Diagnosis of Helicobacter pylori using AutoEncoders for the Detection of Anomalous Staining Patterns in Immunohistochemistry Images

TL;DR

This paper presents an unsupervised autoencoder-based method for detecting Helicobacter pylori in immunohistochemistry images, achieving high accuracy and sensitivity, thus aiding faster diagnosis without extensive manual inspection.

Contribution

The study introduces a novel autoencoder approach for anomaly detection in histological images, eliminating the need for annotated training data and improving diagnostic efficiency.

Findings

91% overall accuracy in H. pylori detection

86% sensitivity and 96% specificity achieved

0.97 AUC indicating high discriminative performance

Abstract

This work addresses the detection of Helicobacter pylori a bacterium classified since 1994 as class 1 carcinogen to humans. By its highest specificity and sensitivity, the preferred diagnosis technique is the analysis of histological images with immunohistochemical staining, a process in which certain stained antibodies bind to antigens of the biological element of interest. This analysis is a time demanding task, which is currently done by an expert pathologist that visually inspects the digitized samples. We propose to use autoencoders to learn latent patterns of healthy tissue and detect H. pylori as an anomaly in image staining. Unlike existing classification approaches, an autoencoder is able to learn patterns in an unsupervised manner (without the need of image annotations) with high performance. In particular, our model has an overall 91% of accuracy with 86\% sensitivity, 96% specificity and 0.97 AUC in the detection of H. pylori.