Surface-to-surface registration using level sets

Mads Fogtmann Hansen, Søren G. Erbou, Martin Vester-Christensen, Rasmus Larsen, Bjarne Kjær Ersbøll, Lars Bager Christensen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    This paper presents a general approach for surface-to-surface registration (S2SR) with the Euclidean metric using signed distance maps. In addition, the method is symmetric such that the registration of a shape A to a shape B is identical to the registration of the shape B to the shape A. The S2SR problem can be approximated by the image registration (IR) problem of the signed distance maps (SDMs) of the surfaces confined to some narrow band. By shrinking the narrow bands around the zero level sets the solution to the IR problem converges towards the S2SR problem. It is our hypothesis that this approach is more robust and less prone to fall into local minima than ordinary surface-to-surface registration. The IR problem is solved using the inverse compositional algorithm. In this paper, a set of 40 pelvic bones of Duroc pigs are registered to each other w.r.t. the Euclidean transformation with both the S2SR approach and iterative closest point approach, and the results are compared.
    Original languageEnglish
    Title of host publicationLecture Notes in Computer Science : Scandinavian Conference on Image Analysis
    EditorsBjarne Kjær Ersbøll, Kim Steenstrup Pedersen
    Volume4522
    Place of PublicationBerlin / Heidelberg
    PublisherSpringer
    Publication date2007
    Pages780-788
    ISBN (Print)978-3-540-73039-2
    DOIs
    Publication statusPublished - 2007
    Event15th Scandinavian Conference on Image Analysis (SCIA) - Aalborg, Denmark
    Duration: 1 Jan 2007 → …

    Conference

    Conference15th Scandinavian Conference on Image Analysis (SCIA)
    CountryDenmark
    CityAalborg
    Period01/01/2007 → …

    Cite this

    Hansen, M. F., Erbou, S. G., Vester-Christensen, M., Larsen, R., Ersbøll, B. K., & Christensen, L. B. (2007). Surface-to-surface registration using level sets. In B. K. Ersbøll, & K. S. Pedersen (Eds.), Lecture Notes in Computer Science: Scandinavian Conference on Image Analysis (Vol. 4522, pp. 780-788). Berlin / Heidelberg: Springer. https://doi.org/10.1007/978-3-540-73040-8_79
    Hansen, Mads Fogtmann ; Erbou, Søren G. ; Vester-Christensen, Martin ; Larsen, Rasmus ; Ersbøll, Bjarne Kjær ; Christensen, Lars Bager. / Surface-to-surface registration using level sets. Lecture Notes in Computer Science: Scandinavian Conference on Image Analysis. editor / Bjarne Kjær Ersbøll ; Kim Steenstrup Pedersen. Vol. 4522 Berlin / Heidelberg : Springer, 2007. pp. 780-788
    @inproceedings{2ac99053327c4cc4b9bf6a1f9ad1e264,
    title = "Surface-to-surface registration using level sets",
    abstract = "This paper presents a general approach for surface-to-surface registration (S2SR) with the Euclidean metric using signed distance maps. In addition, the method is symmetric such that the registration of a shape A to a shape B is identical to the registration of the shape B to the shape A. The S2SR problem can be approximated by the image registration (IR) problem of the signed distance maps (SDMs) of the surfaces confined to some narrow band. By shrinking the narrow bands around the zero level sets the solution to the IR problem converges towards the S2SR problem. It is our hypothesis that this approach is more robust and less prone to fall into local minima than ordinary surface-to-surface registration. The IR problem is solved using the inverse compositional algorithm. In this paper, a set of 40 pelvic bones of Duroc pigs are registered to each other w.r.t. the Euclidean transformation with both the S2SR approach and iterative closest point approach, and the results are compared.",
    author = "Hansen, {Mads Fogtmann} and Erbou, {S{\o}ren G.} and Martin Vester-Christensen and Rasmus Larsen and Ersb{\o}ll, {Bjarne Kj{\ae}r} and Christensen, {Lars Bager}",
    year = "2007",
    doi = "10.1007/978-3-540-73040-8_79",
    language = "English",
    isbn = "978-3-540-73039-2",
    volume = "4522",
    pages = "780--788",
    editor = "Ersb{\o}ll, {Bjarne Kj{\ae}r} and Pedersen, {Kim Steenstrup}",
    booktitle = "Lecture Notes in Computer Science",
    publisher = "Springer",

    }

    Hansen, MF, Erbou, SG, Vester-Christensen, M, Larsen, R, Ersbøll, BK & Christensen, LB 2007, Surface-to-surface registration using level sets. in BK Ersbøll & KS Pedersen (eds), Lecture Notes in Computer Science: Scandinavian Conference on Image Analysis. vol. 4522, Springer, Berlin / Heidelberg, pp. 780-788, 15th Scandinavian Conference on Image Analysis (SCIA), Aalborg, Denmark, 01/01/2007. https://doi.org/10.1007/978-3-540-73040-8_79

    Surface-to-surface registration using level sets. / Hansen, Mads Fogtmann; Erbou, Søren G.; Vester-Christensen, Martin; Larsen, Rasmus; Ersbøll, Bjarne Kjær; Christensen, Lars Bager.

    Lecture Notes in Computer Science: Scandinavian Conference on Image Analysis. ed. / Bjarne Kjær Ersbøll; Kim Steenstrup Pedersen. Vol. 4522 Berlin / Heidelberg : Springer, 2007. p. 780-788.

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    TY - GEN

    T1 - Surface-to-surface registration using level sets

    AU - Hansen, Mads Fogtmann

    AU - Erbou, Søren G.

    AU - Vester-Christensen, Martin

    AU - Larsen, Rasmus

    AU - Ersbøll, Bjarne Kjær

    AU - Christensen, Lars Bager

    PY - 2007

    Y1 - 2007

    N2 - This paper presents a general approach for surface-to-surface registration (S2SR) with the Euclidean metric using signed distance maps. In addition, the method is symmetric such that the registration of a shape A to a shape B is identical to the registration of the shape B to the shape A. The S2SR problem can be approximated by the image registration (IR) problem of the signed distance maps (SDMs) of the surfaces confined to some narrow band. By shrinking the narrow bands around the zero level sets the solution to the IR problem converges towards the S2SR problem. It is our hypothesis that this approach is more robust and less prone to fall into local minima than ordinary surface-to-surface registration. The IR problem is solved using the inverse compositional algorithm. In this paper, a set of 40 pelvic bones of Duroc pigs are registered to each other w.r.t. the Euclidean transformation with both the S2SR approach and iterative closest point approach, and the results are compared.

    AB - This paper presents a general approach for surface-to-surface registration (S2SR) with the Euclidean metric using signed distance maps. In addition, the method is symmetric such that the registration of a shape A to a shape B is identical to the registration of the shape B to the shape A. The S2SR problem can be approximated by the image registration (IR) problem of the signed distance maps (SDMs) of the surfaces confined to some narrow band. By shrinking the narrow bands around the zero level sets the solution to the IR problem converges towards the S2SR problem. It is our hypothesis that this approach is more robust and less prone to fall into local minima than ordinary surface-to-surface registration. The IR problem is solved using the inverse compositional algorithm. In this paper, a set of 40 pelvic bones of Duroc pigs are registered to each other w.r.t. the Euclidean transformation with both the S2SR approach and iterative closest point approach, and the results are compared.

    U2 - 10.1007/978-3-540-73040-8_79

    DO - 10.1007/978-3-540-73040-8_79

    M3 - Article in proceedings

    SN - 978-3-540-73039-2

    VL - 4522

    SP - 780

    EP - 788

    BT - Lecture Notes in Computer Science

    A2 - Ersbøll, Bjarne Kjær

    A2 - Pedersen, Kim Steenstrup

    PB - Springer

    CY - Berlin / Heidelberg

    ER -

    Hansen MF, Erbou SG, Vester-Christensen M, Larsen R, Ersbøll BK, Christensen LB. Surface-to-surface registration using level sets. In Ersbøll BK, Pedersen KS, editors, Lecture Notes in Computer Science: Scandinavian Conference on Image Analysis. Vol. 4522. Berlin / Heidelberg: Springer. 2007. p. 780-788 https://doi.org/10.1007/978-3-540-73040-8_79