Chapter

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011

Volume 6891 of the series Lecture Notes in Computer Science pp 670-677

Detection of Neuron Membranes in Electron Microscopy Images Using Multi-scale Context and Radon-Like Features

  • Mojtaba SeyedhosseiniAffiliated withElectrical and Computer Engineering Department, University of UtahScientific Computing and Imaging Institute, University of Utah
  • , Ritwik KumarAffiliated withIBM Almaden Research Center
  • , Elizabeth JurrusAffiliated withScientific Computing and Imaging Institute, University of Utah
  • , Rick GiulyAffiliated withNational Center for Microscopy and Imaging Research, University of California
  • , Mark EllismanAffiliated withNational Center for Microscopy and Imaging Research, University of California
  • , Hanspeter PfisterAffiliated withSchool of Engineering and Applied Sciences, Harvard University
  • , Tolga TasdizenAffiliated withElectrical and Computer Engineering Department, University of UtahScientific Computing and Imaging Institute, University of Utah

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Automated neural circuit reconstruction through electron microscopy (EM) images is a challenging problem. In this paper, we present a novel method that exploits multi-scale contextual information together with Radon-like features (RLF) to learn a series of discriminative models. The main idea is to build a framework which is capable of extracting information about cell membranes from a large contextual area of an EM image in a computationally efficient way. Toward this goal, we extract RLF that can be computed efficiently from the input image and generate a scale-space representation of the context images that are obtained at the output of each discriminative model in the series. Compared to a single-scale model, the use of a multi-scale representation of the context image gives the subsequent classifiers access to a larger contextual area in an effective way. Our strategy is general and independent of the classifier and has the potential to be used in any context based framework. We demonstrate that our method outperforms the state-of-the-art algorithms in detection of neuron membranes in EM images.

Keywords

Machine learning Membrane detection Neural circuit reconstruction Multi-scale context Radon-like features (RLF)