A method to detect glands in histological gastric cancer images

摘要

Automatic detection and quantification of glands in gastric cancer may contribute to objectively measure thelesion severity, to develop strategies for early diagnosis, and most importantly to improve the patient catego-rization. This article presents an entire framework for automatic detection of glands in gastric cancer images.This approach starts by selecting gland candidates from a binarized version of the hematoxylin channel. Next,the gland's shape and nuclei are characterized using local features which feed a Monte Carlo Cross validationmethod classifier trained previously with manually labeled images. Validation was carried out using a datasetwith 1330 annotated structures (2372 glands) from seven fields of view extracted from gastric cancer whole slideimages. Results showed an accuracy of 93% using a simple linear classifier. The presented strategy is quitesimple, exible and easily adapted to an actual pathology laboratory.