DiffKillR：用于密集显微镜图像中细胞标注的微分同胚消灭与重建
DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images
AI总结：
DiffKillR通过结合原型匹配与图像配准，利用两个神经网络实现密集显微镜图像的高效细胞标注，减少手动标注需求，适用于多种像素级标注任务。
摘要：
数字显微镜图像的激增，得益于自动全切片扫描的进步，为生物医学研究和临床诊断带来了重大机遇。然而，准确标注这些图像中密集排列的信息仍然是一个重大挑战。为解决这一问题，我们提出了DiffKillR，一种新颖的框架，将细胞标注重新定义为原型匹配和图像配准任务的组合。DiffKillR采用两个互补的神经网络：一个学习微分同胚不变的特征空间以进行稳健的细胞匹配，另一个计算细胞之间的精确变形场以进行标注映射。利用一组标注好的原型，DiffKillR能够高效地将标注传播到大型显微镜图像中，减少了对大量手动标注的需求。更重要的是，它适用于任何类型的像素级标注。我们将讨论DiffKillR的理论性质，并在三个显微镜任务上进行验证，展示其相对于现有监督、半监督和无监督方法的优势。代码可在https://github.com/KrishnaswamyLab/DiffKillR获取。
英文摘要：
The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address this, we introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks. DiffKillR employs two complementary neural networks: one that learns a diffeomorphism-invariant feature space for robust cell matching and another that computes the precise warping field between cells for annotation mapping. Using a small set of annotated archetypes, DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling. More importantly, it is suitable for any type of pixel-level annotation. We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods. The code is available at https://github.com/KrishnaswamyLab/DiffKillR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
