Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images
This work addresses boundary delineation in cancer tissue segmentation, which is crucial for prognosis and treatment, but it is incremental as it refines existing CAM-based methods.
The paper tackles the problem of unclear boundaries in weakly-supervised semantic segmentation for histopathology images by proposing a multi-level superpixel correction algorithm, achieving a mIoU of 71.08% on a breast cancer dataset.
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.