Automated Neuron Tracing Using Content-Aware Adaptive Voxel Scooping on CNN Predicted Probability Map.

Qing Huang,Yijun Chen,Anan Li,Tingwei Quan,Tingting Cao,Shaoqun Zeng

doi:10.3389/fnana.2021.712842

Abstract

Neuron tracing, as the essential step for neural circuit building and brain information flow analyzing, plays an important role in the understanding of brain organization and function. Though lots of methods have been proposed, automatic and accurate neuron tracing from optical images remains challenging. Current methods often had trouble in tracing the complex tree-like distorted structures and broken parts of neurite from a noisy background. To address these issues, we propose a method for accurate neuron tracing using content-aware adaptive voxel scooping on a convolutional neural network (CNN) predicted probability map. First, a 3D residual CNN was applied as preprocessing to predict the object probability and suppress high noise. Then, instead of tracing on the binary image produced by maximum classification, an adaptive voxel scooping method was presented for successive neurite tracing on the probability map, based on the internal content properties (distance, connectivity, and probability continuity along direction) of the neurite. Last, the neuron tree graph was built using the length first criterion. The proposed method was evaluated on the public BigNeuron datasets and fluorescence micro-optical sectioning tomography (fMOST) datasets and outperformed current state-of-art methods on images with neurites that had broken parts and complex structures. The high accuracy tracing proved the potential of the proposed method for neuron tracing on large-scale.

Highlights

Digital reconstruction or tracing of neurons, which converts a neuronal image into a digital representation by obtaining the 3D spatial position of neuron skeletons and building their topological connections, is one of the major subjects in computational neuroscience (Parekh and Ascoli, 2013)
Neurite probability is estimated by 3D residual convolutional neural network (CNN) as preprocessing
We presented an effective neuron tracing method to address these issues, which is achieved by the following aspects: (1) the neurite probability map is robustly and accurately estimated by 3D residual CNN with hybrid loss function and a series of training skills, including various data augmentation

Summary

Introduction

Digital reconstruction or tracing of neurons, which converts a neuronal image into a digital representation by obtaining the 3D spatial position of neuron skeletons and building their topological connections, is one of the major subjects in computational neuroscience (Parekh and Ascoli, 2013). The neuron structure is complex and distorted with various direction changes, even an experienced annotator had to spend hours to trace these tree-like or mushroom-like structures from the image (Figures 1B1–E1). These are common problems of tubular objects tracing of medical images, including retinal, liver vessel, and brain vessel tracking

Methods

Results

Discussion

Conclusion