Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Mengmeng, Dai, Xingyuan, Sun, Yicheng, Wang, Jing, Yao, Yueyang, Gong, Xiaoyan, Cong, Fuze, Wang, Feiyue, Lv, Yisheng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908391607107584
author Zhang, Mengmeng
Dai, Xingyuan
Sun, Yicheng
Wang, Jing
Yao, Yueyang
Gong, Xiaoyan
Cong, Fuze
Wang, Feiyue
Lv, Yisheng
author_facet Zhang, Mengmeng
Dai, Xingyuan
Sun, Yicheng
Wang, Jing
Yao, Yueyang
Gong, Xiaoyan
Cong, Fuze
Wang, Feiyue
Lv, Yisheng
contents Although the Segment Anything Model (SAM) is highly effective in natural image segmentation, it requires dependencies on prompts, which limits its applicability to medical imaging where manual prompts are often unavailable. Existing efforts to fine-tune SAM for medical segmentation typically struggle to remove this dependency. We propose Hierarchical Self-Prompting SAM (HSP-SAM), a novel self-prompting framework that enables SAM to achieve strong performance in prompt-free medical image segmentation. Unlike previous self-prompting methods that remain limited to positional prompts similar to vanilla SAM, we are the first to introduce learning abstract prompts during the self-prompting process. This simple and intuitive self-prompting framework achieves superior performance on classic segmentation tasks such as polyp and skin lesion segmentation, while maintaining robustness across diverse medical imaging modalities. Furthermore, it exhibits strong generalization to unseen datasets, achieving improvements of up to 14.04% over previous state-of-the-art methods on some challenging benchmarks. These results suggest that abstract prompts encapsulate richer and higher-dimensional semantic information compared to positional prompts, thereby enhancing the model's robustness and generalization performance. All models and codes will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework
Zhang, Mengmeng
Dai, Xingyuan
Sun, Yicheng
Wang, Jing
Yao, Yueyang
Gong, Xiaoyan
Cong, Fuze
Wang, Feiyue
Lv, Yisheng
Computer Vision and Pattern Recognition
Although the Segment Anything Model (SAM) is highly effective in natural image segmentation, it requires dependencies on prompts, which limits its applicability to medical imaging where manual prompts are often unavailable. Existing efforts to fine-tune SAM for medical segmentation typically struggle to remove this dependency. We propose Hierarchical Self-Prompting SAM (HSP-SAM), a novel self-prompting framework that enables SAM to achieve strong performance in prompt-free medical image segmentation. Unlike previous self-prompting methods that remain limited to positional prompts similar to vanilla SAM, we are the first to introduce learning abstract prompts during the self-prompting process. This simple and intuitive self-prompting framework achieves superior performance on classic segmentation tasks such as polyp and skin lesion segmentation, while maintaining robustness across diverse medical imaging modalities. Furthermore, it exhibits strong generalization to unseen datasets, achieving improvements of up to 14.04% over previous state-of-the-art methods on some challenging benchmarks. These results suggest that abstract prompts encapsulate richer and higher-dimensional semantic information compared to positional prompts, thereby enhancing the model's robustness and generalization performance. All models and codes will be released upon acceptance.
title Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.02854