Savino Cilla1, Gabriella Macchia2, Jacopo Lenkowicz3, Elena H Tran3, Antonio Pierro4, Lella Petrella5, Mara Fanelli5, Celestino Sardu6, Alessia Re2, Luca Boldrini7, Luca Indovina8, Carlo Maria De Filippo9, Eugenio Caradonna9, Francesco Deodato2,10, Massimo Massetti11, Vincenzo Valentini7,10, Pietro Modugno12. 1. Medical Physics Unit, Gemelli Molise Hospital, Università Cattolica del Sacro Cuore, 86100, Campobasso, Italy. savinocilla@gmail.com. 2. Radiation Oncology Unit, Gemelli Molise Hospital, Università Cattolica del Sacro Cuore, Campobasso, Italy. 3. Fondazione Policlinico Universitario "Agostino Gemelli" IRCCS, Rome, Italy. 4. Radiology Department, "A. Cardarelli" Regional Hospital ASReM, Campobasso, Italy. 5. Laboratory of Molecular Oncology, Gemelli Molise Hospital, Campobasso, Italy. 6. Department of Advanced Medical and Surgical Sciences, University of Campania "Luigi Vanvitelli", Caserta, Italy. 7. Radiation Oncology Department, Fondazione Policlinico Universitario "Agostino Gemelli" IRCCS, Rome, Italy. 8. Medical Physics Unit, Fondazione Policlinico Universitario A. Gemelli, Università Cattolica del Sacro Cuore, Rome, Italy. 9. Cardiac Surgery Unit, Gemelli Molise Hospital, Università Cattolica del Sacro Cuore, Campobasso, Italy. 10. Istituto di Radiologia, Fondazione Policlinico Universitario A. Gemelli, Università Cattolica del Sacro Cuore, Rome, Italy. 11. Cardiac Surgery Division, Fondazione Policlinico Universitario A. Gemelli, Università Cattolica del Sacro Cuore, Rome, Italy. 12. Vascular Surgery Unit, Gemelli Molise Hospital, Università Cattolica del Sacro Cuore, Campobasso, Italy.
Abstract
PURPOSES: Radiomics is a quantitative method able to analyze a high-throughput extraction of minable imaging features. Herein, we aim to develop a CT angiography-based radiomics analysis and machine learning model for carotid plaques to discriminate vulnerable from no vulnerable plaques. MATERIALS AND METHODS: Thirty consecutive patients with carotid atherosclerosis were enrolled in this pilot study. At surgery, a binary classification of plaques was adopted ("hard" vs "soft"). Feature extraction was performed using the R software package Moddicom. Pairwise feature interdependencies were evaluated using the Spearman rank correlation coefficient. A univariate analysis was performed to assess the association between each feature and the plaque classification and chose top-ranked features. The feature predictive value was investigated using binary logistic regression. A stepwise backward elimination procedure was performed to minimize the Akaike information criterion (AIC). The final significant features were used to build the models for binary classification of carotid plaques, including logistic regression (LR), support vector machine (SVM), and classification and regression tree analysis (CART). All models were cross-validated using fivefold cross validation. Class-specific accuracy, precision, recall and F-measure evaluation metrics were used to quantify classifier output quality. RESULTS: A total of 230 radiomics features were extracted from each plaque. Pairwise Spearman correlation between features reported a high level of correlations, with more than 80% correlating with at least one other feature at |ρ|> 0.8. After a stepwise backward elimination procedure, the entropy and volume features were found to be the most significantly associated with the two plaque groups (p < 0.001), with AUCs of 0.92 and 0.96, respectively. The best performance was registered by the SVM classifier with the RBF kernel, with accuracy, precision, recall and F-score equal to 86.7, 92.9, 81.3 and 86.7%, respectively. The CART classification tree model for the entropy and volume features model achieved 86.7% well-classified plaques and an AUC of 0.987. CONCLUSION: This pilot study highlighted the potential of CTA-based radiomics and machine learning to discriminate plaque composition. This new approach has the potential to provide a reliable method to improve risk stratification in patients with carotid atherosclerosis.
PURPOSES: Radiomics is a quantitative method able to analyze a high-throughput extraction of minable imaging features. Herein, we aim to develop a CT angiography-based radiomics analysis and machine learning model for carotid plaques to discriminate vulnerable from no vulnerable plaques. MATERIALS AND METHODS: Thirty consecutive patients with carotid atherosclerosis were enrolled in this pilot study. At surgery, a binary classification of plaques was adopted ("hard" vs "soft"). Feature extraction was performed using the R software package Moddicom. Pairwise feature interdependencies were evaluated using the Spearman rank correlation coefficient. A univariate analysis was performed to assess the association between each feature and the plaque classification and chose top-ranked features. The feature predictive value was investigated using binary logistic regression. A stepwise backward elimination procedure was performed to minimize the Akaike information criterion (AIC). The final significant features were used to build the models for binary classification of carotid plaques, including logistic regression (LR), support vector machine (SVM), and classification and regression tree analysis (CART). All models were cross-validated using fivefold cross validation. Class-specific accuracy, precision, recall and F-measure evaluation metrics were used to quantify classifier output quality. RESULTS: A total of 230 radiomics features were extracted from each plaque. Pairwise Spearman correlation between features reported a high level of correlations, with more than 80% correlating with at least one other feature at |ρ|> 0.8. After a stepwise backward elimination procedure, the entropy and volume features were found to be the most significantly associated with the two plaque groups (p < 0.001), with AUCs of 0.92 and 0.96, respectively. The best performance was registered by the SVM classifier with the RBF kernel, with accuracy, precision, recall and F-score equal to 86.7, 92.9, 81.3 and 86.7%, respectively. The CART classification tree model for the entropy and volume features model achieved 86.7% well-classified plaques and an AUC of 0.987. CONCLUSION: This pilot study highlighted the potential of CTA-based radiomics and machine learning to discriminate plaque composition. This new approach has the potential to provide a reliable method to improve risk stratification in patients with carotid atherosclerosis.
Authors: Anna E H Zavodni; Bruce A Wasserman; Robyn L McClelland; Antoinette S Gomes; Aaron R Folsom; Joseph F Polak; João A C Lima; David A Bluemke Journal: Radiology Date: 2014-03-04 Impact factor: 11.105
Authors: Luca Saba; Tobias Saam; H Rolf Jäger; Chun Yuan; Thomas S Hatsukami; David Saloner; Bruce A Wasserman; Leo H Bonati; Max Wintermark Journal: Lancet Neurol Date: 2019-04-04 Impact factor: 44.182
Authors: Laura Pletsch-Borba; Mariana Selwaness; Aad van der Lugt; Albert Hofman; Oscar H Franco; Meike W Vernooij Journal: JACC Cardiovasc Imaging Date: 2017-04-12
Authors: P M Rothwell; M Eliasziw; S A Gutnikov; A J Fox; D W Taylor; M R Mayberg; C P Warlow; H J M Barnett Journal: Lancet Date: 2003-01-11 Impact factor: 79.321
Authors: Xue-Qiao Zhao; Thomas S Hatsukami; Daniel S Hippe; Jie Sun; Niranjan Balu; Daniel A Isquith; John R Crouse; Todd Anderson; John Huston; Nayak Polissar; Kevin O'Brien; Chun Yuan Journal: Am J Cardiol Date: 2014-08-13 Impact factor: 2.778
Authors: Andreas Schindler; Regina Schinner; Nishaf Altaf; Akram A Hosseini; Richard J Simpson; Lorena Esposito-Bauer; Navneet Singh; Robert M Kwee; Yoshitaka Kurosaki; Sen Yamagata; Kazumichi Yoshida; Susumu Miyamoto; Robert Maggisano; Alan R Moody; Holger Poppert; M Eline Kooi; Dorothee P Auer; Leo H Bonati; Tobias Saam Journal: JACC Cardiovasc Imaging Date: 2019-06-12