Text-guided multi-stage cross-perception network for medical image segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Gaoyu, Pan, Haixia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914208672645120
author Chen, Gaoyu
Pan, Haixia
author_facet Chen, Gaoyu
Pan, Haixia
contents Medical image segmentation plays a crucial role in clinical medicine, serving as a key tool for auxiliary diagnosis, treatment planning, and disease monitoring. However, traditional segmentation methods such as U-Net are often limited by weak semantic expression of target regions, which stems from insufficient generalization and a lack of interactivity. Incorporating text prompts offers a promising avenue to more accurately pinpoint lesion locations, yet existing text-guided methods are still hindered by insufficient cross-modal interaction and inadequate cross-modal feature representation. To address these challenges, we propose the Text-guided Multi-stage Cross-perception network (TMC). TMC incorporates a Multi-stage Cross-attention Module (MCM) to enhance the model's understanding of fine-grained semantic details and a Multi-stage Alignment Loss (MA Loss) to improve the consistency of cross-modal semantics across different feature levels. Experimental results on three public datasets (QaTa-COV19, MosMedData, and Duke-Breast-Cancer-MRI) demonstrate the superior performance of TMC, achieving Dice scores of 84.65\%, 78.39\%, and 88.09\%, respectively, and consistently outperforming both U-Net-based networks and existing text-guided methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Text-guided multi-stage cross-perception network for medical image segmentation
Chen, Gaoyu
Pan, Haixia
Image and Video Processing
Computer Vision and Pattern Recognition
Medical image segmentation plays a crucial role in clinical medicine, serving as a key tool for auxiliary diagnosis, treatment planning, and disease monitoring. However, traditional segmentation methods such as U-Net are often limited by weak semantic expression of target regions, which stems from insufficient generalization and a lack of interactivity. Incorporating text prompts offers a promising avenue to more accurately pinpoint lesion locations, yet existing text-guided methods are still hindered by insufficient cross-modal interaction and inadequate cross-modal feature representation. To address these challenges, we propose the Text-guided Multi-stage Cross-perception network (TMC). TMC incorporates a Multi-stage Cross-attention Module (MCM) to enhance the model's understanding of fine-grained semantic details and a Multi-stage Alignment Loss (MA Loss) to improve the consistency of cross-modal semantics across different feature levels. Experimental results on three public datasets (QaTa-COV19, MosMedData, and Duke-Breast-Cancer-MRI) demonstrate the superior performance of TMC, achieving Dice scores of 84.65\%, 78.39\%, and 88.09\%, respectively, and consistently outperforming both U-Net-based networks and existing text-guided methods.
title Text-guided multi-stage cross-perception network for medical image segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.07475