Test Time Transform Prediction for Open Set Histopathological Image Recognition

TL;DR

This paper introduces a novel open set recognition method for histopathological images that predicts applied data augmentation transforms during training and uses confidence measures at test time to identify unknown tissue categories.

Contribution

It proposes a new approach combining transform prediction with open set recognition for histopathology, enhancing unknown sample detection.

Findings

Effective identification of unknown tissue samples in colorectal cancer images.

Improved open set recognition performance over baseline methods.

Code released for reproducibility and further research.

Abstract

Tissue typology annotation in Whole Slide histological images is a complex and tedious, yet necessary task for the development of computational pathology models. We propose to address this problem by applying Open Set Recognition techniques to the task of jointly classifying tissue that belongs to a set of annotated classes, e.g. clinically relevant tissue categories, while rejecting in test time Open Set samples, i.e. images that belong to categories not present in the training set. To this end, we introduce a new approach for Open Set histopathological image recognition based on training a model to accurately identify image categories and simultaneously predict which data augmentation transform has been applied. In test time, we measure model confidence in predicting this transform, which we expect to be lower for images in the Open Set. We carry out comprehensive experiments in the context of colorectal cancer assessment from histological images, which provide evidence on the strengths of our approach to automatically identify samples from unknown categories. Code is released at https://github.com/agaldran/t3po .