Test Time Transform Prediction for Open Set Histopathological Image Recognition
This work addresses the need for automated tissue typology annotation in computational pathology by enabling models to handle unknown categories, which is incremental as it builds on existing open set recognition techniques.
The paper tackles the problem of open set recognition in histopathological images by training a model to classify known tissue types and predict applied data augmentation transforms, using transform prediction confidence to reject unknown categories at test time. The approach is validated on colorectal cancer histological images, showing effectiveness in identifying samples from unknown categories.
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 .