Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Detection

TL;DR

This paper introduces a recursive training approach with a hybrid 2D-3D convolutional network architecture, significantly improving neuronal boundary detection in anisotropic 3D EM images by leveraging deeper networks, 3D context, and efficient CPU-based training.

Contribution

It presents a novel recursive training framework combined with a hybrid 2D-3D CNN architecture and a new multicore CPU implementation, advancing boundary detection accuracy in anisotropic 3D images.

Findings

Substantial accuracy improvement over previous methods

Effective use of deeper networks and 3D context

Accelerated training with multicore CPU implementation

Abstract

Efforts to automate the reconstruction of neural circuits from 3D electron microscopic (EM) brain images are critical for the field of connectomics. An important computation for reconstruction is the detection of neuronal boundaries. Images acquired by serial section EM, a leading 3D EM technique, are highly anisotropic, with inferior quality along the third dimension. For such images, the 2D max-pooling convolutional network has set the standard for performance at boundary detection. Here we achieve a substantial gain in accuracy through three innovations. Following the trend towards deeper networks for object recognition, we use a much deeper network than previously employed for boundary detection. Second, we incorporate 3D as well as 2D filters, to enable computations that use 3D context. Finally, we adopt a recursively trained architecture in which a first network generates a preliminary boundary map that is provided as input along with the original image to a second network that generates a final boundary map. Backpropagation training is accelerated by ZNN, a new implementation of 3D convolutional networks that uses multicore CPU parallelism for speed. Our hybrid 2D-3D architecture could be more generally applicable to other types of anisotropic 3D images, including video, and our recursive framework for any image labeling problem.