Unsupervised Prostate Cancer Detection on H&E using Convolutional Adversarial Autoencoders
This addresses the problem of reducing reliance on labeled data for medical image analysis, though it is incremental as it builds on existing autoencoder and clustering techniques.
The paper tackles unsupervised prostate cancer detection from H&E tissue images using a self-clustering convolutional adversarial autoencoder, achieving an F1 score of 0.62 with minimal labeled data for cluster assignment.
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.