Log In Sign Up

An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

by   Xundong Wu, et al.

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.


page 3

page 5


FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics

Electron microscopic connectomics is an ambitious research direction wit...

Combinatorial Energy Learning for Image Segmentation

We introduce a new machine learning approach for image segmentation that...

Nanoscale Microscopy Images Colourisation Using Neural Networks

Microscopy images are powerful tools and widely used in the majority of ...

Segmentation of Drosophila Heart in Optical Coherence Microscopy Images Using Convolutional Neural Networks

Convolutional neural networks are powerful tools for image segmentation ...

Convolutional Neural Network Pruning to Accelerate Membrane Segmentation in Electron Microscopy

Biological membranes are one of the most basic structures and regions of...

What Properties are Desirable from an Electron Microscopy Segmentation Algorithm

The prospect of neural reconstruction from Electron Microscopy (EM) imag...

Efficient 2D neuron boundary segmentation with local topological constraints

We present a method for segmenting neuron membranes in 2D electron micro...