Unsupervised Prostate Cancer Detection on H&E using Convolutional Adversarial Autoencoders

TL;DR

This paper introduces an unsupervised convolutional autoencoder approach with self-clustering for prostate cancer detection in H&E tissue images, eliminating the need for labeled training data and improving feature learning with IHC data.

Contribution

It presents a novel unsupervised clustering method integrated into autoencoder training, utilizing IHC data to enhance feature relevance for tumor classification.

Findings

Achieved an F1 score of 0.62 with minimal labeled data

Demonstrated improved feature learning using IHC as reconstruction target

Reduced post-processing requirements for tissue classification

Abstract

We propose an unsupervised method using self-clustering convolutional adversarial autoencoders to classify prostate tissue as tumor or non-tumor without any labeled training data. The clustering method is integrated into the training of the autoencoder and requires only little post-processing. Our network trains on hematoxylin and eosin (H&E) input patches and we tested two different reconstruction targets, H&E and immunohistochemistry (IHC). We show that antibody-driven feature learning using IHC helps the network to learn relevant features for the clustering task. Our network achieves a F1 score of 0.62 using only a small set of validation labels to assign classes to clusters.