Crowdsourcing the creation of image segmentation algorithms for connectomics
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 agree...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Frontiers Media SA
2018
|
| Online Access: | http://hdl.handle.net/1721.1/116672 https://orcid.org/0000-0002-8161-3604 |
| _version_ | 1826202207331024896 |
|---|---|
| author | Arganda-Carreras, Ignacio Turaga, Srinivas C. Berger, Daniel R. Cireşan, Dan Giusti, Alessandro Gambardella, Luca M. Schmidhuber, Jürgen Laptev, Dmitry Dwivedi, Sarvesh Buhmann, Joachim M. Liu, Ting Seyedhosseini, Mojtaba Tasdizen, Tolga Kamentsky, Lee Burget, Radim Uher, Vaclav Tan, Xiao Sun, Changming Pham, Tuan D. Bas, Erhan Uzunbas, Mustafa G. Cardona, Albert Schindelin, Johannes Seung, H. Sebastian |
| author2 | Institute for Medical Engineering and Science |
| author_facet | Institute for Medical Engineering and Science Arganda-Carreras, Ignacio Turaga, Srinivas C. Berger, Daniel R. Cireşan, Dan Giusti, Alessandro Gambardella, Luca M. Schmidhuber, Jürgen Laptev, Dmitry Dwivedi, Sarvesh Buhmann, Joachim M. Liu, Ting Seyedhosseini, Mojtaba Tasdizen, Tolga Kamentsky, Lee Burget, Radim Uher, Vaclav Tan, Xiao Sun, Changming Pham, Tuan D. Bas, Erhan Uzunbas, Mustafa G. Cardona, Albert Schindelin, Johannes Seung, H. Sebastian |
| author_sort | Arganda-Carreras, Ignacio |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T12:03:52Z |
| format | Article |
| id | mit-1721.1/116672 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T12:03:52Z |
| publishDate | 2018 |
| publisher | Frontiers Media SA |
| record_format | dspace |
| spelling | mit-1721.1/1166722022-10-01T07:56:07Z Crowdsourcing the creation of image segmentation algorithms for connectomics Arganda-Carreras, Ignacio Turaga, Srinivas C. Berger, Daniel R. Cireşan, Dan Giusti, Alessandro Gambardella, Luca M. Schmidhuber, Jürgen Laptev, Dmitry Dwivedi, Sarvesh Buhmann, Joachim M. Liu, Ting Seyedhosseini, Mojtaba Tasdizen, Tolga Kamentsky, Lee Burget, Radim Uher, Vaclav Tan, Xiao Sun, Changming Pham, Tuan D. Bas, Erhan Uzunbas, Mustafa G. Cardona, Albert Schindelin, Johannes Seung, H. Sebastian Institute for Medical Engineering and Science Kamentsky, Lee 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. 2018-06-27T20:03:56Z 2018-06-27T20:03:56Z 2015-11 2015-05 2018-06-27T16:39:42Z Article http://purl.org/eprint/type/JournalArticle 1662-5129 http://hdl.handle.net/1721.1/116672 Arganda-Carreras, Ignacio, et al. “Crowdsourcing the Creation of Image Segmentation Algorithms for Connectomics.” Frontiers in Neuroanatomy, vol. 9, Nov. 2015. © 2015 The Authors https://orcid.org/0000-0002-8161-3604 http://dx.doi.org/10.3389/FNANA.2015.00142 Frontiers in Neuroanatomy Creative Commons Attribution 4.0 International License http://creativecommons.org/licenses/by/4.0/ application/pdf Frontiers Media SA Frontiers |
| spellingShingle | Arganda-Carreras, Ignacio Turaga, Srinivas C. Berger, Daniel R. Cireşan, Dan Giusti, Alessandro Gambardella, Luca M. Schmidhuber, Jürgen Laptev, Dmitry Dwivedi, Sarvesh Buhmann, Joachim M. Liu, Ting Seyedhosseini, Mojtaba Tasdizen, Tolga Kamentsky, Lee Burget, Radim Uher, Vaclav Tan, Xiao Sun, Changming Pham, Tuan D. Bas, Erhan Uzunbas, Mustafa G. Cardona, Albert Schindelin, Johannes Seung, H. Sebastian Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title | Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title_full | Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title_fullStr | Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title_full_unstemmed | Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title_short | Crowdsourcing the creation of image segmentation algorithms for connectomics |
| title_sort | crowdsourcing the creation of image segmentation algorithms for connectomics |
| url | http://hdl.handle.net/1721.1/116672 https://orcid.org/0000-0002-8161-3604 |
| work_keys_str_mv | AT argandacarrerasignacio crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT turagasrinivasc crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT bergerdanielr crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT ciresandan crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT giustialessandro crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT gambardellalucam crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT schmidhuberjurgen crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT laptevdmitry crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT dwivedisarvesh crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT buhmannjoachimm crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT liuting crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT seyedhosseinimojtaba crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT tasdizentolga crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT kamentskylee crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT burgetradim crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT uhervaclav crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT tanxiao crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT sunchangming crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT phamtuand crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT baserhan crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT uzunbasmustafag crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT cardonaalbert crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT schindelinjohannes crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics AT seunghsebastian crowdsourcingthecreationofimagesegmentationalgorithmsforconnectomics |