Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images

Samaneh Mazaheri, Puteri Suhaiza Sulaiman, Rahmita Wirza, Mohd Zamrin Dimon, Fatimah Khalid, Rohollah Moosavi Tayebi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order to utilize both computed tomography (CT) and echocardiography images of the heart for medical applications such as diagnosis and image guided intervention concurrently, non-rigid registration is an essential task. A challenging but important problem in image registration is evaluating the performance of a registration algorithm. The direct quantitative approach is to compare the deformation field solution with the ground truth transformation (at all or some landmark pixels). However, in clinical data, the ground truth is typically unknown. To deal with the absence of ground truth, some methods opted to estimate registration accuracy by using uncertainty measures as a surrogate for quantitative registration error. In this paper, we define the registration uncertainty and explore its use for diagnostic purposes. We use uncertainty estimation for improving accuracy of a hybrid registration which register a pre-operative CT to an intra-operative echocardiography images. In other words, uncertainty estimation is used to evaluate the registration algorithm performance which integrates intensity-based and feature-based methods. This registration can potentially be used to improve the diagnosis of cardiac disease by augmenting echocardiography images with high-resolution CT images and to facilitate intraoperative image fusion for minimally invasive cardio-thoracic surgical navigation. Here, we show how to determine the registration uncertainty, by using uncertainty quantification regarding to abnormal intensity and geometry distribution. The result indicates that registration uncertainty is a good predictor for the functional abnormality of subjects.

Original languageEnglish
Title of host publicationIFIP Advances in Information and Communication Technology
PublisherSpringer New York LLC
Pages19-28
Number of pages10
Volume458
ISBN (Print)9783319238678
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015 - Bayonne, France
Duration: 14 Sep 201517 Sep 2015

Publication series

NameIFIP Advances in Information and Communication Technology
Volume458
ISSN (Print)18684238

Other

Other11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015
CountryFrance
CityBayonne
Period14/9/1517/9/15

Fingerprint

Registration
Uncertainty
Computed tomography
Echocardiography
Geometry
Diagnostics
Predictors
Quantification
Fusion
Navigation

Keywords

  • Computed Tomography (CT)
  • Echocardiography
  • Hybrid. Featurebased
  • Intensity-based
  • Multimodality Image Registration
  • Uncertainty

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Mazaheri, S., Sulaiman, P. S., Wirza, R., Dimon, M. Z., Khalid, F., & Tayebi, R. M. (2015). Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images. In IFIP Advances in Information and Communication Technology (Vol. 458, pp. 19-28). (IFIP Advances in Information and Communication Technology; Vol. 458). Springer New York LLC. https://doi.org/10.1007/978-3-319-23868-5_2

Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images. / Mazaheri, Samaneh; Sulaiman, Puteri Suhaiza; Wirza, Rahmita; Dimon, Mohd Zamrin; Khalid, Fatimah; Tayebi, Rohollah Moosavi.

IFIP Advances in Information and Communication Technology. Vol. 458 Springer New York LLC, 2015. p. 19-28 (IFIP Advances in Information and Communication Technology; Vol. 458).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mazaheri, S, Sulaiman, PS, Wirza, R, Dimon, MZ, Khalid, F & Tayebi, RM 2015, Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images. in IFIP Advances in Information and Communication Technology. vol. 458, IFIP Advances in Information and Communication Technology, vol. 458, Springer New York LLC, pp. 19-28, 11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015, Bayonne, France, 14/9/15. https://doi.org/10.1007/978-3-319-23868-5_2
Mazaheri S, Sulaiman PS, Wirza R, Dimon MZ, Khalid F, Tayebi RM. Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images. In IFIP Advances in Information and Communication Technology. Vol. 458. Springer New York LLC. 2015. p. 19-28. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-3-319-23868-5_2
Mazaheri, Samaneh ; Sulaiman, Puteri Suhaiza ; Wirza, Rahmita ; Dimon, Mohd Zamrin ; Khalid, Fatimah ; Tayebi, Rohollah Moosavi. / Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images. IFIP Advances in Information and Communication Technology. Vol. 458 Springer New York LLC, 2015. pp. 19-28 (IFIP Advances in Information and Communication Technology).
@inproceedings{88efe552ecb8409c8372469d3470d81a,
title = "Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images",
abstract = "In order to utilize both computed tomography (CT) and echocardiography images of the heart for medical applications such as diagnosis and image guided intervention concurrently, non-rigid registration is an essential task. A challenging but important problem in image registration is evaluating the performance of a registration algorithm. The direct quantitative approach is to compare the deformation field solution with the ground truth transformation (at all or some landmark pixels). However, in clinical data, the ground truth is typically unknown. To deal with the absence of ground truth, some methods opted to estimate registration accuracy by using uncertainty measures as a surrogate for quantitative registration error. In this paper, we define the registration uncertainty and explore its use for diagnostic purposes. We use uncertainty estimation for improving accuracy of a hybrid registration which register a pre-operative CT to an intra-operative echocardiography images. In other words, uncertainty estimation is used to evaluate the registration algorithm performance which integrates intensity-based and feature-based methods. This registration can potentially be used to improve the diagnosis of cardiac disease by augmenting echocardiography images with high-resolution CT images and to facilitate intraoperative image fusion for minimally invasive cardio-thoracic surgical navigation. Here, we show how to determine the registration uncertainty, by using uncertainty quantification regarding to abnormal intensity and geometry distribution. The result indicates that registration uncertainty is a good predictor for the functional abnormality of subjects.",
keywords = "Computed Tomography (CT), Echocardiography, Hybrid. Featurebased, Intensity-based, Multimodality Image Registration, Uncertainty",
author = "Samaneh Mazaheri and Sulaiman, {Puteri Suhaiza} and Rahmita Wirza and Dimon, {Mohd Zamrin} and Fatimah Khalid and Tayebi, {Rohollah Moosavi}",
year = "2015",
doi = "10.1007/978-3-319-23868-5_2",
language = "English",
isbn = "9783319238678",
volume = "458",
series = "IFIP Advances in Information and Communication Technology",
publisher = "Springer New York LLC",
pages = "19--28",
booktitle = "IFIP Advances in Information and Communication Technology",

}

TY - GEN

T1 - Uncertainty estimation for improving accuracy of non-rigid registration in cardiac images

AU - Mazaheri, Samaneh

AU - Sulaiman, Puteri Suhaiza

AU - Wirza, Rahmita

AU - Dimon, Mohd Zamrin

AU - Khalid, Fatimah

AU - Tayebi, Rohollah Moosavi

PY - 2015

Y1 - 2015

N2 - In order to utilize both computed tomography (CT) and echocardiography images of the heart for medical applications such as diagnosis and image guided intervention concurrently, non-rigid registration is an essential task. A challenging but important problem in image registration is evaluating the performance of a registration algorithm. The direct quantitative approach is to compare the deformation field solution with the ground truth transformation (at all or some landmark pixels). However, in clinical data, the ground truth is typically unknown. To deal with the absence of ground truth, some methods opted to estimate registration accuracy by using uncertainty measures as a surrogate for quantitative registration error. In this paper, we define the registration uncertainty and explore its use for diagnostic purposes. We use uncertainty estimation for improving accuracy of a hybrid registration which register a pre-operative CT to an intra-operative echocardiography images. In other words, uncertainty estimation is used to evaluate the registration algorithm performance which integrates intensity-based and feature-based methods. This registration can potentially be used to improve the diagnosis of cardiac disease by augmenting echocardiography images with high-resolution CT images and to facilitate intraoperative image fusion for minimally invasive cardio-thoracic surgical navigation. Here, we show how to determine the registration uncertainty, by using uncertainty quantification regarding to abnormal intensity and geometry distribution. The result indicates that registration uncertainty is a good predictor for the functional abnormality of subjects.

AB - In order to utilize both computed tomography (CT) and echocardiography images of the heart for medical applications such as diagnosis and image guided intervention concurrently, non-rigid registration is an essential task. A challenging but important problem in image registration is evaluating the performance of a registration algorithm. The direct quantitative approach is to compare the deformation field solution with the ground truth transformation (at all or some landmark pixels). However, in clinical data, the ground truth is typically unknown. To deal with the absence of ground truth, some methods opted to estimate registration accuracy by using uncertainty measures as a surrogate for quantitative registration error. In this paper, we define the registration uncertainty and explore its use for diagnostic purposes. We use uncertainty estimation for improving accuracy of a hybrid registration which register a pre-operative CT to an intra-operative echocardiography images. In other words, uncertainty estimation is used to evaluate the registration algorithm performance which integrates intensity-based and feature-based methods. This registration can potentially be used to improve the diagnosis of cardiac disease by augmenting echocardiography images with high-resolution CT images and to facilitate intraoperative image fusion for minimally invasive cardio-thoracic surgical navigation. Here, we show how to determine the registration uncertainty, by using uncertainty quantification regarding to abnormal intensity and geometry distribution. The result indicates that registration uncertainty is a good predictor for the functional abnormality of subjects.

KW - Computed Tomography (CT)

KW - Echocardiography

KW - Hybrid. Featurebased

KW - Intensity-based

KW - Multimodality Image Registration

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=84946075921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946075921&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-23868-5_2

DO - 10.1007/978-3-319-23868-5_2

M3 - Conference contribution

SN - 9783319238678

VL - 458

T3 - IFIP Advances in Information and Communication Technology

SP - 19

EP - 28

BT - IFIP Advances in Information and Communication Technology

PB - Springer New York LLC

ER -