NELGJun 18, 2015

An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation

arXiv:1506.05849v114 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of building brain connectomics maps by enhancing segmentation accuracy for electron microscopy images, representing an incremental improvement in a domain-specific application.

The paper tackles the problem of automatically refining membrane detection probability maps for electron microscopy image segmentation by iteratively applying a convolutional neural network to recover removed center pixel labels, achieving significant improvements in segmentation results.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes