123

Home > Academic Announcements > (Oct. 12) 3D Neuron Reconstruction in Tangled Neuronal Image with Deep Networks

(Oct. 12) 3D Neuron Reconstruction in Tangled Neuronal Image with Deep Networks

Last updated :2019-10-08

Topic: 3D Neuron Reconstruction in Tangled Neuronal Image with Deep Networks
Speaker: Professor SHEN Linlin
(Director, Institute of Computer Vision, Shenzhen University)
Host: Associate Professor WANG Ruixuan
Time: 11:20-12:00, Saturday, October 12, 2019
Venue: A101, School of Data and Computer Science, Guangzhou East Campus, SYSU

Abstract:
Digital reconstruction or tracing of 3D neuron is essential for understanding the brain functions. While existing automatic tracing algorithms work well for clean neuronal image with a single neuron, they are not robust to trace the neuron surrounded by nerve fibers. We propose a 3D U-Net based network, namely 3D U-Net Plus, to segment the neuron from the surrounding fibers before the application of tracing algorithms. All the images in BigNeuron, the biggest available neuronal image dataset, contain clean neurons with no interference of nerve fibers, which are not practical to train the segmentation network. Based upon the BigNeuron images, we synthesize a SYNethic TAngled NEuronal Image dataset (SYNTANEI) to train the proposed network, by fusing the neurons with extracted nerve fibers. Due to the adoption of dropout, atrous convolution and atrous Spatial Pyramid Pooling (ASPP), experimental results on the synthetic and real tangled neuronal images show that the proposed 3D U-Net Plus network achieved very promising segmentation results. The neurons reconstructed by the tracing algorithm using the segmentation result match significantly better with the ground truth than that using the original images.