SuperPromptSeg: A Novel Fine-Tuning-Free Segmentation Method Leveraging Superpixel-Based Point Prompts

Abstract

The efficient segmentation of histopathological tissues plays a crucial role in aiding diagnostics and prognosis. However, the existing segmentation methods not only typically demand extensive human annotation and/or time-consuming model fine-tuning, but also exhibit limited generalization capabilities. To address these, we propose a novel fine-tuning-free method SuperPromptSeg, which can use the Segment Anything Model (SAM) as a foundation model and only needs a few point prompts. SuperPromptSeg consists of three main components: prompt selection, pseudo point generation, and mask selection. First, Simple Linear Iterative Clustering (SLIC) is employed to partition a patch into superpixels and K-means clustering is used to select point prompts. Then, pseudo points are generated from these point prompts and superpixels, serving together with the point prompts as inputs of SAM. Finally, two novel penalties are proposed to select predicted mask results using SAM’s outputs. Extensive experiments are conducted on three benchmark datasets to demonstrate the robust zero-shot segmentation capabilities of SuperPromptSeg. SuperPromptSeg achieves an average increase of 8.4% in Dice score, with a maximum improvement of 19.6%, greatly improving SAM’s segmentation capability on digital pathology images.