Transformer based multiple instance learning for weakly supervised histopathology image segmentation

TL;DR

This paper introduces a Transformer-enhanced multiple instance learning framework for weakly supervised histopathology image segmentation, effectively capturing global dependencies and improving segmentation accuracy with hierarchical supervision.

Contribution

It proposes a novel Transformer-based MIL method that models long-range dependencies and utilizes deep supervision for better weakly supervised segmentation performance.

Findings

Achieved state-of-the-art results on colon cancer dataset

Demonstrated the effectiveness of global dependency modeling

Showed improved segmentation accuracy over existing methods

Abstract

Hispathological image segmentation algorithms play a critical role in computer aided diagnosis technology. The development of weakly supervised segmentation algorithm alleviates the problem of medical image annotation that it is time-consuming and labor-intensive. As a subset of weakly supervised learning, Multiple Instance Learning (MIL) has been proven to be effective in segmentation. However, there is a lack of related information between instances in MIL, which limits the further improvement of segmentation performance. In this paper, we propose a novel weakly supervised method for pixel-level segmentation in histopathology images, which introduces Transformer into the MIL framework to capture global or long-range dependencies. The multi-head self-attention in the Transformer establishes the relationship between instances, which solves the shortcoming that instances are independent of each other in MIL. In addition, deep supervision is introduced to overcome the limitation of annotations in weakly supervised methods and make the better utilization of hierarchical information. The state-of-the-art results on the colon cancer dataset demonstrate the superiority of the proposed method compared with other weakly supervised methods. It is worth believing that there is a potential of our approach for various applications in medical images.