Header

UZH-Logo

Maintenance Infos

Candidate sampling for neuron reconstruction from anisotropic electron microscopy volumes


Funke, Jan; Martel, Julien N P; Gerhard, Stephan; Ciresan, Dan C; Giusti, Alessandro; Gambardella, Luca M; Schmidhuber, Jürgen; Pfister, Hanspeter; Cardona, Albert; Cook, Matthew (2014). Candidate sampling for neuron reconstruction from anisotropic electron microscopy volumes. In: Medical Image Computing and Computer Assisted Intervention (MICCAI) 2014, Boston, MA, United States of America, 14 September 2014 - 18 September 2014, 17-24.

Abstract

The automatic reconstruction of neurons from stacks of electron microscopy sections is an important computer vision problem in neuroscience. Recent advances are based on a two step approach: First, a set of possible 2D neuron candidates is generated for each section independently based on membrane predictions of a local classifier. Second, the candidates of all sections of the stack are fed to a neuron tracker that selects and connects them in 3D to yield a reconstruction. The accuracy of the result is currently limited by the quality of the generated candidates. In this paper, we propose to replace the heuristic set of candidates used in previous methods with samples drawn from a conditional random field (CRF) that is trained to label sections of neural tissue. We show on a stack of Drosophila melanogaster neural tissue that neuron candidates generated with our method produce 30% less reconstruction errors than current candidate generation methods. Two properties of our CRF are crucial for the accuracy and applicability of our method: (1) The CRF models the orientation of membranes to produce more plausible neuron candidates. (2) The interactions in the CRF are restricted to form a bipartite graph, which allows a great sampling speed-up without loss of accuracy.

Abstract

The automatic reconstruction of neurons from stacks of electron microscopy sections is an important computer vision problem in neuroscience. Recent advances are based on a two step approach: First, a set of possible 2D neuron candidates is generated for each section independently based on membrane predictions of a local classifier. Second, the candidates of all sections of the stack are fed to a neuron tracker that selects and connects them in 3D to yield a reconstruction. The accuracy of the result is currently limited by the quality of the generated candidates. In this paper, we propose to replace the heuristic set of candidates used in previous methods with samples drawn from a conditional random field (CRF) that is trained to label sections of neural tissue. We show on a stack of Drosophila melanogaster neural tissue that neuron candidates generated with our method produce 30% less reconstruction errors than current candidate generation methods. Two properties of our CRF are crucial for the accuracy and applicability of our method: (1) The CRF models the orientation of membranes to produce more plausible neuron candidates. (2) The interactions in the CRF are restricted to form a bipartite graph, which allows a great sampling speed-up without loss of accuracy.

Statistics

Citations

3 citations in Web of Science®
2 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

6 downloads since deposited on 25 Feb 2015
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Speech), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:18 September 2014
Deposited On:25 Feb 2015 10:52
Last Modified:21 Aug 2017 15:20
Publisher:Springer
Series Name:Lecture Notes in Computer Science
Number:8673
ISSN:0302-9743
ISBN:978-3-319-10404-1
Publisher DOI:https://doi.org/10.1007/978-3-319-10404-1_3
Related URLs:http://www.springer.com/gp/book/9783319104034# (Publisher)

Download

Download PDF  'Candidate sampling for neuron reconstruction from anisotropic electron microscopy volumes'.
Preview
Filetype: PDF
Size: 85kB
View at publisher