Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder-decoder deep networks.
Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder-decoder deep networks.
复制标题
DOI：
10.1038/s42256-020-0227-9
复制
发表时间：
2020-10
影响因子：
23.8
通讯作者：
Mitra PP
中科院分区：
文献类型：
--
作者：
Banerjee S;Magee L;Wang D;Li X;Huo BX;Jayakumar J;Matho K;Lin MK;Ram K;Sivaprakasam M;Huang J;Wang Y;Mitra PP
对大脑内细胞分辨率的神经回路的理解依赖于神经元追踪方法，这需要由经验丰富的神经科学家仔细观察和解释。随着最近成像和数字化的发展，这种方法对于大规模（tb到pb范围）的图像不再可行。基于机器学习的技术，使用深度网络，为这个问题提供了一个有效的替代方案。然而，这些方法依赖于非常大量的带注释的图像进行训练，并且对于科学数据分析来说错误率太高，因此需要大量的人工循环校对。在这里，我们介绍了一种混合架构，将基于离散莫尔斯理论的拓扑数据分析方法形式的先验结构与用于神经元连通性分析的同类最佳深度网络架构相结合。与人类观察者相比，我们使用我们的混合架构在拓扑结构检测（例如，神经元过程的连通性和与突触膨胀相对应的轴突上的局部强度最大值）上显示了显着的性能提升，精度/召回率接近90%。我们已经将我们的架构调整为高性能管道，能够将光显微镜下的全脑图像数据语义分割到神经元区室的层次结构中。我们期望将离散莫尔斯技术纳入深度网络的混合架构将推广到其他数据领域。
Understanding of neuronal circuitry at cellular resolution within the brain has relied on neuron tracing methods which involve careful observation and interpretation by experienced neuroscientists. With recent developments in imaging and digitization, this approach is no longer feasible with the large scale (terabyte to petabyte range) images. Machine learning based techniques, using deep networks, provide an efficient alternative to the problem. However, these methods rely on very large volumes of annotated images for training and have error rates that are too high for scientific data analysis, and thus requires a significant volume of human-in-the-loop proofreading. Here we introduce a hybrid architecture combining prior structure in the form of topological data analysis methods, based on discrete Morse theory, with the best-in-class deep-net architectures for the neuronal connectivity analysis. We show significant performance gains using our hybrid architecture on detection of topological structure (e.g. connectivity of neuronal processes and local intensity maxima on axons corresponding to synaptic swellings) with precision/recall close to 90% compared with human observers. We have adapted our architecture to a high performance pipeline capable of semantic segmentation of light microscopic whole-brain image data into a hierarchy of neuronal compartments. We expect that the hybrid architecture incorporating discrete Morse techniques into deep nets will generalize to other data domains.
登录
查看更多内容
影响因子：
64.8
作者：
通讯作者：
--
影响因子：
1.9
作者：
FUKUSHIMA, K
通讯作者：
FUKUSHIMA, K
DOI：
10.1109/tvcg.2008.110
发表时间：
2008-11-01
影响因子：
5.2
作者：
Gyulassy, Attila;Bremer, Peer-Timo;Pascucci, Valerio
通讯作者：
Pascucci, Valerio
影响因子：
7.7
作者：
Lin, Meng Kuan;Takahashi, Yeonsook Shin;Mitra, Partha
通讯作者：
Mitra, Partha
影响因子：
4.3
作者：
Bohland JW;Wu C;Barbas H;Bokil H;Bota M;Breiter HC;Cline HT;Doyle JC;Freed PJ;Greenspan RJ;Haber SN;Hawrylycz M;Herrera DG;Hilgetag CC;Huang ZJ;Jones A;Jones EG;Karten HJ;Kleinfeld D;Kötter R;Lester HA;Lin JM;Mensh BD;Mikula S;Panksepp J;Price JL;Safdieh J;Saper CB;Schiff ND;Schmahmann JD;Stillman BW;Svoboda K;Swanson LW;Toga AW;Van Essen DC;Watson JD;Mitra PP
通讯作者：
Mitra PP