摘要：文本描述可通过明确需要勾画的病灶及其位置，降低医学图像分割中的歧义。现有文本引导方法主要改进图像与语言特征的交互位置，但通常针对所有图文对保留单一的学习更新路径。我们提出 MRSeg，这是一种参数高效框架，可利用每一个图文对，在稠密预测之前对视觉和文本特征的适配过程进行路由。冻结的 ConvNeXt-Tiny 和 PubMedBERT 编码器分别提供多尺度视觉特征和临床文本 Token。一个联合路由器利用最深层视觉特征与池化文本，在低秩 Adapter 基上预测稀疏混合。所得路由在两个视觉尺度和文本各自独立的 Adapter 库之间共享，从而在保持特征专属参数独立的同时协调其适配过程。Region Bridge 使用由文本派生的查询，将稠密视觉 Token 聚合为潜在区域；随后通过自注意力和文本交叉注意力细化这些区域，并将细化后的信息重新分发至特征图。最后，多尺度解码器将细化后的语义特征与浅层图像证据相结合。在 QaTa-COV19 和 MosMedData+ 上，MRSeg 分别实现了 90.90/83.32 和 81.53/68.82 的 Dice/mIoU，训练参数量为 7.11M，计算量为 7.60 GFLOPs。代码：此 HTTPS 链接。

Abstract:Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language features interact but generally retain a single learned update pathway across all image-text pairs. We propose MRSeg, a parameter-efficient framework that uses each image-text pair to route the adaptation of visual and textual features before dense prediction. Frozen ConvNeXt-Tiny and PubMedBERT encoders provide multiscale visual features and clinical text tokens. A joint router uses the deepest visual feature and pooled text to predict a sparse mixture over low-rank adapter bases. The resulting route is shared across separate adapter banks for two visual scales and text, coordinating their adaptation while keeping the feature-specific parameters separate. Region Bridge uses text-derived queries to aggregate dense visual tokens into latent regions, refines these regions through self-attention and text cross-attention, and redistributes the refined information back to the feature maps. Finally, a multiscale decoder combines refined semantic features with shallow image evidence. On QaTa-COV19 and MosMedData+, MRSeg achieves 90.90/83.32 and 81.53/68.82 Dice/mIoU, respectively, with 7.11M trainable parameters and 7.60 GFLOPs. Code: this https URL.