TY - JOUR
T1 - A Comparative Classification Analysis of Abdominal Aortic Aneurysms by Machine Learning Algorithms
AU - Rengarajan, Balaji
AU - Wu, Wei
AU - Wiedner, Crystal
AU - Ko, Daijin
AU - Muluk, Satish C.
AU - Eskandari, Mark K.
AU - Menon, Prahlad G.
AU - Finol, Ender A.
N1 - Funding Information:
Research funding was provided in part by National Institutes of Health Award No. R01HL121293. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The use of ANSYS Ensight is gratefully acknowledged through an educational licensing agreement with Ansys, Inc.
Publisher Copyright:
© 2020, Biomedical Engineering Society.
PY - 2020/4/1
Y1 - 2020/4/1
N2 - The objective of this work was to perform image-based classification of abdominal aortic aneurysms (AAA) based on their demographic, geometric, and biomechanical attributes. We retrospectively reviewed existing demographics and abdominal computed tomography angiography images of 100 asymptomatic and 50 symptomatic AAA patients who received an elective or emergent repair, respectively, within 1–6 months of their last follow up. An in-house script developed within the MATLAB computational platform was used to segment the clinical images, calculate 53 descriptors of AAA geometry, and generate volume meshes suitable for finite element analysis (FEA). Using a third party FEA solver, four biomechanical markers were calculated from the wall stress distributions. Eight machine learning algorithms (MLA) were used to develop classification models based on the discriminatory potential of the demographic, geometric, and biomechanical variables. The overall classification performance of the algorithms was assessed by the accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and precision of their predictions. The generalized additive model (GAM) was found to have the highest accuracy (87%), AUC (89%), and sensitivity (78%), and the third highest specificity (92%), in classifying the individual AAA as either asymptomatic or symptomatic. The k-nearest neighbor classifier yielded the highest specificity (96%). GAM used seven markers (six geometric and one biomechanical) to develop the classifier. The maximum transverse dimension, the average wall thickness at the maximum diameter, and the spatially averaged wall stress were found to be the most influential markers in the classification analysis. A second classification analysis revealed that using maximum diameter alone results in a lower accuracy (79%) than using GAM with seven geometric and biomechanical markers. We infer from these results that biomechanical and geometric measures by themselves are not sufficient to discriminate adequately between population samples of asymptomatic and symptomatic AAA, whereas MLA offer a statistical approach to stratification of rupture risk by combining demographic, geometric, and biomechanical attributes of patient-specific AAA.
AB - The objective of this work was to perform image-based classification of abdominal aortic aneurysms (AAA) based on their demographic, geometric, and biomechanical attributes. We retrospectively reviewed existing demographics and abdominal computed tomography angiography images of 100 asymptomatic and 50 symptomatic AAA patients who received an elective or emergent repair, respectively, within 1–6 months of their last follow up. An in-house script developed within the MATLAB computational platform was used to segment the clinical images, calculate 53 descriptors of AAA geometry, and generate volume meshes suitable for finite element analysis (FEA). Using a third party FEA solver, four biomechanical markers were calculated from the wall stress distributions. Eight machine learning algorithms (MLA) were used to develop classification models based on the discriminatory potential of the demographic, geometric, and biomechanical variables. The overall classification performance of the algorithms was assessed by the accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and precision of their predictions. The generalized additive model (GAM) was found to have the highest accuracy (87%), AUC (89%), and sensitivity (78%), and the third highest specificity (92%), in classifying the individual AAA as either asymptomatic or symptomatic. The k-nearest neighbor classifier yielded the highest specificity (96%). GAM used seven markers (six geometric and one biomechanical) to develop the classifier. The maximum transverse dimension, the average wall thickness at the maximum diameter, and the spatially averaged wall stress were found to be the most influential markers in the classification analysis. A second classification analysis revealed that using maximum diameter alone results in a lower accuracy (79%) than using GAM with seven geometric and biomechanical markers. We infer from these results that biomechanical and geometric measures by themselves are not sufficient to discriminate adequately between population samples of asymptomatic and symptomatic AAA, whereas MLA offer a statistical approach to stratification of rupture risk by combining demographic, geometric, and biomechanical attributes of patient-specific AAA.
KW - Abdominal aortic aneurysm
KW - Generalized additive model
KW - Image segmentation
KW - Machine learning
KW - Rupture risk evaluation
UR - http://www.scopus.com/inward/record.url?scp=85078094736&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078094736&partnerID=8YFLogxK
U2 - 10.1007/s10439-020-02461-9
DO - 10.1007/s10439-020-02461-9
M3 - Article
C2 - 31980998
AN - SCOPUS:85078094736
VL - 48
SP - 1419
EP - 1429
JO - Annals of Biomedical Engineering
JF - Annals of Biomedical Engineering
SN - 0090-6964
IS - 4
ER -