SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images

TL;DR

SegMix introduces a shuffle-based feedback learning approach that enhances pseudo-label quality for pathology image segmentation using only image-level labels, outperforming existing methods.

Contribution

The paper proposes a novel shuffle-based feedback learning method that adaptively improves pseudo segmentation masks in pathology images with weak supervision.

Findings

Outperforms state-of-the-art methods on three datasets.

Uses patch-level shuffle to improve pseudo mask quality.

Adaptive shuffle strategy based on feedback enhances learning.

Abstract

Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervised segmentation data requires significant workload demands from experienced pathologists, limiting the application of deep learning. To overcome this challenge, relaxing the label conditions to image-level classification labels allows for more data to be used and more scenarios to be enabled. One approach is to leverage Class Activation Map (CAM) to generate pseudo pixel-level annotations for semantic segmentation with only image-level labels. However, this method fails to thoroughly explore the essential characteristics of pathology images, thus identifying only small areas that are insufficient for pseudo masking. In this paper, we propose a novel shuffle-based feedback learning method inspired by curriculum learning to generate higher-quality pseudo-semantic segmentation masks. Specifically, we perform patch level shuffle of pathology images, with the model adaptively adjusting the shuffle strategy based on feedback from previous learning. Experimental results demonstrate that our proposed approach outperforms state-of-the-arts on three different datasets.