用轻量级变换器实现全切片细胞核高效分割，无需后处理
LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole Slide Images
- 基于星形凸多边形表示核，用径向距离损失自然分离重叠核
- 在PanNuke和MoNuSeg上速度比现有最快方法快5倍以上
- 端到端框架，支持大图处理且不增加计算成本，适合病理分析
精确且可扩展的细胞核实例分割对计算病理学至关重要，但千兆像素级全切片图像带来巨大计算挑战。现有方法依赖分块处理和昂贵的后处理进行实例分离，牺牲了上下文信息并降低效率。我们提出LSP-DETR（局部星形多边形检测变压器），一种全端到端框架，采用线性复杂度的轻量级变压器，可在不增加计算成本的前提下处理更大图像。细胞核以星形凸多边形表示，新颖的径向距离损失函数使重叠核的分割自然涌现，无需显式重叠标注或手工后处理。在PanNuke和MoNuSeg数据集上的评估显示其具有强泛化能力与最先进的效率，LSP-DETR速度超过次快方法五倍以上。代码与模型已公开于https://github.com/RationAI/lsp-detr。
原文摘要 · Abstract (English)
Precise and scalable instance segmentation of cell nuclei is essential for computational pathology, yet gigapixel Whole-Slide Images pose major computational challenges. Existing approaches rely on patch-based processing and costly post-processing for instance separation, sacrificing context and efficiency. We introduce LSP-DETR (Local Star Polygon DEtection TRansformer), a fully end-to-end framework that uses a lightweight transformer with linear complexity to process substantially larger images without additional computational cost. Nuclei are represented as star-convex polygons, and a novel radial distance loss function allows the segmentation of overlapping nuclei to emerge naturally, without requiring explicit overlap annotations or handcrafted post-processing. Evaluations on PanNuke and MoNuSeg show strong generalization across tissues and state-of-the-art efficiency, with LSP-DETR being over five times faster than the next-fastest leading method. Code and models are available at https://github.com/RationAI/lsp-detr.
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。