Creating synthetic digital slides using conditional generative adversarial networks: application to Ki67 staining

Caglar Senaras; Berkman Sahiner; Gary Tozbikian; Gerard Lozanski; Metin N. Gurcan

doi:10.1117/12.2294999

6 March 2018 Creating synthetic digital slides using conditional generative adversarial networks: application to Ki67 staining

Caglar Senaras, Berkman Sahiner, Gary Tozbikian, Gerard Lozanski, Metin N. Gurcan

Author Affiliations +

Proceedings Volume 10581, Medical Imaging 2018: Digital Pathology; 1058103 (2018) https://doi.org/10.1117/12.2294999
Event: SPIE Medical Imaging, 2018, Houston, Texas, United States

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%).

Citation Download Citation

Caglar Senaras, Berkman Sahiner, Gary Tozbikian, Gerard Lozanski, and Metin N. Gurcan "Creating synthetic digital slides using conditional generative adversarial networks: application to Ki67 staining", Proc. SPIE 10581, Medical Imaging 2018: Digital Pathology, 1058103 (6 March 2018); https://doi.org/10.1117/12.2294999

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available