A non-linear diffeomorphic framework for prostate multimodal registration

Jhimli Mitra, Z. Kato, Robert Martí, Arnau Oliver, Xavier Lladó, Soumya Ghose, Joan C. Vilanova, Fabrice Meriaudeau

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively.

Original languageEnglish
Title of host publicationProceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011
Pages31-36
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011 - Noosa, QLD, Australia
Duration: Dec 6 2011Dec 8 2011

Other

Other2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011
CountryAustralia
CityNoosa, QLD
Period12/6/1112/8/11

Fingerprint

Splines
Nonlinear equations
Magnetic resonance
Ultrasonics

Keywords

  • magnetic resonance
  • multimodal fusion
  • non-linear diffeomorphism
  • point correspondences
  • Prostate biopsy
  • thin-plate splines
  • transrectal ultrasound

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Mitra, J., Kato, Z., Martí, R., Oliver, A., Lladó, X., Ghose, S., ... Meriaudeau, F. (2011). A non-linear diffeomorphic framework for prostate multimodal registration. In Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011 (pp. 31-36). [6128656] https://doi.org/10.1109/DICTA.2011.14

A non-linear diffeomorphic framework for prostate multimodal registration. / Mitra, Jhimli; Kato, Z.; Martí, Robert; Oliver, Arnau; Lladó, Xavier; Ghose, Soumya; Vilanova, Joan C.; Meriaudeau, Fabrice.

Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011. 2011. p. 31-36 6128656.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mitra, J, Kato, Z, Martí, R, Oliver, A, Lladó, X, Ghose, S, Vilanova, JC & Meriaudeau, F 2011, A non-linear diffeomorphic framework for prostate multimodal registration. in Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011., 6128656, pp. 31-36, 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011, Noosa, QLD, Australia, 12/6/11. https://doi.org/10.1109/DICTA.2011.14
Mitra J, Kato Z, Martí R, Oliver A, Lladó X, Ghose S et al. A non-linear diffeomorphic framework for prostate multimodal registration. In Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011. 2011. p. 31-36. 6128656 https://doi.org/10.1109/DICTA.2011.14
Mitra, Jhimli ; Kato, Z. ; Martí, Robert ; Oliver, Arnau ; Lladó, Xavier ; Ghose, Soumya ; Vilanova, Joan C. ; Meriaudeau, Fabrice. / A non-linear diffeomorphic framework for prostate multimodal registration. Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011. 2011. pp. 31-36
@inproceedings{91ab67cee0ae4e428c50996148037f41,
title = "A non-linear diffeomorphic framework for prostate multimodal registration",
abstract = "This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95{\%} Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively.",
keywords = "magnetic resonance, multimodal fusion, non-linear diffeomorphism, point correspondences, Prostate biopsy, thin-plate splines, transrectal ultrasound",
author = "Jhimli Mitra and Z. Kato and Robert Mart{\'i} and Arnau Oliver and Xavier Llad{\'o} and Soumya Ghose and Vilanova, {Joan C.} and Fabrice Meriaudeau",
year = "2011",
doi = "10.1109/DICTA.2011.14",
language = "English",
isbn = "9780769545882",
pages = "31--36",
booktitle = "Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011",

}

TY - GEN

T1 - A non-linear diffeomorphic framework for prostate multimodal registration

AU - Mitra, Jhimli

AU - Kato, Z.

AU - Martí, Robert

AU - Oliver, Arnau

AU - Lladó, Xavier

AU - Ghose, Soumya

AU - Vilanova, Joan C.

AU - Meriaudeau, Fabrice

PY - 2011

Y1 - 2011

N2 - This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively.

AB - This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively.

KW - magnetic resonance

KW - multimodal fusion

KW - non-linear diffeomorphism

KW - point correspondences

KW - Prostate biopsy

KW - thin-plate splines

KW - transrectal ultrasound

UR - http://www.scopus.com/inward/record.url?scp=84856980939&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856980939&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2011.14

DO - 10.1109/DICTA.2011.14

M3 - Conference contribution

AN - SCOPUS:84856980939

SN - 9780769545882

SP - 31

EP - 36

BT - Proceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011

ER -