CellPilot统一自动与交互式细胞分割，提升病理图像分析效率。
CellPilot: A unified approach to automatic and interactive segmentation in histopathology
- 融合自动与交互式分割，先生成初筛结果再精准修正。
- 在9个数据集上训练，覆盖16个器官，超67.5万张标注图。
- 开源模型与界面，助力构建大规模病理标注数据集。
组织病理学是疾病组织显微研究，正日益数字化，促进可视化和工作流程优化。关键任务是细胞与腺体的分割，可反映形态与频率，作为疾病指标。深度学习广泛应用于该领域，但组织外观和细胞形态差异大，导致分割可靠性不足，常需人工修正。本文提出CellPilot框架，连接自动与交互式分割，提供初始自动分割及引导式交互优化。模型在超过67.5万张来自9个多样化的细胞与腺体分割数据集的标注图上训练，覆盖16个器官。在三个独立测试数据集上，其性能优于其他交互式工具，同时支持自动分割。我们开源了模型及为研究人员设计的图形化用户界面，以帮助创建大规模标注数据集，推动更鲁棒、泛化性更强的诊断模型发展。
原文摘要 · Abstract (English)
Histopathology, the microscopic study of diseased tissue, is increasingly digitized, enabling improved visualization and streamlined workflows. An important task in histopathology is the segmentation of cells and glands, essential for determining shape and frequencies that can serve as indicators of disease. Deep learning tools are widely used in histopathology. However, variability in tissue appearance and cell morphology presents challenges for achieving reliable segmentation, often requiring manual correction to improve accuracy. This work introduces CellPilot, a framework that bridges the gap between automatic and interactive segmentation by providing initial automatic segmentation as well as guided interactive refinement. Our model was trained on over 675,000 masks of nine diverse cell and gland segmentation datasets, spanning 16 organs. CellPilot demonstrates superior performance compared to other interactive tools on three held-out histopathological datasets while enabling automatic segmentation. We make the model and a graphical user interface designed to assist practitioners in creating large-scale annotated datasets available as open-source, fostering the development of more robust and generalized diagnostic models.
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。