Weakly Supervised Learning of 3D Deep Network for Neuron Reconstruction

Qing Huang; Yijun Chen; Shijie Liu; Cheng Xu; Tingting Cao; Yongchao Xu; Xiaojun Wang; Gong Rao; Anan Li; Shaoqun Zeng; Tingwei Quan

doi:10.3389/fnana.2020.00038

Weakly Supervised Learning of 3D Deep Network for Neuron Reconstruction

Front Neuroanat. 2020 Jul 28:14:38. doi: 10.3389/fnana.2020.00038. eCollection 2020.

Authors

Qing Huang^{1

2}, Yijun Chen^{1

2}, Shijie Liu³, Cheng Xu^{1

2}, Tingting Cao^{1

2}, Yongchao Xu⁴, Xiaojun Wang^{1

2}, Gong Rao^{1

2}, Anan Li^{1

2}, Shaoqun Zeng^{1

2}, Tingwei Quan^{1

2}

Affiliations

¹ Wuhan National Laboratory for Optoelectronics-Huazhong, Britton Chance Center for Biomedical Photonics, University of Science and Technology, Wuhan, China.
² Ministry of Education (MoE) Key Laboratory for Biomedical Photonics, Collaborative Innovation Center for Biomedical Engineering, School of Engineering Sciences, Huazhong University of Science and Technology, Wuhan, China.
³ School of Mathematics and Physics, China University of Geosciences, Wuhan, China.
⁴ School of Electronics Information and Communications, Huazhong University of Science and Technology, Wuhan, China.

Abstract

Digital reconstruction or tracing of 3D tree-like neuronal structures from optical microscopy images is essential for understanding the functionality of neurons and reveal the connectivity of neuronal networks. Despite the existence of numerous tracing methods, reconstructing a neuron from highly noisy images remains challenging, particularly for neurites with low and inhomogeneous intensities. Conducting deep convolutional neural network (CNN)-based segmentation prior to neuron tracing facilitates an approach to solving this problem via separation of weak neurites from a noisy background. However, large manual annotations are needed in deep learning-based methods, which is labor-intensive and limits the algorithm's generalization for different datasets. In this study, we present a weakly supervised learning method of a deep CNN for neuron reconstruction without manual annotations. Specifically, we apply a 3D residual CNN as the architecture for discriminative neuronal feature extraction. We construct the initial pseudo-labels (without manual segmentation) of the neuronal images on the basis of an existing automatic tracing method. A weakly supervised learning framework is proposed via iterative training of the CNN model for improved prediction and refining of the pseudo-labels to update training samples. The pseudo-label was iteratively modified via mining and addition of weak neurites from the CNN predicted probability map on the basis of their tubularity and continuity. The proposed method was evaluated on several challenging images from the public BigNeuron and Diadem datasets, to fMOST datasets. Owing to the adaption of 3D deep CNNs and weakly supervised learning, the presented method demonstrates effective detection of weak neurites from noisy images and achieves results similar to those of the CNN model with manual annotations. The tracing performance was significantly improved by the proposed method on both small and large datasets (>100 GB). Moreover, the proposed method proved to be superior to several novel tracing methods on original images. The results obtained on various large-scale datasets demonstrated the generalization and high precision achieved by the proposed method for neuron reconstruction.

Keywords: automatic; generalization; neuron reconstruction; precise; weakly supervised deep learning.