DuSSS：用于半监督医学图像分割的双语义相似性监督视觉语言模型
DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation
AI总结：
提出DuSSS模型，通过双对比学习与语义相似性监督策略，利用视觉语言模型增强伪标签，提升半监督医学图像分割性能，在三个数据集上取得优异Dice结果。
摘要：
半监督医学图像分割（SSMIS）利用一致性学习来规范模型训练，从而减轻像素级手动标注的负担。然而，它常常受到低质量伪标签带来的错误监督的影响。视觉语言模型（VLM）通过引入文本提示引导的多模态监督信息，具有增强伪标签的巨大潜力，但它面临跨模态问题：所获取的信息往往对应多个目标。为解决上述问题，我们提出了一种用于SSMIS的双语义相似性监督VLM（DuSSS）。具体而言，1）设计了一种双对比学习（DCL），通过捕获每个模态内的内在表示以及跨模态的语义相关性，来提高跨模态语义一致性。2）为了促进多个语义对应关系的学习，提出了一种语义相似性监督策略（SSS），并将其注入DCL中的每个对比学习过程，通过基于分布的置信度水平来监督语义相似性。此外，设计了一种新颖的基于VLM的SSMIS网络，以弥补伪标签的质量缺陷。它利用预训练的VLM生成文本提示引导的监督信息，细化伪标签以获得更好的一致性正则化。实验结果表明，我们的DuSSS在三个公开数据集（QaTa-COV19、BM-Seg和MoNuSeg）上取得了优异的性能，Dice系数分别为82.52%、74.61%和78.03%。
英文摘要：
Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
