Computational anatomy in Theano

Line Kühnel; Stefan Horst Sommer

doi:10.1007/978-3-319-67675-3_15

Computational anatomy in Theano

Line Kühnel, Stefan Horst Sommer

Datalogisk Institut

5 Citationer (Scopus)

Abstract

To model deformation of anatomical shapes, non-linear statistics are required to take into account the non-linear structure of the data space. Computer implementations of non-linear statistics and differential geometry algorithms often lead to long and complex code sequences. The aim of the paper is to show how the Theano framework can be used for simple and concise implementation of complex differential geometry algorithms while being able to handle complex and high-dimensional data structures. We show how the Theano framework meets both of these requirements. The framework provides a symbolic language that allows mathematical equations to be directly translated into Theano code, and it is able to perform both fast CPU and GPU computations on high-dimensional data. We show how different concepts from non-linear statistics and differential geometry can be implemented in Theano, and give examples of the implemented theory visualized on landmark representations of Corpus Callosum shapes.

Originalsprog	Engelsk
Titel	Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics : First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings
Redaktører	J. Cardoso, T. Arbel, E. Ferrante, X. Pennec, A. Dalca, S. Parisot, S. Joshi, N. K. Batmanghelich, A. Sotiras, M. Nielsen, M. R. Sabuncu, T. Fletcher, L. Shen, S. Durrleman, S. Sommer
Antal sider	13
Forlag	Springer
Publikationsdato	2017
Sider	164-176
ISBN (Trykt)	978-3-319-67674-6
ISBN (Elektronisk)	978-3-319-67675-3
DOI	https://doi.org/10.1007/978-3-319-67675-3_15
Status	Udgivet - 2017
Begivenhed	6th International Workshop on Mathematical Foundations of Computational Anatomy - Québec City, Canada Varighed: 10 sep. 2017 → 14 sep. 2017 Konferencens nummer: 6

Konference

Konference	6th International Workshop on Mathematical Foundations of Computational Anatomy
Nummer	6
Land/Område	Canada
By	Québec City
Periode	10/09/2017 → 14/09/2017

Navn	Lecture notes in computer science
Vol/bind	10551
ISSN	0302-9743

Adgang til dokumentet

10.1007/978-3-319-67675-3_15

https://arxiv.org/pdf/1706.07690.pdf

Citationsformater

Kühnel, L., & Sommer, S. H. (2017). Computational anatomy in Theano. I J. Cardoso, T. Arbel, E. Ferrante, X. Pennec, A. Dalca, S. Parisot, S. Joshi, N. K. Batmanghelich, A. Sotiras, M. Nielsen, M. R. Sabuncu, T. Fletcher, L. Shen, S. Durrleman, & S. Sommer (red.), Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics: First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings (s. 164-176). Springer. https://doi.org/10.1007/978-3-319-67675-3_15

Computational anatomy in Theano. / Kühnel, Line; Sommer, Stefan Horst.
Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics: First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings. red. / J. Cardoso; T. Arbel; E. Ferrante; X. Pennec; A. Dalca; S. Parisot; S. Joshi; N. K. Batmanghelich; A. Sotiras; M. Nielsen; M. R. Sabuncu; T. Fletcher; L. Shen; S. Durrleman; S. Sommer. Springer, 2017. s. 164-176 (Lecture notes in computer science, Bind 10551).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Kühnel, L & Sommer, SH 2017, Computational anatomy in Theano. i J Cardoso, T Arbel, E Ferrante, X Pennec, A Dalca, S Parisot, S Joshi, NK Batmanghelich, A Sotiras, M Nielsen, MR Sabuncu, T Fletcher, L Shen, S Durrleman & S Sommer (red), Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics: First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings. Springer, Lecture notes in computer science, bind 10551, s. 164-176, 6th International Workshop on Mathematical Foundations of Computational Anatomy, Québec City, Canada, 10/09/2017. https://doi.org/10.1007/978-3-319-67675-3_15

Kühnel L, Sommer SH. Computational anatomy in Theano. I Cardoso J, Arbel T, Ferrante E, Pennec X, Dalca A, Parisot S, Joshi S, Batmanghelich NK, Sotiras A, Nielsen M, Sabuncu MR, Fletcher T, Shen L, Durrleman S, Sommer S, red., Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics: First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings. Springer. 2017. s. 164-176. (Lecture notes in computer science, Bind 10551). doi: 10.1007/978-3-319-67675-3_15

Kühnel, Line ; Sommer, Stefan Horst. / Computational anatomy in Theano. Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics: First International Workshop, GRAIL 2017, 6th International Workshop, MFCA 2017, and Third International Workshop, MICGen 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 10–14, 2017, Proceedings. red. / J. Cardoso ; T. Arbel ; E. Ferrante ; X. Pennec ; A. Dalca ; S. Parisot ; S. Joshi ; N. K. Batmanghelich ; A. Sotiras ; M. Nielsen ; M. R. Sabuncu ; T. Fletcher ; L. Shen ; S. Durrleman ; S. Sommer. Springer, 2017. s. 164-176 (Lecture notes in computer science, Bind 10551).

@inproceedings{bc73ccc38876408ba39ed540e9f7f64b,

title = "Computational anatomy in Theano",

abstract = "To model deformation of anatomical shapes, non-linear statistics are required to take into account the non-linear structure of the data space. Computer implementations of non-linear statistics and differential geometry algorithms often lead to long and complex code sequences. The aim of the paper is to show how the Theano framework can be used for simple and concise implementation of complex differential geometry algorithms while being able to handle complex and high-dimensional data structures. We show how the Theano framework meets both of these requirements. The framework provides a symbolic language that allows mathematical equations to be directly translated into Theano code, and it is able to perform both fast CPU and GPU computations on high-dimensional data. We show how different concepts from non-linear statistics and differential geometry can be implemented in Theano, and give examples of the implemented theory visualized on landmark representations of Corpus Callosum shapes.",

author = "Line K{\"u}hnel and Sommer, {Stefan Horst}",

year = "2017",

doi = "10.1007/978-3-319-67675-3_15",

language = "English",

isbn = "978-3-319-67674-6",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "164--176",

editor = "J. Cardoso and T. Arbel and E. Ferrante and X. Pennec and A. Dalca and S. Parisot and S. Joshi and Batmanghelich, {N. K.} and A. Sotiras and M. Nielsen and Sabuncu, {M. R.} and T. Fletcher and L. Shen and S. Durrleman and S. Sommer",

booktitle = "Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics",

note = "6th International Workshop on Mathematical Foundations of Computational Anatomy ; Conference date: 10-09-2017 Through 14-09-2017",

}

TY - GEN

T1 - Computational anatomy in Theano

AU - Kühnel, Line

AU - Sommer, Stefan Horst

N1 - Conference code: 6

PY - 2017

Y1 - 2017

N2 - To model deformation of anatomical shapes, non-linear statistics are required to take into account the non-linear structure of the data space. Computer implementations of non-linear statistics and differential geometry algorithms often lead to long and complex code sequences. The aim of the paper is to show how the Theano framework can be used for simple and concise implementation of complex differential geometry algorithms while being able to handle complex and high-dimensional data structures. We show how the Theano framework meets both of these requirements. The framework provides a symbolic language that allows mathematical equations to be directly translated into Theano code, and it is able to perform both fast CPU and GPU computations on high-dimensional data. We show how different concepts from non-linear statistics and differential geometry can be implemented in Theano, and give examples of the implemented theory visualized on landmark representations of Corpus Callosum shapes.

AB - To model deformation of anatomical shapes, non-linear statistics are required to take into account the non-linear structure of the data space. Computer implementations of non-linear statistics and differential geometry algorithms often lead to long and complex code sequences. The aim of the paper is to show how the Theano framework can be used for simple and concise implementation of complex differential geometry algorithms while being able to handle complex and high-dimensional data structures. We show how the Theano framework meets both of these requirements. The framework provides a symbolic language that allows mathematical equations to be directly translated into Theano code, and it is able to perform both fast CPU and GPU computations on high-dimensional data. We show how different concepts from non-linear statistics and differential geometry can be implemented in Theano, and give examples of the implemented theory visualized on landmark representations of Corpus Callosum shapes.

U2 - 10.1007/978-3-319-67675-3_15

DO - 10.1007/978-3-319-67675-3_15

M3 - Article in proceedings

SN - 978-3-319-67674-6

T3 - Lecture notes in computer science

SP - 164

EP - 176

BT - Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics

A2 - Cardoso, J.

A2 - Arbel, T.

A2 - Ferrante, E.

A2 - Pennec, X.

A2 - Dalca, A.

A2 - Parisot, S.

A2 - Joshi, S.

A2 - Batmanghelich, N. K.

A2 - Sotiras, A.

A2 - Nielsen, M.

A2 - Sabuncu, M. R.

A2 - Fletcher, T.

A2 - Shen, L.

A2 - Durrleman, S.

A2 - Sommer, S.

PB - Springer

T2 - 6th International Workshop on Mathematical Foundations of Computational Anatomy

Y2 - 10 September 2017 through 14 September 2017

ER -

Computational anatomy in Theano

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater