Papers › ProMISe: Promptable Medical Image Segmentation using SAM

ProMISe: Promptable Medical Image Segmentation using SAM

7 Mar 2024arXiv:2403.04164archive 2025-07-28

Jinfeng Wang, Sifan Song, Xinkun Wang, Yiyi Wang, Yiyi Miao, Jionglong Su, S. Kevin Zhou

With the proposal of the Segment Anything Model (SAM), fine-tuning SAM for medical image segmentation (MIS) has become popular. However, due to the large size of the SAM model and the significant domain gap between natural and medical images, fine-tuning-based strategies are costly with potential risk of instability, feature damage and catastrophic forgetting. Furthermore, some methods of transferring SAM to a domain-specific MIS through fine-tuning strategies disable the model's prompting capability, severely limiting its utilization scenarios. In this paper, we propose an Auto-Prompting Module (APM), which provides SAM-based foundation model with Euclidean adaptive prompts in the target domain. Our experiments demonstrate that such adaptive prompts significantly improve SAM's non-fine-tuned performance in MIS. In addition, we propose a novel non-invasive method called Incremental Pattern Shifting (IPS) to adapt SAM to specific medical domains. Experimental results show that the IPS enables SAM to achieve state-of-the-art or competitive performance in MIS without the need for fine-tuning. By coupling these two methods, we propose ProMISe, an end-to-end non-fine-tuned framework for Promptable Medical Image Segmentation. Our experiments demonstrate that both using our methods individually or in combination achieves satisfactory performance in low-cost pattern shifting, with all of SAM's parameters frozen.

PaperPDFCode

Code

xinkunwang111/promise officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image SegmentationLesion SegmentationMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 ProMISe Mean IoU 0.850 #3 of 17 Archive leaderboard report
Lesion Segmentation ISIC 2018 ProMISe mean Dice 0.921 #3 of 17 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB ProMISe mIoU 0.789 #6 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB ProMISe mean Dice 0.874 #6 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB ProMISe mIoU 0.750 #5 of 25 Archive leaderboard report
Medical Image Segmentation ETIS-LARIBPOLYPDB ProMISe mean Dice 0.840 #5 of 25 Archive leaderboard report
Medical Image Segmentation ISIC 2018 ProMISe DSC 92.10 #1 of 5 Archive leaderboard report
Medical Image Segmentation ISIC 2018 ProMISe mIoU 85.00 #1 of 5 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG ProMISe mIoU 0.851 #36 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG ProMISe mean Dice 0.911 #36 of 58 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections