Spiers Helen, Songhurst Harry, Nightingale Luke, de Folter Joost, Hutchings Roger, Peddie Christopher J, Weston Anne, Strange Amy, Hindmarsh Steve, Lintott Chris, Collinson Lucy M, Jones Martin L
Electron Microscopy Science Technology Platform, The Francis Crick Institute, London, UK.
Department of Physics, University of Oxford, Oxford, UK.
Traffic. 2021 Jul;22(7):240-253. doi: 10.1111/tra.12789. Epub 2021 May 16.
Advancements in volume electron microscopy mean it is now possible to generate thousands of serial images at nanometre resolution overnight, yet the gold standard approach for data analysis remains manual segmentation by an expert microscopist, resulting in a critical research bottleneck. Although some machine learning approaches exist in this domain, we remain far from realizing the aspiration of a highly accurate, yet generic, automated analysis approach, with a major obstacle being lack of sufficient high-quality ground-truth data. To address this, we developed a novel citizen science project, Etch a Cell, to enable volunteers to manually segment the nuclear envelope (NE) of HeLa cells imaged with serial blockface scanning electron microscopy. We present our approach for aggregating multiple volunteer annotations to generate a high-quality consensus segmentation and demonstrate that data produced exclusively by volunteers can be used to train a highly accurate machine learning algorithm for automatic segmentation of the NE, which we share here, in addition to our archived benchmark data.
体积电子显微镜技术的进步意味着现在有可能在一夜之间生成数千张纳米分辨率的连续图像，然而数据分析的金标准方法仍然是由专业显微镜学家进行手动分割，这导致了一个关键的研究瓶颈。尽管该领域存在一些机器学习方法，但我们距离实现一种高度准确、通用的自动化分析方法的目标仍有很大差距，一个主要障碍是缺乏足够的高质量基准数据。为了解决这个问题，我们开发了一个新颖的公民科学项目“蚀刻细胞”，让志愿者手动分割通过连续块面扫描电子显微镜成像的HeLa细胞的核膜。我们展示了聚合多个志愿者注释以生成高质量一致性分割的方法，并证明仅由志愿者产生的数据可用于训练一种用于核膜自动分割的高度准确的机器学习算法，我们在此分享该算法，以及我们存档的基准数据。
