An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

Abstract

To build the connectomics map of the brain, we developed a new algorithm that can automatically refine the Membrane Detection Probability Maps (MDPM) generated to perform automatic segmentation of electron microscopy (EM) images. To achieve this, we executed supervised training of a convolutional neural network to recover the removed center pixel label of patches sampled from a MDPM. MDPM can be generated from other machine learning based algorithms recognizing whether a pixel in an image corresponds to the cell membrane. By iteratively applying this network over MDPM for multiple rounds, we were able to significantly improve membrane segmentation results.

References in corpus (2)

• Fully Convolutional Networks for Semantic Segmentation
• Image Super-Resolution Using Deep Convolutional Networks

Cited by in corpus (5)

• FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
• The Importance of Skip Connections in Biomedical Image Segmentation
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
• Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy