Share Email Print

Proceedings Paper

Automated gastric cancer diagnosis on H&E-stained sections; ltraining a classifier on a large scale with multiple instance machine learning
Author(s): Eric Cosatto; Pierre-Francois Laquerre; Christopher Malon; Hans-Peter Graf; Akira Saito; Tomoharu Kiyuna; Atsushi Marugame; Ken'ichi Kamijo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We present a system that detects cancer on slides of gastric tissue sections stained with hematoxylin and eosin (H&E). At its heart is a classifier trained using the semi-supervised multi-instance learning framework (MIL) where each tissue is represented by a set of regions-of-interest (ROI) and a single label. Such labels are readily obtained because pathologists diagnose each tissue independently as part of the normal clinical workflow. From a large dataset of over 26K gastric tissue sections from over 12K patients obtained from a clinical load spanning several months, we train a MIL classifier on a patient-level partition of the dataset (2/3 of the patients) and obtain a very high performance of 96% (AUC), tested on the remaining 1/3 never-seen before patients (over 8K tissues). We show this level of performance to match the more costly supervised approach where individual ROIs need to be labeled manually. The large amount of data used to train this system gives us confidence in its robustness and that it can be safely used in a clinical setting. We demonstrate how it can improve the clinical workflow when used for pre-screening or quality control. For pre-screening, the system can diagnose 47% of the tissues with a very low likelihood (< 1%) of missing cancers, thus halving the clinicians' caseload. For quality control, compared to random rechecking of 33% of the cases, the system achieves a three-fold increase in the likelihood of catching cancers missed by pathologists. The system is currently in regular use at independent pathology labs in Japan where it is used to double-check clinician's diagnoses. At the end of 2012 it will have analyzed over 80,000 slides of gastric and colorectal samples (200,000 tissues).

Paper Details

Date Published: 29 March 2013
PDF: 9 pages
Proc. SPIE 8676, Medical Imaging 2013: Digital Pathology, 867605 (29 March 2013); doi: 10.1117/12.2007047
Show Author Affiliations
Eric Cosatto, NEC Labs. America, Inc. (United States)
Pierre-Francois Laquerre, NEC Labs. America, Inc. (United States)
Christopher Malon, NEC Labs. America, Inc. (United States)
Hans-Peter Graf, NEC Labs. America, Inc. (United States)
Akira Saito, NEC Corp. (Japan)
Tomoharu Kiyuna, NEC Corp. (Japan)
Atsushi Marugame, NEC Corp. (Japan)
Ken'ichi Kamijo, NEC Corp. (Japan)

Published in SPIE Proceedings Vol. 8676:
Medical Imaging 2013: Digital Pathology
Metin N. Gurcan; Anant Madabhushi, 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?