Share Email Print

Proceedings Paper

Heterogeneity characterization of immunohistochemistry stained tissue using convolutional autoencoder
Author(s): Erwan Zerhouni; Bogdan Prisacari; Qing Zhong; Peter Wild; Maria Gabrani
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The focus of this paper is to illustrate how computational image processing and machine learning can help address two of the challenges of histological image analysis, namely, the cellular heterogeneity, and the imprecise labeling. We propose an unsupervised method of generating representative image signatures based on an autoencoder architecture which reduces the dependency on labels that tend to be imprecise and tedious to get. We have modified and enhanced the architecture to simultaneously produce representative image features as well as perform dictionary learning on these features to enable robust characterization of the cellular phenotypes. We integrate the extracted features in a disease grading framework, test it in prostate tissues immunostained for different protein visualization and show significant improvement in terms of grading accuracy compared to alternative supervised feature-extraction methods.

Paper Details

Date Published: 1 March 2017
PDF: 9 pages
Proc. SPIE 10140, Medical Imaging 2017: Digital Pathology, 101400P (1 March 2017); doi: 10.1117/12.2256238
Show Author Affiliations
Erwan Zerhouni, IBM Research - Zürich (Switzerland)
Bogdan Prisacari, IBM Research - Zürich (Switzerland)
Qing Zhong, Univ. Hospital Zürich (Switzerland)
Peter Wild, Univ. Hospital Zürich (Switzerland)
Maria Gabrani, IBM Research - Zürich (Switzerland)

Published in SPIE Proceedings Vol. 10140:
Medical Imaging 2017: Digital Pathology
Metin N. Gurcan; John E. Tomaszewski, Editor(s)

© SPIE. Terms of Use
Back to Top