让医学图像分割记住用户历史操作，提升交互效率与精度。
MAIS: Memory-Attention for Interactive Segmentation
- 引入记忆注意力机制，融合历史交互信息
- 在多种影像模态上实现更高效精准的分割修正
- 适合需要频繁交互的医疗图像标注场景
交互式医学图像分割通过用户反馈来优化预测，减少标注工作量。基于视觉变换器（ViT）的模型，如通用分割模型（SAM），利用用户点击和先验掩码作为提示，达到当前最佳性能。然而，现有方法将交互视为独立事件，导致重复修正且改进有限。为此，我们提出MAIS，一种用于交互式分割的记忆-注意力机制，可存储过往用户输入与分割状态，实现时间上下文融合。该方法在多种影像模态下提升了ViT-based分割表现，实现了更高效、更准确的迭代优化。
原文摘要 · Abstract (English)
Interactive medical segmentation reduces annotation effort by refining predictions through user feedback. Vision Transformer (ViT)-based models, such as the Segment Anything Model (SAM), achieve state-of-the-art performance using user clicks and prior masks as prompts. However, existing methods treat interactions as independent events, leading to redundant corrections and limited refinement gains. We address this by introducing MAIS, a Memory-Attention mechanism for Interactive Segmentation that stores past user inputs and segmentation states, enabling temporal context integration. Our approach enhances ViT-based segmentation across diverse imaging modalities, achieving more efficient and accurate refinements.
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。