Automated plaque classification using computed tomography angiography and Gabor transformations

Cardiovascular diseases are the primary cause of death globally. These are often associated with atherosclerosis. This inflammation process triggers important variations in the coronary arteries (CA) and can lead to coronary artery disease (CAD). The presence of CA calcification (CAC) has recently b...

Full description

Bibliographic Details
Main Authors: Acharya, U. Rajendra, Meiburger, Kristen Mariko, Wei Koh, Joel En, Vicnesh, Jahmunah, Ciaccio, Edward J., Shu Lih, Oh, Tan, Sock Keow, Raja Aman, Raja Rizal Azman, Molinari, Filippo, Ng, Kwan Hoong
Format: Article
Published: Elsevier 2019
Subjects:
_version_ 1825722106419085312
author Acharya, U. Rajendra
Meiburger, Kristen Mariko
Wei Koh, Joel En
Vicnesh, Jahmunah
Ciaccio, Edward J.
Shu Lih, Oh
Tan, Sock Keow
Raja Aman, Raja Rizal Azman
Molinari, Filippo
Ng, Kwan Hoong
author_facet Acharya, U. Rajendra
Meiburger, Kristen Mariko
Wei Koh, Joel En
Vicnesh, Jahmunah
Ciaccio, Edward J.
Shu Lih, Oh
Tan, Sock Keow
Raja Aman, Raja Rizal Azman
Molinari, Filippo
Ng, Kwan Hoong
author_sort Acharya, U. Rajendra
collection UM
description Cardiovascular diseases are the primary cause of death globally. These are often associated with atherosclerosis. This inflammation process triggers important variations in the coronary arteries (CA) and can lead to coronary artery disease (CAD). The presence of CA calcification (CAC) has recently been shown to be a strong predictor of CAD. In this clinical setting, computed tomography angiography (CTA) has begun to play a crucial role as a non-intrusive imaging method to characterize and study CA plaques. Herein, we describe an automated algorithm to classify plaque as either normal, calcified, or non-calcified using 2646 CTA images acquired from 73 patients. The automated technique is based on various features that are extracted from the Gabor transform of the acquired CTA images. Specifically, seven features are extracted from the Gabor coefficients: energy, and Kapur, Max, Rényi, Shannon, Vajda, and Yager entropies. The features were then ordered based on the F-value and input to numerous classification methods to achieve the best classification accuracy with the least number of features. Moreover, two well-known feature reduction techniques were employed, and the features acquired were also ranked according to F-value and input to several classifiers. The best classification results were obtained using all computed features without the employment of feature reduction, using a probabilistic neural network. An accuracy, positive predictive value, sensitivity, and specificity of 89.09%, 91.70%, 91.83% and 83.70% was obtained, respectively. Based on these results, it is evident that the technique can be helpful in the automated classification of plaques present in CTA images, and may become an important tool to reduce procedural costs and patient radiation dose. This could also aid clinicians in plaque diagnostics. © 2019 Elsevier B.V.
first_indexed 2024-03-06T06:00:35Z
format Article
id um.eprints-23691
institution Universiti Malaya
last_indexed 2024-03-06T06:00:35Z
publishDate 2019
publisher Elsevier
record_format dspace
spelling um.eprints-236912020-02-06T02:45:50Z http://eprints.um.edu.my/23691/ Automated plaque classification using computed tomography angiography and Gabor transformations Acharya, U. Rajendra Meiburger, Kristen Mariko Wei Koh, Joel En Vicnesh, Jahmunah Ciaccio, Edward J. Shu Lih, Oh Tan, Sock Keow Raja Aman, Raja Rizal Azman Molinari, Filippo Ng, Kwan Hoong R Medicine TK Electrical engineering. Electronics Nuclear engineering Cardiovascular diseases are the primary cause of death globally. These are often associated with atherosclerosis. This inflammation process triggers important variations in the coronary arteries (CA) and can lead to coronary artery disease (CAD). The presence of CA calcification (CAC) has recently been shown to be a strong predictor of CAD. In this clinical setting, computed tomography angiography (CTA) has begun to play a crucial role as a non-intrusive imaging method to characterize and study CA plaques. Herein, we describe an automated algorithm to classify plaque as either normal, calcified, or non-calcified using 2646 CTA images acquired from 73 patients. The automated technique is based on various features that are extracted from the Gabor transform of the acquired CTA images. Specifically, seven features are extracted from the Gabor coefficients: energy, and Kapur, Max, Rényi, Shannon, Vajda, and Yager entropies. The features were then ordered based on the F-value and input to numerous classification methods to achieve the best classification accuracy with the least number of features. Moreover, two well-known feature reduction techniques were employed, and the features acquired were also ranked according to F-value and input to several classifiers. The best classification results were obtained using all computed features without the employment of feature reduction, using a probabilistic neural network. An accuracy, positive predictive value, sensitivity, and specificity of 89.09%, 91.70%, 91.83% and 83.70% was obtained, respectively. Based on these results, it is evident that the technique can be helpful in the automated classification of plaques present in CTA images, and may become an important tool to reduce procedural costs and patient radiation dose. This could also aid clinicians in plaque diagnostics. © 2019 Elsevier B.V. Elsevier 2019 Article PeerReviewed Acharya, U. Rajendra and Meiburger, Kristen Mariko and Wei Koh, Joel En and Vicnesh, Jahmunah and Ciaccio, Edward J. and Shu Lih, Oh and Tan, Sock Keow and Raja Aman, Raja Rizal Azman and Molinari, Filippo and Ng, Kwan Hoong (2019) Automated plaque classification using computed tomography angiography and Gabor transformations. Artificial Intelligence in Medicine, 100. p. 101724. ISSN 0933-3657, DOI https://doi.org/10.1016/j.artmed.2019.101724 <https://doi.org/10.1016/j.artmed.2019.101724>. https://doi.org/10.1016/j.artmed.2019.101724 doi:10.1016/j.artmed.2019.101724
spellingShingle R Medicine
TK Electrical engineering. Electronics Nuclear engineering
Acharya, U. Rajendra
Meiburger, Kristen Mariko
Wei Koh, Joel En
Vicnesh, Jahmunah
Ciaccio, Edward J.
Shu Lih, Oh
Tan, Sock Keow
Raja Aman, Raja Rizal Azman
Molinari, Filippo
Ng, Kwan Hoong
Automated plaque classification using computed tomography angiography and Gabor transformations
title Automated plaque classification using computed tomography angiography and Gabor transformations
title_full Automated plaque classification using computed tomography angiography and Gabor transformations
title_fullStr Automated plaque classification using computed tomography angiography and Gabor transformations
title_full_unstemmed Automated plaque classification using computed tomography angiography and Gabor transformations
title_short Automated plaque classification using computed tomography angiography and Gabor transformations
title_sort automated plaque classification using computed tomography angiography and gabor transformations
topic R Medicine
TK Electrical engineering. Electronics Nuclear engineering
work_keys_str_mv AT acharyaurajendra automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT meiburgerkristenmariko automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT weikohjoelen automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT vicneshjahmunah automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT ciaccioedwardj automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT shulihoh automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT tansockkeow automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT rajaamanrajarizalazman automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT molinarifilippo automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations
AT ngkwanhoong automatedplaqueclassificationusingcomputedtomographyangiographyandgabortransformations