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

TL;DR

Clore introduces a hierarchical, click-based local refinement method for pathology image segmentation, improving accuracy and efficiency by combining global and local interactions.

Contribution

The paper proposes a novel hierarchical interaction paradigm that enhances interactive segmentation by combining global initial segmentation with local refinement, reducing interactions and improving detail accuracy.

Findings

Clore achieves state-of-the-art accuracy on four datasets.

The method reduces the number of interactions needed for precise segmentation.

Clore effectively captures fine-grained structures and corrects subtle errors.

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.