Standard

Ensemble landmarking of 3D facial surface scans. / De Jong, Markus A.; Hysi, Pirro; Spector, Tim; Niessen, Wiro; Koudstaal, Maarten J.; Wolvius, Eppo B.; Kayser, Manfred; Böhringer, Stefan.

In: Scientific Reports, Vol. 8, No. 1, 12, 08.01.2018.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

De Jong, MA, Hysi, P, Spector, T, Niessen, W, Koudstaal, MJ, Wolvius, EB, Kayser, M & Böhringer, S 2018, 'Ensemble landmarking of 3D facial surface scans' Scientific Reports, vol. 8, no. 1, 12. https://doi.org/10.1038/s41598-017-18294-x

APA

De Jong, M. A., Hysi, P., Spector, T., Niessen, W., Koudstaal, M. J., Wolvius, E. B., ... Böhringer, S. (2018). Ensemble landmarking of 3D facial surface scans. Scientific Reports, 8(1), [12]. https://doi.org/10.1038/s41598-017-18294-x

Vancouver

De Jong MA, Hysi P, Spector T, Niessen W, Koudstaal MJ, Wolvius EB et al. Ensemble landmarking of 3D facial surface scans. Scientific Reports. 2018 Jan 8;8(1). 12. https://doi.org/10.1038/s41598-017-18294-x

Author

De Jong, Markus A. ; Hysi, Pirro ; Spector, Tim ; Niessen, Wiro ; Koudstaal, Maarten J. ; Wolvius, Eppo B. ; Kayser, Manfred ; Böhringer, Stefan. / Ensemble landmarking of 3D facial surface scans. In: Scientific Reports. 2018 ; Vol. 8, No. 1.

BibTeX

@article{7486481e1e2e423397c7e122cc5d1cf6,
title = "Ensemble landmarking of 3D facial surface scans",
abstract = "Landmarking of 3D facial surface scans is an important analysis step in medical and biological applications, such as genome-wide association studies (GWAS). Manual landmarking is often employed with considerable cost and rater dependent variability. Landmarking automatically with minimal training is therefore desirable. We apply statistical ensemble methods to improve automated landmarking of 3D facial surface scans. Base landmarking algorithms using features derived from 3D surface scans are combined using either bagging or stacking. A focus is on low training complexity of maximal 40 training samples with template based landmarking algorithms that have proved successful in such applications. Additionally, we use correlations between landmark coordinates by introducing a search strategy guided by principal components (PCs) of training landmarks. We found that bagging has no useful impact, while stacking strongly improves accuracy to an average error of 1.7 mm across all 21 landmarks in this study, a 22{\%} improvement as compared to a previous, comparable algorithm. Heritability estimates in twin pairs also show improvements when using facial distances from landmarks. Ensemble methods allow improvement of automatic, accurate landmarking of 3D facial images with minimal training which is advantageous in large cohort studies for GWAS and when landmarking needs change or data quality varies.",
author = "{De Jong}, {Markus A.} and Pirro Hysi and Tim Spector and Wiro Niessen and Koudstaal, {Maarten J.} and Wolvius, {Eppo B.} and Manfred Kayser and Stefan B{\"o}hringer",
year = "2018",
month = "1",
day = "8",
doi = "10.1038/s41598-017-18294-x",
language = "English",
volume = "8",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

RIS

TY - JOUR

T1 - Ensemble landmarking of 3D facial surface scans

AU - De Jong, Markus A.

AU - Hysi, Pirro

AU - Spector, Tim

AU - Niessen, Wiro

AU - Koudstaal, Maarten J.

AU - Wolvius, Eppo B.

AU - Kayser, Manfred

AU - Böhringer, Stefan

PY - 2018/1/8

Y1 - 2018/1/8

N2 - Landmarking of 3D facial surface scans is an important analysis step in medical and biological applications, such as genome-wide association studies (GWAS). Manual landmarking is often employed with considerable cost and rater dependent variability. Landmarking automatically with minimal training is therefore desirable. We apply statistical ensemble methods to improve automated landmarking of 3D facial surface scans. Base landmarking algorithms using features derived from 3D surface scans are combined using either bagging or stacking. A focus is on low training complexity of maximal 40 training samples with template based landmarking algorithms that have proved successful in such applications. Additionally, we use correlations between landmark coordinates by introducing a search strategy guided by principal components (PCs) of training landmarks. We found that bagging has no useful impact, while stacking strongly improves accuracy to an average error of 1.7 mm across all 21 landmarks in this study, a 22% improvement as compared to a previous, comparable algorithm. Heritability estimates in twin pairs also show improvements when using facial distances from landmarks. Ensemble methods allow improvement of automatic, accurate landmarking of 3D facial images with minimal training which is advantageous in large cohort studies for GWAS and when landmarking needs change or data quality varies.

AB - Landmarking of 3D facial surface scans is an important analysis step in medical and biological applications, such as genome-wide association studies (GWAS). Manual landmarking is often employed with considerable cost and rater dependent variability. Landmarking automatically with minimal training is therefore desirable. We apply statistical ensemble methods to improve automated landmarking of 3D facial surface scans. Base landmarking algorithms using features derived from 3D surface scans are combined using either bagging or stacking. A focus is on low training complexity of maximal 40 training samples with template based landmarking algorithms that have proved successful in such applications. Additionally, we use correlations between landmark coordinates by introducing a search strategy guided by principal components (PCs) of training landmarks. We found that bagging has no useful impact, while stacking strongly improves accuracy to an average error of 1.7 mm across all 21 landmarks in this study, a 22% improvement as compared to a previous, comparable algorithm. Heritability estimates in twin pairs also show improvements when using facial distances from landmarks. Ensemble methods allow improvement of automatic, accurate landmarking of 3D facial images with minimal training which is advantageous in large cohort studies for GWAS and when landmarking needs change or data quality varies.

UR - http://resolverlink.tudelft.nl/uuid:7486481e-1e2e-4233-97c7-e122cc5d1cf6

UR - http://www.scopus.com/inward/record.url?scp=85042784618&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-18294-x

DO - 10.1038/s41598-017-18294-x

M3 - Article

VL - 8

JO - Scientific Reports

T2 - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 12

ER -

ID: 44962483