learning algorithms to process these data. We illustrate the performance by automatic Gleason grading of prostate specimens. The imaging system operates on the principle of interferometry and, as a result, reports on the nanoscale architecture of the unlabeled specimen. We use these data to train a random forest classifier to learn textural behaviors of prostate samples and classify each pixel in the image into different classes. Automatic diagnosis results were computed from the segmented regions. By combining morphological features with quantitative information from the glands and stroma, logistic regression was used to discriminate regions with Gleason grade 3 versus grade 4 cancer in prostatectomy tissue. The overall accuracy of this classification derived from a receiver operating curve was 82%, which is in the range of human error when interobserver variability is considered. We anticipate that our approach will provide a clinically objective and quantitative metric for Gleason grading, allowing us to corroborate results across instruments and laboratories and feed the computer algorithms for improved accuracy.

Original languageEnglish (US)
Article number036015
JournalJournal of biomedical optics
Issue number3
StatePublished - Mar 1 2017


  • holography
  • machine learning
  • microscopy
  • prostate cancer diagnosis
  • quantitative phase imaging

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomedical Engineering
  • Biomaterials


Dive into the research topics of 'Automatic Gleason grading of prostate cancer using quantitative phase imaging and machine learning'. Together they form a unique fingerprint.

Cite this