An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

2015/06/18 by Xundong Wu, Wu, Xundong
Biochemistry, Genetics and Molecular Biology · Materials Science · #Advanced Electron Microscopy Techniques and Applications #Cell Image Analysis Techniques #Electron and X-Ray Spectroscopy Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1506.05849

openalex publication_date 2015/06/18 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

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.

Related

• Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy
• What Properties are Desirable from an Electron Microscopy Segmentation Algorithm
• Efficient 2D neuron boundary segmentation with local topological constraints
• Unsupervised Domain Adaptation for Neuron Membrane Segmentation based on Structural Features
• Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection