Multiple Instance Learning with Mixed Supervision in Gleason Grading

TL;DR

This paper introduces a mixed supervision Transformer model for Gleason grading in computational pathology, effectively combining slide-level and pixel-level labels with a masking strategy to improve accuracy and robustness.

Contribution

It proposes a novel mixed supervision Transformer that leverages both slide and pixel-level labels, addressing label inaccuracy and enhancing Gleason grading accuracy.

Findings

Achieved state-of-the-art performance on SICAPv2 dataset.

Demonstrated robustness to inaccurate pixel-level labels.

Provided accurate instance-level predictions through visual analysis.

Abstract

With the development of computational pathology, deep learning methods for Gleason grading through whole slide images (WSIs) have excellent prospects. Since the size of WSIs is extremely large, the image label usually contains only slide-level label or limited pixel-level labels. The current mainstream approach adopts multi-instance learning to predict Gleason grades. However, some methods only considering the slide-level label ignore the limited pixel-level labels containing rich local information. Furthermore, the method of additionally considering the pixel-level labels ignores the inaccuracy of pixel-level labels. To address these problems, we propose a mixed supervision Transformer based on the multiple instance learning framework. The model utilizes both slide-level label and instance-level labels to achieve more accurate Gleason grading at the slide level. The impact of inaccurate instance-level labels is further reduced by introducing an efficient random masking strategy in the mixed supervision training process. We achieve the state-of-the-art performance on the SICAPv2 dataset, and the visual analysis shows the accurate prediction results of instance level. The source code is available at https://github.com/bianhao123/Mixed_supervision.