Surface curvature as a classifier of abdominal aortic aneurysms: A comparative analysis

Kibaek Lee; Junjun Zhu; Judy Shum; Yongjie Zhang; Satish C. Muluk; Ankur Chandra; Mark K. Eskandari; Ender A. Finol

doi:10.1007/s10439-012-0691-4

Surface curvature as a classifier of abdominal aortic aneurysms: A comparative analysis

Kibaek Lee, Junjun Zhu, Judy Shum, Yongjie Zhang, Satish C. Muluk, Ankur Chandra, Mark K. Eskandari, Ender A. Finol^*

^*Corresponding author for this work

Surgery, Vascular Surgery Division

Research output: Contribution to journal › Article › peer-review

36 Scopus citations

Abstract

An abdominal aortic aneurysm (AAA) carries one of the highest mortality rates among vascular diseases when it ruptures. To predict the role of surface curvature in rupture risk assessment, a discriminatory analysis of aneurysm geometry characterization was conducted. Data was obtained from 205 patient-specific computed tomography image sets corresponding to three AAA population subgroups: patients under surveillance, those that underwent elective repair of the aneurysm, and those with an emergent repair. Each AAA was reconstructed and their surface curvatures estimated using the biquintic Hermite finite element method. Local surface curvatures were processed into ten global curvature indices. Statistical analysis of the data revealed that the L2-norm of the Gaussian and Mean surface curvatures can be utilized as classifiers of the three AAA population subgroups. The application of statistical machine learning on the curvature features yielded 85.5% accuracy in classifying electively and emergent repaired AAAs, compared to a 68.9% accuracy obtained by using maximum aneurysm diameter alone. Such combination of non-invasive geometric quantification and statistical machine learning methods can be used in a clinical setting to assess the risk of rupture of aneurysms during regular patient follow-ups.

Original language	English (US)
Pages (from-to)	562-576
Number of pages	15
Journal	Annals of Biomedical Engineering
Volume	41
Issue number	3
DOIs	https://doi.org/10.1007/s10439-012-0691-4
State	Published - Mar 2013

Funding

The authors would like to acknowledge research funding from the Korean Government Scholarship Program for Study Overseas, and the Vlahakis Graduate Fellowship program. This work was also funded in part by NIH grants R21EB007651, R21EB008804 and R15HL087268. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The authors would like to thank Drs. Michael Sacks and David Smith for their insightful discussions on the basics of the BQFE method and its implementation for surface curvature analysis.

Keywords

Abdominal aortic aneurysm
Finite element method
Geometry quantification
Machine learning
Reconstruction
Rupture risk
Surface curvature

ASJC Scopus subject areas

Biomedical Engineering

Access to Document

10.1007/s10439-012-0691-4

Cite this

@article{c23c56fec1de49f9b3a2f4ae58efb97e,

title = "Surface curvature as a classifier of abdominal aortic aneurysms: A comparative analysis",

abstract = "An abdominal aortic aneurysm (AAA) carries one of the highest mortality rates among vascular diseases when it ruptures. To predict the role of surface curvature in rupture risk assessment, a discriminatory analysis of aneurysm geometry characterization was conducted. Data was obtained from 205 patient-specific computed tomography image sets corresponding to three AAA population subgroups: patients under surveillance, those that underwent elective repair of the aneurysm, and those with an emergent repair. Each AAA was reconstructed and their surface curvatures estimated using the biquintic Hermite finite element method. Local surface curvatures were processed into ten global curvature indices. Statistical analysis of the data revealed that the L2-norm of the Gaussian and Mean surface curvatures can be utilized as classifiers of the three AAA population subgroups. The application of statistical machine learning on the curvature features yielded 85.5% accuracy in classifying electively and emergent repaired AAAs, compared to a 68.9% accuracy obtained by using maximum aneurysm diameter alone. Such combination of non-invasive geometric quantification and statistical machine learning methods can be used in a clinical setting to assess the risk of rupture of aneurysms during regular patient follow-ups.",

keywords = "Abdominal aortic aneurysm, Finite element method, Geometry quantification, Machine learning, Reconstruction, Rupture risk, Surface curvature",

author = "Kibaek Lee and Junjun Zhu and Judy Shum and Yongjie Zhang and Muluk, {Satish C.} and Ankur Chandra and Eskandari, {Mark K.} and Finol, {Ender A.}",

note = "Funding Information: The authors would like to acknowledge research funding from the Korean Government Scholarship Program for Study Overseas, and the Vlahakis Graduate Fellowship program. This work was also funded in part by NIH grants R21EB007651, R21EB008804 and R15HL087268. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The authors would like to thank Drs. Michael Sacks and David Smith for their insightful discussions on the basics of the BQFE method and its implementation for surface curvature analysis.",

year = "2013",

month = mar,

doi = "10.1007/s10439-012-0691-4",

language = "English (US)",

volume = "41",

pages = "562--576",

journal = "Annals of Biomedical Engineering",

issn = "0090-6964",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Surface curvature as a classifier of abdominal aortic aneurysms

T2 - A comparative analysis

AU - Lee, Kibaek

AU - Zhu, Junjun

AU - Shum, Judy

AU - Zhang, Yongjie

AU - Muluk, Satish C.

AU - Chandra, Ankur

AU - Eskandari, Mark K.

AU - Finol, Ender A.

N1 - Funding Information: The authors would like to acknowledge research funding from the Korean Government Scholarship Program for Study Overseas, and the Vlahakis Graduate Fellowship program. This work was also funded in part by NIH grants R21EB007651, R21EB008804 and R15HL087268. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The authors would like to thank Drs. Michael Sacks and David Smith for their insightful discussions on the basics of the BQFE method and its implementation for surface curvature analysis.

PY - 2013/3

Y1 - 2013/3

N2 - An abdominal aortic aneurysm (AAA) carries one of the highest mortality rates among vascular diseases when it ruptures. To predict the role of surface curvature in rupture risk assessment, a discriminatory analysis of aneurysm geometry characterization was conducted. Data was obtained from 205 patient-specific computed tomography image sets corresponding to three AAA population subgroups: patients under surveillance, those that underwent elective repair of the aneurysm, and those with an emergent repair. Each AAA was reconstructed and their surface curvatures estimated using the biquintic Hermite finite element method. Local surface curvatures were processed into ten global curvature indices. Statistical analysis of the data revealed that the L2-norm of the Gaussian and Mean surface curvatures can be utilized as classifiers of the three AAA population subgroups. The application of statistical machine learning on the curvature features yielded 85.5% accuracy in classifying electively and emergent repaired AAAs, compared to a 68.9% accuracy obtained by using maximum aneurysm diameter alone. Such combination of non-invasive geometric quantification and statistical machine learning methods can be used in a clinical setting to assess the risk of rupture of aneurysms during regular patient follow-ups.

AB - An abdominal aortic aneurysm (AAA) carries one of the highest mortality rates among vascular diseases when it ruptures. To predict the role of surface curvature in rupture risk assessment, a discriminatory analysis of aneurysm geometry characterization was conducted. Data was obtained from 205 patient-specific computed tomography image sets corresponding to three AAA population subgroups: patients under surveillance, those that underwent elective repair of the aneurysm, and those with an emergent repair. Each AAA was reconstructed and their surface curvatures estimated using the biquintic Hermite finite element method. Local surface curvatures were processed into ten global curvature indices. Statistical analysis of the data revealed that the L2-norm of the Gaussian and Mean surface curvatures can be utilized as classifiers of the three AAA population subgroups. The application of statistical machine learning on the curvature features yielded 85.5% accuracy in classifying electively and emergent repaired AAAs, compared to a 68.9% accuracy obtained by using maximum aneurysm diameter alone. Such combination of non-invasive geometric quantification and statistical machine learning methods can be used in a clinical setting to assess the risk of rupture of aneurysms during regular patient follow-ups.

KW - Abdominal aortic aneurysm

KW - Finite element method

KW - Geometry quantification

KW - Machine learning

KW - Reconstruction

KW - Rupture risk

KW - Surface curvature

UR - http://www.scopus.com/inward/record.url?scp=84876168686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876168686&partnerID=8YFLogxK

U2 - 10.1007/s10439-012-0691-4

DO - 10.1007/s10439-012-0691-4

M3 - Article

C2 - 23180028

AN - SCOPUS:84876168686

SN - 0090-6964

VL - 41

SP - 562

EP - 576

JO - Annals of Biomedical Engineering

JF - Annals of Biomedical Engineering

IS - 3

ER -

Surface curvature as a classifier of abdominal aortic aneurysms: A comparative analysis

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this