Share Email Print

Proceedings Paper

Generative modeling for label-free glomerular modeling and classification
Author(s): Brendon Lutnick; Brandon Ginley; Kuang-Yu Jen; Wen Dong; Pinaki Sarder
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Generative modeling using GANs has gained traction in machine learning literature, as training does not require labeled datasets. This is perfect for applications in biological datasets, where large labeled datasets are often difficult and expensive to acquire. However, generative models offer no easy way to encode real images into feature-sets, something that is desirable for network explainability and may yield potentially informative image features. For this reason, we test a VAE-GAN architecture for label-free modeling of glomerular structural features. We show that this network can generate realistic looking synthetic images, and be used to interpolate between images. To prove the biological relevance of the network encodings, we classify small-labeled sets of encoded glomeruli by biopsy Tervaert class and for the presence of sclerosis, obtaining a Cohen’s kappa values of 0.87 and 0.78 respectfully.

Paper Details

Date Published: 16 March 2020
PDF: 6 pages
Proc. SPIE 11320, Medical Imaging 2020: Digital Pathology, 1132007 (16 March 2020); doi: 10.1117/12.2548757
Show Author Affiliations
Brendon Lutnick, State Univ. New York Buffalo (United States)
Brandon Ginley, State Univ. New York Buffalo (United States)
Kuang-Yu Jen, Univ. of California, Davis (United States)
Wen Dong, State Univ. New York Buffalo (United States)
Pinaki Sarder, State Univ. New York Buffalo (United States)

Published in SPIE Proceedings Vol. 11320:
Medical Imaging 2020: Digital Pathology
John E. Tomaszewski; Aaron D. Ward, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?