Share Email Print
cover

Proceedings Paper

Creating synthetic digital slides using conditional generative adversarial networks: application to Ki67 staining
Author(s): Caglar Senaras; Berkman Sahiner; Gary Tozbikian; Gerard Lozanski; Metin N. Gurcan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Immunohistochemical staining (IHC) of tissue sections is routinely used in pathology to diagnose and characterize malignant tumors. Unfortunately, in the majority of cases, IHC stain interpretation is completed by a trained pathologist using a manual method, which consists of counting each positively and negatively stained cell under a microscope. Even in the hands of expert pathologists, the manual enumeration suffers from poor reproducibility. In this study, we propose a novel method to create artificial datasets in silico with known ground truth, allowing us to analyze the accuracy, precision, and intra- and inter-observer variability in a systematic manner and compare different computer analysis approaches. Our approach employs conditional Generative Adversarial Networks. We created our dataset by using 32 different breast cancer patients' Ki67 stained tissues. Our experiments indicated that synthetic images are indistinguishable from real images: The accuracy of five experts (3 pathologists and 2 image analysts) in distinguishing between 15 real and 15 synthetic images was only 47.3% (±8.5%).

Paper Details

Date Published: 6 March 2018
PDF: 6 pages
Proc. SPIE 10581, Medical Imaging 2018: Digital Pathology, 1058103 (6 March 2018); doi: 10.1117/12.2294999
Show Author Affiliations
Caglar Senaras, The Ohio State Univ. (United States)
Berkman Sahiner, U.S. Food and Drug Administration (United States)
Gary Tozbikian, The Ohio State Univ. (United States)
Gerard Lozanski, The Ohio State Univ. (United States)
Metin N. Gurcan, Wake Forest School of Medicine (United States)


Published in SPIE Proceedings Vol. 10581:
Medical Imaging 2018: Digital Pathology
John E. Tomaszewski; Metin N. Gurcan, Editor(s)

© SPIE. Terms of Use
Back to Top