</> Code with Papers by Syntology

Papers › STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation

STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation

2 Apr 2025arXiv:2504.01561archive 2025-07-28

Dandan Shan, Zihan Li, Yunxiang Li, Qingde Li, Jie Tian, Qingqi Hong

Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and size. To address these issues, we propose STPNet, a Scale-aware Text Prompt Network that leverages vision-language modeling to enhance medical image segmentation. Our approach utilizes multi-scale textual descriptions to guide lesion localization and employs retrieval-segmentation joint learning to bridge the semantic gap between visual and linguistic modalities. Crucially, STPNet retrieves relevant textual information from a specialized medical text repository during training, eliminating the need for text input during inference while retaining the benefits of cross-modal learning. We evaluate STPNet on three datasets: COVID-Xray, COVID-CT, and Kvasir-SEG. Experimental results show that our vision-language approach outperforms state-of-the-art segmentation methods, demonstrating the effectiveness of incorporating textual semantic knowledge into medical image analysis. The code has been made publicly on https://github.com/HUANGLIZI/STPNet.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

huanglizi/stpnet 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 SegmentationLanguage ModelingLanguage ModellingLesion SegmentationMedical Image AnalysisMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation STPNet Dice 76.18 #1 of 17 Archive leaderboard report
Lesion Segmentation CMIRNet Dice 73.69 #2 of 17 Archive leaderboard report
Lesion Segmentation LAVT Dice 73.29 #3 of 17 Archive leaderboard report
Lesion Segmentation SAM2UNet Dice 72.91 #4 of 17 Archive leaderboard report
Lesion Segmentation nnUNet Dice 72.59 #5 of 17 Archive leaderboard report
Lesion Segmentation GLoRIA Dice 72.42 #6 of 17 Archive leaderboard report
Lesion Segmentation ViLT Dice 72.36 #7 of 17 Archive leaderboard report
Lesion Segmentation ConVIRT Dice 72.06 #8 of 17 Archive leaderboard report
Lesion Segmentation CLIP Dice 71.97 #9 of 17 Archive leaderboard report
Lesion Segmentation UNet++ Dice 71.75 #10 of 17 Archive leaderboard report
Lesion Segmentation UniLSeg Dice 71.6 #11 of 17 Archive leaderboard report
Lesion Segmentation TransUNet Dice 71.24 #12 of 17 Archive leaderboard report
Lesion Segmentation TGANet Dice 70.29 #13 of 17 Archive leaderboard report
Lesion Segmentation UCTransNet Dice 66.74 #14 of 17 Archive leaderboard report
Lesion Segmentation AttUNet Dice 65.57 #15 of 17 Archive leaderboard report
Lesion Segmentation Swin-UNet Dice 63.29 #16 of 17 Archive leaderboard report
Lesion Segmentation UNet Dice 62.96 #17 of 17 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.

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