Přístupnostní navigace
E-application
Search Search Close
Publication detail
ARGANDA-CARRERAS, I. TURAGA, S. C. BERGER, D. R. CIRESAN, D. GIUSTI, A. GAMBARDELLA, L. M. SCHMIDHUBER, J. LAPTEV, D. DWIVEDI, S. BUHMANN, J. M. LIU, T. SEYEDHOSSEINI, M. TASDIZEN, T. KAMENTSKY, L. BURGET, R. UHER, V. TAN, X. SUN, C. PHAM, T. BAS, E. UZUNBAS, M. G. CARDONA, A. SCHINDELIN, J. SEUNG H. S.
Original Title
Crowdsourcing the creation of image segmentation algorithms for connectomics
Type
journal article in Web of Science
Language
English
Original Abstract
To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This “deep learning” approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.
Keywords
connectomics; electron microscopy; image segmentation; machine learning; reconstruction
Authors
ARGANDA-CARRERAS, I.; TURAGA, S. C.; BERGER, D. R.; CIRESAN, D.; GIUSTI, A.; GAMBARDELLA, L. M.; SCHMIDHUBER, J.; LAPTEV, D.; DWIVEDI, S.; BUHMANN, J. M.; LIU, T.; SEYEDHOSSEINI, M.; TASDIZEN, T.; KAMENTSKY, L.; BURGET, R.; UHER, V.; TAN, X.; SUN, C.; PHAM, T.; BAS, E.; UZUNBAS, M. G.; CARDONA, A.; SCHINDELIN, J.; SEUNG H. S.
RIV year
2015
Released
5. 11. 2015
Publisher
Frontiers Research Foundation
Location
Švýcarsko
ISBN
1662-5129
Periodical
Frontiers in Neuroanatomy
Year of study
9
Number
142
State
Swiss Confederation
Pages from
1
Pages to
13
Pages count
URL
http://journal.frontiersin.org/Journal/10.3389/fnana.2015.00142/full
BibTex
@article{BUT118015, author="ARGANDA-CARRERAS, I. and TURAGA, S. C. and BERGER, D. R. and CIRESAN, D. and GIUSTI, A. and GAMBARDELLA, L. M. and SCHMIDHUBER, J. and LAPTEV, D. and DWIVEDI, S. and BUHMANN, J. M. and LIU, T. and SEYEDHOSSEINI, M. and TASDIZEN, T. and KAMENTSKY, L. and BURGET, R. and UHER, V. and TAN, X. and SUN, C. and PHAM, T. and BAS, E. and UZUNBAS, M. G. and CARDONA, A. and SCHINDELIN, J. and SEUNG H. S.", title="Crowdsourcing the creation of image segmentation algorithms for connectomics", journal="Frontiers in Neuroanatomy", year="2015", volume="9", number="142", pages="1--13", doi="10.3389/fnana.2015.00142", issn="1662-5129", url="http://journal.frontiersin.org/Journal/10.3389/fnana.2015.00142/full" }