From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization

Darko Stern, Thomas Ebner, Martin Urschler

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Buch/BerichtForschungBegutachtung

Abstract

State of the art anatomical landmark localization algorithms pair local Random Forest (RF) detection with disambiguation of locally similar structures by including high level knowledge about relative landmark locations. In this work we pursue the question, how much high-level knowledge is needed in addition to a single landmark localization RF to implicitly model the global configuration of multiple, potentially ambiguous landmarks. We further propose a novel RF localization algorithm that distinguishes locally similar structures by automatically identifying them, exploring the back-projection of the response from accurate local RF predictions. In our experiments we show that this approach achieves competitive results in single and multi-landmark localization when applied to 2D hand radiographic and 3D teeth MRI data sets. Additionally, when combined with a simple Markov Random Field model, we are able to outperform state of the art methods.
Originalspracheenglisch
TitelMedical Image Computing and Computer-Assisted Intervention – MICCAI 2016
Untertitel19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II
Redakteure/-innenSebastien Ourselin, Leo Joskowicz, Mert R. Sabuncu, Gozde Unal, William Wells
Herausgeber (Verlag)Springer International Publishing AG
Seiten221-229
Seitenumfang9
Band9901
ISBN (elektronisch)978-3-319-46723-8
ISBN (Print)978-3-319-46722-1
DOIs
PublikationsstatusVeröffentlicht - 21 Okt 2016
Veranstaltung19th International Conference on Medical Image Computing & Computer Assisted Intervention - Intercontinental Athenaeum, Athens, Griechenland
Dauer: 17 Okt 201621 Okt 2016
http://www.miccai2016.org

Publikationsreihe

NameLecture Notes in Computer Science
Herausgeber (Verlag)Springer

Konferenz

Konferenz19th International Conference on Medical Image Computing & Computer Assisted Intervention
KurztitelMICCAI
LandGriechenland
OrtAthens
Zeitraum17/10/1621/10/16
Internetadresse

Fingerprint

Magnetic resonance imaging
Experiments

Fields of Expertise

  • Information, Communication & Computing

Kooperationen

  • BioTechMed-Graz

Dies zitieren

Stern, D., Ebner, T., & Urschler, M. (2016). From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization. in S. Ourselin, L. Joskowicz, M. R. Sabuncu, G. Unal, & W. Wells (Hrsg.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II (Band 9901, S. 221-229). (Lecture Notes in Computer Science). Springer International Publishing AG . https://doi.org/10.1007/978-3-319-46723-8_26

From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization. / Stern, Darko; Ebner, Thomas; Urschler, Martin.

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II. Hrsg. / Sebastien Ourselin; Leo Joskowicz; Mert R. Sabuncu; Gozde Unal; William Wells. Band 9901 Springer International Publishing AG , 2016. S. 221-229 (Lecture Notes in Computer Science).

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Buch/BerichtForschungBegutachtung

Stern, D, Ebner, T & Urschler, M 2016, From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization. in S Ourselin, L Joskowicz, MR Sabuncu, G Unal & W Wells (Hrsg.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II. Bd. 9901, Lecture Notes in Computer Science, Springer International Publishing AG , S. 221-229, Athens, Griechenland, 17/10/16. https://doi.org/10.1007/978-3-319-46723-8_26
Stern D, Ebner T, Urschler M. From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization. in Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W, Hrsg., Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II. Band 9901. Springer International Publishing AG . 2016. S. 221-229. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-46723-8_26
Stern, Darko ; Ebner, Thomas ; Urschler, Martin. / From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II. Hrsg. / Sebastien Ourselin ; Leo Joskowicz ; Mert R. Sabuncu ; Gozde Unal ; William Wells. Band 9901 Springer International Publishing AG , 2016. S. 221-229 (Lecture Notes in Computer Science).
@inbook{c56be3bed8b34461b74af50c47bf4fca,
title = "From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization",
abstract = "State of the art anatomical landmark localization algorithms pair local Random Forest (RF) detection with disambiguation of locally similar structures by including high level knowledge about relative landmark locations. In this work we pursue the question, how much high-level knowledge is needed in addition to a single landmark localization RF to implicitly model the global configuration of multiple, potentially ambiguous landmarks. We further propose a novel RF localization algorithm that distinguishes locally similar structures by automatically identifying them, exploring the back-projection of the response from accurate local RF predictions. In our experiments we show that this approach achieves competitive results in single and multi-landmark localization when applied to 2D hand radiographic and 3D teeth MRI data sets. Additionally, when combined with a simple Markov Random Field model, we are able to outperform state of the art methods.",
author = "Darko Stern and Thomas Ebner and Martin Urschler",
year = "2016",
month = "10",
day = "21",
doi = "10.1007/978-3-319-46723-8_26",
language = "English",
isbn = "978-3-319-46722-1",
volume = "9901",
series = "Lecture Notes in Computer Science",
publisher = "Springer International Publishing AG",
pages = "221--229",
editor = "Sebastien Ourselin and Leo Joskowicz and Sabuncu, {Mert R.} and Gozde Unal and William Wells",
booktitle = "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016",
address = "Switzerland",

}

TY - CHAP

T1 - From Local to Global Random Regression Forests: Exploring Anatomical Landmark Localization

AU - Stern, Darko

AU - Ebner, Thomas

AU - Urschler, Martin

PY - 2016/10/21

Y1 - 2016/10/21

N2 - State of the art anatomical landmark localization algorithms pair local Random Forest (RF) detection with disambiguation of locally similar structures by including high level knowledge about relative landmark locations. In this work we pursue the question, how much high-level knowledge is needed in addition to a single landmark localization RF to implicitly model the global configuration of multiple, potentially ambiguous landmarks. We further propose a novel RF localization algorithm that distinguishes locally similar structures by automatically identifying them, exploring the back-projection of the response from accurate local RF predictions. In our experiments we show that this approach achieves competitive results in single and multi-landmark localization when applied to 2D hand radiographic and 3D teeth MRI data sets. Additionally, when combined with a simple Markov Random Field model, we are able to outperform state of the art methods.

AB - State of the art anatomical landmark localization algorithms pair local Random Forest (RF) detection with disambiguation of locally similar structures by including high level knowledge about relative landmark locations. In this work we pursue the question, how much high-level knowledge is needed in addition to a single landmark localization RF to implicitly model the global configuration of multiple, potentially ambiguous landmarks. We further propose a novel RF localization algorithm that distinguishes locally similar structures by automatically identifying them, exploring the back-projection of the response from accurate local RF predictions. In our experiments we show that this approach achieves competitive results in single and multi-landmark localization when applied to 2D hand radiographic and 3D teeth MRI data sets. Additionally, when combined with a simple Markov Random Field model, we are able to outperform state of the art methods.

U2 - 10.1007/978-3-319-46723-8_26

DO - 10.1007/978-3-319-46723-8_26

M3 - Chapter

SN - 978-3-319-46722-1

VL - 9901

T3 - Lecture Notes in Computer Science

SP - 221

EP - 229

BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016

A2 - Ourselin, Sebastien

A2 - Joskowicz, Leo

A2 - Sabuncu, Mert R.

A2 - Unal, Gozde

A2 - Wells, William

PB - Springer International Publishing AG

ER -