ZoomISEG: Interactive Multi-Scale Fusion for Histopathology Whole Slide Image Segmentation

Accurate segmentation of histopathology whole slide images (WSIs) is a crucial task for disease diagnosis and treatment planning. However, conventional automated algorithms may not always be applicable to WSI due their large size variations in tissue appearance, staining, imaging conditions. Recent advances interactive segmentation, which combines human expertise with algorithms, have shown promise improve efficiency accuracy but also presented us challenging issues. In this paper, we propose novel method, ZoomISEG, that leverages multi-resolution WSIs. We demonstrate the efficacy performance proposed method via comparison single-scale methods an ablation study. The results confirm can reduce interaction while achieving comparable brute-force approach using highest-resolution data.