Unsupervised anomaly detection in digital pathology using GANs

TL;DR

This paper introduces an unsupervised GAN-based method for anomaly detection in digital pathology, addressing the challenge of identifying outliers in complex histopathology images to improve clinical reliability.

Contribution

It presents a novel GAN architecture and anomaly metric tailored for histopathology data, significantly enhancing anomaly detection performance over previous methods.

Findings

GAN-based approach outperforms existing methods in pathology data

Histopathology images are more complex than previous datasets used in GAN research

Advanced GAN architecture and metrics are necessary for effective anomaly detection

Abstract

Machine learning (ML) algorithms are optimized for the distribution represented by the training data. For outlier data, they often deliver predictions with equal confidence, even though these should not be trusted. In order to deploy ML-based digital pathology solutions in clinical practice, effective methods for detecting anomalous data are crucial to avoid incorrect decisions in the outlier scenario. We propose a new unsupervised learning approach for anomaly detection in histopathology data based on generative adversarial networks (GANs). Compared to the existing GAN-based methods that have been used in medical imaging, the proposed approach improves significantly on performance for pathology data. Our results indicate that histopathology imagery is substantially more complex than the data targeted by the previous methods. This complexity requires not only a more advanced GAN architecture but also an appropriate anomaly metric to capture the quality of the reconstructed images.