Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images

TL;DR

This paper introduces a superpixel correction method to improve boundary accuracy in weakly-supervised semantic segmentation of histopathology images, significantly enhancing tumor boundary delineation.

Contribution

The paper presents a novel multi-level superpixel correction algorithm that refines CAM-based segmentation boundaries using superpixel clustering and floodfill techniques.

Findings

Achieved 71.08% mIoU on breast cancer dataset

Significantly improved tumor microenvironment boundary delineation

Enhanced boundary accuracy in weakly-supervised segmentation

Abstract

With the rapid advancement of deep learning, computational pathology has made significant progress in cancer diagnosis and subtyping. Tissue segmentation is a core challenge, essential for prognosis and treatment decisions. Weakly supervised semantic segmentation (WSSS) reduces the annotation requirement by using image-level labels instead of pixel-level ones. However, Class Activation Map (CAM)-based methods still suffer from low spatial resolution and unclear boundaries. To address these issues, we propose a multi-level superpixel correction algorithm that refines CAM boundaries using superpixel clustering and floodfill. Experimental results show that our method achieves great performance on breast cancer segmentation dataset with mIoU of 71.08%, significantly improving tumor microenvironment boundary delineation.