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

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.

References in corpus (4)

• Natural Scales in Geographical Patterns
• Learning Spatiotemporal Features with 3D Convolutional Networks
• Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph
• ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines

Cited by in corpus (10)

• Estimation of the volume of the left ventricle from MRI images using deep neural networks
• ZNN - A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-Core and Many-Core Shared Memory Machines
• Morphological Error Detection in 3D Segmentations
• Dense Transformer Networks
• Toward Streaming Synapse Detection with Compositional ConvNets
• Deep Tensor Convolution on Multicores
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture
• 3D Dense Separated Convolution Module for Volumetric Image Analysis
• Learning Generative Models of Tissue Organization with Supervised GANs
• A Review of Network Inference Techniques for Neural Activation Time Series