用不确定性引导人工校正，提升3D显微图像分割精度
Bridging 3D Deep Learning and Curation for Analysis and High-Quality Segmentation in Practice
- 根据置信度图聚焦易错区域，智能引导人工校正
- 校正误差检出率从67%提升至94.0%，时间成本基本不变
- 适合需要高精度分割的生物医学图像分析人员
准确的3D显微图像分割对定量生物图像分析至关重要，但即使是最先进的基础模型也会产生错误。因此，人工校正仍广泛用于生成高质量训练数据或在分析前修正错误。我们提出VessQC，一个开源工具，用于大体积3D显微分割的不确定性引导校正。通过整合不确定性图，VessQC将用户注意力引向最可能包含生物学意义错误的区域。初步用户研究表明，不确定性引导校正使错误检测召回率从67%显著提升至94.0%（p=0.007），且总校正时间无显著增加。VessQC因此实现了高效的人机协同体积分割优化，弥合了不确定性估计与实际人机交互之间的关键鸿沟。软件已开源：github.com/MMV-Lab/VessQC。
原文摘要 · Abstract (English)
Accurate 3D microscopy image segmentation is critical for quantitative bioimage analysis but even state-of-the-art foundation models yield error-prone results. Therefore, manual curation is still widely used for either preparing high-quality training data or fixing errors before analysis. We present VessQC, an open-source tool for uncertainty-guided curation of large 3D microscopy segmentations. By integrating uncertainty maps, VessQC directs user attention to regions most likely containing biologically meaningful errors. In a preliminary user study uncertainty-guided correction significantly improved error detection recall from 67% to 94.0% (p=0.007) without a significant increase in total curation time. VessQC thus enables efficient, human-in-the-loop refinement of volumetric segmentations and bridges a key gap in real-world applications between uncertainty estimation and practical human-computer interaction. The software is freely available at github.com/MMV-Lab/VessQC.
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。