Clore: Interactive Pathology Image Segmentation with Click-based Local Refinement

2026-03-29

AI Summary

This work addresses the inefficiency and limited precision of existing interactive segmentation methods for histopathology images, which rely on global iterative updates that incur redundant computation and hinder accurate local refinement. To overcome these limitations, the authors propose a hierarchical interaction paradigm: an initial user click triggers a global coarse segmentation to rapidly localize the target region, while subsequent clicks exclusively drive localized fine-tuning without re-predicting the entire image. Integrating a deep learning framework with a click-guided local refinement mechanism, the method achieves state-of-the-art performance across four histopathology datasets. It significantly improves segmentation accuracy for fine-grained structures while substantially reducing the number of required interactions, thereby striking an optimal balance between precision and interaction cost.

Abstract

Recent advancements in deep learning-based interactive segmentation methods have significantly improved pathology image segmentation. Most existing approaches utilize user-provided positive and negative clicks to guide the segmentation process. However, these methods primarily rely on iterative global updates for refinement, which lead to redundant re-prediction and often fail to capture fine-grained structures or correct subtle errors during localized adjustments. To address this limitation, we propose the Click-based Local Refinement (Clore) pipeline, a simple yet efficient method designed to enhance interactive segmentation. The key innovation of Clore lies in its hierarchical interaction paradigm: the initial clicks drive global segmentation to rapidly outline large target regions, while subsequent clicks progressively refine local details to achieve precise boundaries. This approach not only improves the ability to handle fine-grained segmentation tasks but also achieves high-quality results with fewer interactions. Experimental results on four datasets demonstrate that Clore achieves the best balance between segmentation accuracy and interaction cost, making it an effective solution for efficient and accurate interactive pathology image segmentation.

Problem

• interactive segmentation
• pathology image
• click-based refinement
• local adjustment
• fine-grained structures

Innovation

• interactive segmentation
• local refinement
• pathology image analysis
• click-based interaction
• hierarchical paradigm