Dense cellular segmentation for EM using 2D-3D neural network ensembles.
Dense cellular segmentation for EM using 2D-3D neural network ensembles.
复制标题
DOI：
10.1038/s41598-021-81590-0
复制
发表时间：
2021-01-28
影响因子：
4.6
通讯作者：
Leapman RD
中科院分区：
文献类型：
--
作者：
Guay MD;Emam ZAS;Anderson AB;Aronova MA;Pokrovskaya ID;Storrie B;Leapman RD
生物学家使用电子显微镜（EM）图像来构建整个细胞及其细胞器的纳米级3D模型，由于成像和分析的限制，历史上一直局限于少量细胞和细胞特征。这一直是一个主要的因素限制洞察复杂的细胞环境的变化。现代EM可以产生包含大量细胞的千兆像素图像体积，但是图像特征的精确手动分割是缓慢的，并且限制了细胞模型的创建。基于卷积神经网络的分割算法可以快速处理大量数据，但实现EM任务准确性目标通常对当前技术构成挑战。在这里，我们将密集细胞分割定义为用于对细胞及其大量细胞器进行建模的多类语义分割任务，并以人类血小板为例。我们提出了一种算法，使用新的混合2D-3D分割网络产生密集的细胞分割的准确性水平，优于基线方法和接近人类注释。据我们所知，这项工作代表了第一个公开的方法来自动创建具有这种结构细节水平的细胞模型。
Biologists who use electron microscopy (EM) images to build nanoscale 3D models of whole cells and their organelles have historically been limited to small numbers of cells and cellular features due to constraints in imaging and analysis. This has been a major factor limiting insight into the complex variability of cellular environments. Modern EM can produce gigavoxel image volumes containing large numbers of cells, but accurate manual segmentation of image features is slow and limits the creation of cell models. Segmentation algorithms based on convolutional neural networks can process large volumes quickly, but achieving EM task accuracy goals often challenges current techniques. Here, we define dense cellular segmentation as a multiclass semantic segmentation task for modeling cells and large numbers of their organelles, and give an example in human blood platelets. We present an algorithm using novel hybrid 2D–3D segmentation networks to produce dense cellular segmentations with accuracy levels that outperform baseline methods and approach those of human annotators. To our knowledge, this work represents the first published approach to automating the creation of cell models with this level of structural detail.
登录
查看更多内容
影响因子：
48
作者：
Haberl MG;Churas C;Tindall L;Boassa D;Phan S;Bushong EA;Madany M;Akay R;Deerinck TJ;Peltier ST;Ellisman MH
通讯作者：
Ellisman MH
影响因子：
5.7
作者：
Chen, Hao;Dou, Qi;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann
影响因子：
3.7
作者：
Haft-Javaherian, Mohammad;Fang, Linjing;Sabuncu, Mert R.
通讯作者：
Sabuncu, Mert R.
影响因子：
10.6
作者：
Mohseni Salehi SS;Erdogmus D;Gholipour A
通讯作者：
Gholipour A
影响因子：
10.4
作者：
Pokrovskaya, I. D.;Aronova, M. A.;Storrie, B.
通讯作者：
Storrie, B.