Statistical shape model with random walks for inner ear segmentation

Esmeralda Ruiz Pujadas; Hans Martin Kjer; Gemma Piella; Miguel Angel González Ballester

doi:10.1007/978-3-319-51237-2_8

Statistical shape model with random walks for inner ear segmentation

Esmeralda Ruiz Pujadas, Hans Martin Kjer, Gemma Piella, Miguel Angel González Ballester

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Cochlear implants can restore hearing to completely or partially deaf patients. The intervention planning can be aided by providing a patient-specific model of the inner ear. Such a model has to be built from high resolution images with accurate segmentations. Thus, a precise segmentation is required. We propose a new framework for segmentation of micro-CT cochlear images using random walks combined with a statistical shape model (SSM). The SSM allows us to constrain the less contrasted areas and ensures valid inner ear shape outputs. Additionally, a topology preservation method is proposed to avoid the leakage in the regions with no contrast.

Original language	English
Title of host publication	Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016)
Publisher	Springer
Publication date	2016
Pages	92-102
ISBN (Print)	978-3-319-51236-5
ISBN (Electronic)	978-3-319-51237-2
DOIs	https://doi.org/10.1007/978-3-319-51237-2_8
Publication status	Published - 2016
Event	1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016) - Athens, Greece Duration: 21 Oct 2016 → 21 Oct 2016 Conference number: 1 https://sites.google.com/site/sesami2016/

Workshop

Workshop	1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016)
Number	1
Country	Greece
City	Athens
Period	21/10/2016 → 21/10/2016
Internet address	https://sites.google.com/site/sesami2016/

Series	Lecture Notes in Computer Science
Volume	10126
ISSN	0302-9743

Keywords

Random walks
Segmentation
Shape prior
Iterative segmentation
Distance map prior
Statistical shape model
SSM
Cochlea segmentation
Inner ear segmentation

Access to Document

10.1007/978-3-319-51237-2_8

Fingerprint Dive into the research topics of 'Statistical shape model with random walks for inner ear segmentation'. Together they form a unique fingerprint.

Cite this

Pujadas, E. R., Kjer, H. M., Piella, G., & Ballester, M. A. G. (2016). Statistical shape model with random walks for inner ear segmentation. In Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016) (pp. 92-102). Springer. Lecture Notes in Computer Science Vol. 10126 https://doi.org/10.1007/978-3-319-51237-2_8

@inproceedings{e598da2b90b04dd9aa7ad05d11d2b6fd,

title = "Statistical shape model with random walks for inner ear segmentation",

abstract = "Cochlear implants can restore hearing to completely or partially deaf patients. The intervention planning can be aided by providing a patient-specific model of the inner ear. Such a model has to be built from high resolution images with accurate segmentations. Thus, a precise segmentation is required. We propose a new framework for segmentation of micro-CT cochlear images using random walks combined with a statistical shape model (SSM). The SSM allows us to constrain the less contrasted areas and ensures valid inner ear shape outputs. Additionally, a topology preservation method is proposed to avoid the leakage in the regions with no contrast.",

keywords = "Random walks, Segmentation, Shape prior, Iterative segmentation, Distance map prior, Statistical shape model, SSM, Cochlea segmentation, Inner ear segmentation",

author = "Pujadas, {Esmeralda Ruiz} and Kjer, {Hans Martin} and Gemma Piella and Ballester, {Miguel Angel Gonz{\'a}lez}",

year = "2016",

doi = "10.1007/978-3-319-51237-2_8",

language = "English",

isbn = "978-3-319-51236-5",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "92--102",

booktitle = "Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016)",

note = "1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016), SeSAMI ; Conference date: 21-10-2016 Through 21-10-2016",

url = "https://sites.google.com/site/sesami2016/",

}

Pujadas, ER, Kjer, HM, Piella, G & Ballester, MAG 2016, Statistical shape model with random walks for inner ear segmentation. in Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016). Springer, Lecture Notes in Computer Science, vol. 10126, pp. 92-102, 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016), Athens, Greece, 21/10/2016. https://doi.org/10.1007/978-3-319-51237-2_8

Statistical shape model with random walks for inner ear segmentation. / Pujadas, Esmeralda Ruiz; Kjer, Hans Martin; Piella, Gemma; Ballester, Miguel Angel González.

Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016). Springer, 2016. p. 92-102 (Lecture Notes in Computer Science, Vol. 10126).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Statistical shape model with random walks for inner ear segmentation

AU - Pujadas, Esmeralda Ruiz

AU - Kjer, Hans Martin

AU - Piella, Gemma

AU - Ballester, Miguel Angel González

N1 - Conference code: 1

PY - 2016

Y1 - 2016

N2 - Cochlear implants can restore hearing to completely or partially deaf patients. The intervention planning can be aided by providing a patient-specific model of the inner ear. Such a model has to be built from high resolution images with accurate segmentations. Thus, a precise segmentation is required. We propose a new framework for segmentation of micro-CT cochlear images using random walks combined with a statistical shape model (SSM). The SSM allows us to constrain the less contrasted areas and ensures valid inner ear shape outputs. Additionally, a topology preservation method is proposed to avoid the leakage in the regions with no contrast.

AB - Cochlear implants can restore hearing to completely or partially deaf patients. The intervention planning can be aided by providing a patient-specific model of the inner ear. Such a model has to be built from high resolution images with accurate segmentations. Thus, a precise segmentation is required. We propose a new framework for segmentation of micro-CT cochlear images using random walks combined with a statistical shape model (SSM). The SSM allows us to constrain the less contrasted areas and ensures valid inner ear shape outputs. Additionally, a topology preservation method is proposed to avoid the leakage in the regions with no contrast.

KW - Random walks

KW - Segmentation

KW - Shape prior

KW - Iterative segmentation

KW - Distance map prior

KW - Statistical shape model

KW - SSM

KW - Cochlea segmentation

KW - Inner ear segmentation

U2 - 10.1007/978-3-319-51237-2_8

DO - 10.1007/978-3-319-51237-2_8

M3 - Article in proceedings

SN - 978-3-319-51236-5

T3 - Lecture Notes in Computer Science

SP - 92

EP - 102

BT - Revised Selected Papers of the 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016)

PB - Springer

T2 - 1st International Workshop on Spectral and Shape Analysis in Medical Imaging (SeSAMI 2016)

Y2 - 21 October 2016 through 21 October 2016

ER -