AUTHOR=Cheng Shenghua , Wang Xiaojun , Liu Yurong , Su Lei , Quan Tingwei , Li Ning , Yin Fangfang , Xiong Feng , Liu Xiaomao , Luo Qingming , Gong Hui , Zeng Shaoqun 

TITLE=DeepBouton: Automated Identification of Single-Neuron Axonal Boutons at the Brain-Wide Scale

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2019.00025

DOI=10.3389/fninf.2019.00025

ISSN=1662-5196

ABSTRACT=Fine morphological reconstructions of individual neurons across the entire brain are needed for mapping the brain circuits. Inference of presynaptic axonal boutons, as a key part of single-neuron fine reconstructions, is critical for interpreting the patterns of neural circuit wiring schemes. However, automated bouton identification remains challenging for current neuron reconstruction tools, as they are being focused mainly on neurite skeleton drawing and have difficulties to accurately quantify bouton morphology. Here, we developed an automatic method for recognizing single-neuron axonal boutons in whole-brain fluorescence microscopy datasets. The method is based on deep convolutional neural networks and density-peak clustering. High-dimensional feature representations of bouton morphology can be learned adaptively through the convolutional networks and used for the bouton recognition and bouton subtype classification. We demonstrated that the approach is effective in detecting single-neuron boutons at the brain-wide scale for both long-range projection pyramidal neurons and local interneurons.