Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface

Huan N. Do, Ahsan Ijaz, Hamidreza Gharahi, Byron Zambrano, Jongeun Choi, Whal Lee, Seungik Baek

Research output: Contribution to journalArticle

Abstract

Objective: We propose a novel approach to predict the Abdominal Aortic Aneurysm (AAA) growth in future time, using longitudinal computer tomography (CT) scans of AAAs that are captured at different times in a patient-specific way. Methods: We adopt a formulation that considers a surface of the AAA as a manifold embedded in a scalar field over the three dimensional (3D) space. For this formulation, we develop our Dynamical Gaussian Process Implicit Surface (DGPIS) model based on observed surfaces of 3D AAAs as visible variables while the scalar fields are hidden. In particular, we use Gaussian process regression to construct the field as an observation model from CT training image data. We then learn a dynamic model to represent the evolution of the field. Finally, we derive the predicted AAA surface from the predicted field along with uncertainty quantified in future time. Results: A dataset of 7 subjects (4-7 scans) was collected and used to evaluate the proposed method by comparing its prediction Hausdorff distance errors against those of simple extrapolation. In addition, we evaluate the prediction results with respect to a conventional shape analysis technique such as Principal Component Analysis (PCA). All comparative results show the superior prediction performance of the proposed approach. Conclusion: We introduce a novel approach to predict the AAA growth and its predicted uncertainty in future time, using longitudinal CT scans in a patient-specific fashion. Significance: The capability to predict the AAA shape and its confidence region by our approach establish the potential for guiding clinicians with informed decision in conducting medical treatment and monitoring of AAAs.

Original languageEnglish
Article number8401907
Pages (from-to)609-622
Number of pages14
JournalIEEE Transactions on Biomedical Engineering
Volume66
Issue number3
DOIs
Publication statusPublished - 2019 Mar 1

Fingerprint

Tomography
Extrapolation
Principal component analysis
Dynamic models
Monitoring
Uncertainty

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Do, Huan N. ; Ijaz, Ahsan ; Gharahi, Hamidreza ; Zambrano, Byron ; Choi, Jongeun ; Lee, Whal ; Baek, Seungik. / Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface. In: IEEE Transactions on Biomedical Engineering. 2019 ; Vol. 66, No. 3. pp. 609-622.
@article{de9062e478884f7d9d43e23c5b05fda7,
title = "Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface",
abstract = "Objective: We propose a novel approach to predict the Abdominal Aortic Aneurysm (AAA) growth in future time, using longitudinal computer tomography (CT) scans of AAAs that are captured at different times in a patient-specific way. Methods: We adopt a formulation that considers a surface of the AAA as a manifold embedded in a scalar field over the three dimensional (3D) space. For this formulation, we develop our Dynamical Gaussian Process Implicit Surface (DGPIS) model based on observed surfaces of 3D AAAs as visible variables while the scalar fields are hidden. In particular, we use Gaussian process regression to construct the field as an observation model from CT training image data. We then learn a dynamic model to represent the evolution of the field. Finally, we derive the predicted AAA surface from the predicted field along with uncertainty quantified in future time. Results: A dataset of 7 subjects (4-7 scans) was collected and used to evaluate the proposed method by comparing its prediction Hausdorff distance errors against those of simple extrapolation. In addition, we evaluate the prediction results with respect to a conventional shape analysis technique such as Principal Component Analysis (PCA). All comparative results show the superior prediction performance of the proposed approach. Conclusion: We introduce a novel approach to predict the AAA growth and its predicted uncertainty in future time, using longitudinal CT scans in a patient-specific fashion. Significance: The capability to predict the AAA shape and its confidence region by our approach establish the potential for guiding clinicians with informed decision in conducting medical treatment and monitoring of AAAs.",
author = "Do, {Huan N.} and Ahsan Ijaz and Hamidreza Gharahi and Byron Zambrano and Jongeun Choi and Whal Lee and Seungik Baek",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/TBME.2018.2852306",
language = "English",
volume = "66",
pages = "609--622",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface. / Do, Huan N.; Ijaz, Ahsan; Gharahi, Hamidreza; Zambrano, Byron; Choi, Jongeun; Lee, Whal; Baek, Seungik.

In: IEEE Transactions on Biomedical Engineering, Vol. 66, No. 3, 8401907, 01.03.2019, p. 609-622.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of Abdominal Aortic Aneurysm Growth Using Dynamical Gaussian Process Implicit Surface

AU - Do, Huan N.

AU - Ijaz, Ahsan

AU - Gharahi, Hamidreza

AU - Zambrano, Byron

AU - Choi, Jongeun

AU - Lee, Whal

AU - Baek, Seungik

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Objective: We propose a novel approach to predict the Abdominal Aortic Aneurysm (AAA) growth in future time, using longitudinal computer tomography (CT) scans of AAAs that are captured at different times in a patient-specific way. Methods: We adopt a formulation that considers a surface of the AAA as a manifold embedded in a scalar field over the three dimensional (3D) space. For this formulation, we develop our Dynamical Gaussian Process Implicit Surface (DGPIS) model based on observed surfaces of 3D AAAs as visible variables while the scalar fields are hidden. In particular, we use Gaussian process regression to construct the field as an observation model from CT training image data. We then learn a dynamic model to represent the evolution of the field. Finally, we derive the predicted AAA surface from the predicted field along with uncertainty quantified in future time. Results: A dataset of 7 subjects (4-7 scans) was collected and used to evaluate the proposed method by comparing its prediction Hausdorff distance errors against those of simple extrapolation. In addition, we evaluate the prediction results with respect to a conventional shape analysis technique such as Principal Component Analysis (PCA). All comparative results show the superior prediction performance of the proposed approach. Conclusion: We introduce a novel approach to predict the AAA growth and its predicted uncertainty in future time, using longitudinal CT scans in a patient-specific fashion. Significance: The capability to predict the AAA shape and its confidence region by our approach establish the potential for guiding clinicians with informed decision in conducting medical treatment and monitoring of AAAs.

AB - Objective: We propose a novel approach to predict the Abdominal Aortic Aneurysm (AAA) growth in future time, using longitudinal computer tomography (CT) scans of AAAs that are captured at different times in a patient-specific way. Methods: We adopt a formulation that considers a surface of the AAA as a manifold embedded in a scalar field over the three dimensional (3D) space. For this formulation, we develop our Dynamical Gaussian Process Implicit Surface (DGPIS) model based on observed surfaces of 3D AAAs as visible variables while the scalar fields are hidden. In particular, we use Gaussian process regression to construct the field as an observation model from CT training image data. We then learn a dynamic model to represent the evolution of the field. Finally, we derive the predicted AAA surface from the predicted field along with uncertainty quantified in future time. Results: A dataset of 7 subjects (4-7 scans) was collected and used to evaluate the proposed method by comparing its prediction Hausdorff distance errors against those of simple extrapolation. In addition, we evaluate the prediction results with respect to a conventional shape analysis technique such as Principal Component Analysis (PCA). All comparative results show the superior prediction performance of the proposed approach. Conclusion: We introduce a novel approach to predict the AAA growth and its predicted uncertainty in future time, using longitudinal CT scans in a patient-specific fashion. Significance: The capability to predict the AAA shape and its confidence region by our approach establish the potential for guiding clinicians with informed decision in conducting medical treatment and monitoring of AAAs.

UR - http://www.scopus.com/inward/record.url?scp=85049316494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049316494&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2852306

DO - 10.1109/TBME.2018.2852306

M3 - Article

VL - 66

SP - 609

EP - 622

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

M1 - 8401907

ER -