用扩散与状态空间模型实现未见肿瘤的精准分割
Unleashing Diffusion and State Space Models for Medical Image Segmentation
- 双查询机制：先学器官特征，再用扩散提示精炼肿瘤查询
- 在多种未见过的肿瘤上实现显著优于基线的分割效果
- 适合需要泛化能力的医疗影像多标签分割场景
现有医学图像分割模型在单一数据集上训练后，面对未见器官或肿瘤时鲁棒性不足。构建能识别训练中未出现的罕见或新肿瘤类别模型对推动医学影像应用至关重要。本文提出DSM框架，结合扩散模型与状态空间模型，实现对训练数据之外肿瘤类别的分割。DSM采用两组对象查询，通过改进的注意力解码器增强分类精度：首先利用面向对象的特征分组策略学习器官查询，捕捉器官级视觉特征；随后聚焦于基于扩散的视觉提示，精炼肿瘤查询，实现对从未见过肿瘤的精确分割。此外，引入扩散引导的特征融合以提升语义分割性能。通过集成CLIP文本嵌入，DSM捕捉类别敏感特征，增强语言迁移能力，从而提升在多样化场景和多标签任务中的鲁棒性。大量实验表明，DSM在各类肿瘤分割任务中表现优异。代码已开源：https://github.com/Rows21/k-Means_Mask_Mamba。
原文摘要 · Abstract (English)
Existing segmentation models trained on a single medical imaging dataset often lack robustness when encountering unseen organs or tumors. Developing a robust model capable of identifying rare or novel tumor categories not present during training is crucial for advancing medical imaging applications. We propose DSM, a novel framework that leverages diffusion and state space models to segment unseen tumor categories beyond the training data. DSM utilizes two sets of object queries trained within modified attention decoders to enhance classification accuracy. Initially, the model learns organ queries using an object-aware feature grouping strategy to capture organ-level visual features. It then refines tumor queries by focusing on diffusion-based visual prompts, enabling precise segmentation of previously unseen tumors. Furthermore, we incorporate diffusion-guided feature fusion to improve semantic segmentation performance. By integrating CLIP text embeddings, DSM captures category-sensitive classes to improve linguistic transfer knowledge, thereby enhancing the model's robustness across diverse scenarios and multi-label tasks. Extensive experiments demonstrate the superior performance of DSM in various tumor segmentation tasks. Code is available at https://github.com/Rows21/k-Means_Mask_Mamba.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。