Confidence of model based shape reconstruction from sparse data

N. Baka; Marleen de Bruijne; J. H. C. Reiber; Wiro Niessen; B. P. F. Lelieveldt

doi:10.1109/ISBI.2010.5490179

Confidence of model based shape reconstruction from sparse data

N. Baka, Marleen de Bruijne, J. H. C. Reiber, Wiro Niessen, B. P. F. Lelieveldt

Datalogisk Institut

11 Citationer (Scopus)

Abstract

Statistical shape models (SSM) are commonly applied for plausible interpolation of missing data in medical imaging. However, when fitting a shape model to sparse information, many solutions may fit the available data. In this paper we derive a constrained SSM to fit noisy sparse input landmarks and assign a confidence value to the resulting reconstructed shape. An evaluation study is performed to compare three methods used for sparse SSM fitting w.r.t. specificity, generalization ability, and correctness of estimated confidence limits with an increasing amount of input information. We find that the proposed constrained shape model outperforms the other models, is robust against the selection and amount of sparse information, and indicates the shape confidence well.

Originalsprog	Engelsk
Titel	2010 IEEE International Symposium on Biomedical Imaging : from nano to macro
Antal sider	4
Forlag	IEEE
Publikationsdato	2010
Sider	1077-1080
ISBN (Trykt)	978-1-4244-4125-9
ISBN (Elektronisk)	978-1-4244-4126-6
DOI	https://doi.org/10.1109/ISBI.2010.5490179
Status	Udgivet - 2010
Begivenhed	7th IEEE International Symposium on Biomedical Imaging: from nano to macro - Congress Center "De Doelen", Rotterdam, Holland Varighed: 14 apr. 2010 → 17 apr. 2010 Konferencens nummer: 7

Konference

Konference	7th IEEE International Symposium on Biomedical Imaging
Nummer	7
Lokation	Congress Center "De Doelen"
Land/Område	Holland
By	Rotterdam
Periode	14/04/2010 → 17/04/2010

Adgang til dokumentet

10.1109/ISBI.2010.5490179

Citationsformater

@inproceedings{a396c1b043fc11df928f000ea68e967b,

title = "Confidence of model based shape reconstruction from sparse data",

abstract = "Statistical shape models (SSM) are commonly applied for plausible interpolation of missing data in medical imaging. However, when fitting a shape model to sparse information, many solutions may fit the available data. In this paper we derive a constrained SSM to fit noisy sparse input landmarks and assign a confidence value to the resulting reconstructed shape. An evaluation study is performed to compare three methods used for sparse SSM fitting w.r.t. specificity, generalization ability, and correctness of estimated confidence limits with an increasing amount of input information. We find that the proposed constrained shape model outperforms the other models, is robust against the selection and amount of sparse information, and indicates the shape confidence well.",

author = "N. Baka and {de Bruijne}, Marleen and Reiber, {J. H. C.} and Wiro Niessen and Lelieveldt, {B. P. F.}",

year = "2010",

doi = "10.1109/ISBI.2010.5490179",

language = "English",

isbn = "978-1-4244-4125-9",

pages = "1077--1080",

booktitle = "2010 IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE",

note = "7th IEEE International Symposium on Biomedical Imaging : from nano to macro, ISBI 2010 ; Conference date: 14-04-2010 Through 17-04-2010",

}

TY - GEN

T1 - Confidence of model based shape reconstruction from sparse data

AU - Baka, N.

AU - de Bruijne, Marleen

AU - Reiber, J. H. C.

AU - Niessen, Wiro

AU - Lelieveldt, B. P. F.

N1 - Conference code: 7

PY - 2010

Y1 - 2010

N2 - Statistical shape models (SSM) are commonly applied for plausible interpolation of missing data in medical imaging. However, when fitting a shape model to sparse information, many solutions may fit the available data. In this paper we derive a constrained SSM to fit noisy sparse input landmarks and assign a confidence value to the resulting reconstructed shape. An evaluation study is performed to compare three methods used for sparse SSM fitting w.r.t. specificity, generalization ability, and correctness of estimated confidence limits with an increasing amount of input information. We find that the proposed constrained shape model outperforms the other models, is robust against the selection and amount of sparse information, and indicates the shape confidence well.

AB - Statistical shape models (SSM) are commonly applied for plausible interpolation of missing data in medical imaging. However, when fitting a shape model to sparse information, many solutions may fit the available data. In this paper we derive a constrained SSM to fit noisy sparse input landmarks and assign a confidence value to the resulting reconstructed shape. An evaluation study is performed to compare three methods used for sparse SSM fitting w.r.t. specificity, generalization ability, and correctness of estimated confidence limits with an increasing amount of input information. We find that the proposed constrained shape model outperforms the other models, is robust against the selection and amount of sparse information, and indicates the shape confidence well.

U2 - 10.1109/ISBI.2010.5490179

DO - 10.1109/ISBI.2010.5490179

M3 - Article in proceedings

SN - 978-1-4244-4125-9

SP - 1077

EP - 1080

BT - 2010 IEEE International Symposium on Biomedical Imaging

PB - IEEE

T2 - 7th IEEE International Symposium on Biomedical Imaging

Y2 - 14 April 2010 through 17 April 2010

ER -

Confidence of model based shape reconstruction from sparse data

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater