Lin Li1, Xi Hu2, Xinwei Tao3, Xiaozhe Shi4, Wenli Zhou5, Hongjie Hu6, Xiuhua Hu7. 1. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: lotusll@zju.edu.cn. 2. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: zjuhuxi@zju.edu.cn. 3. Siemens Healthineers China, No.278, Road Zhouzhu, Shanghai, 201314, China. Electronic address: xinwei.tao@siemens-healthineers.com. 4. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: shixiaozhe@zju.edu.cn. 5. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: zwl1993@connect.hku.hk. 6. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: hongjiehu@zju.edu.cn. 7. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang, 310010, China. Electronic address: huxiuhua_srrsh@zju.edu.cn.
Abstract
OBJECTIVE: This study aimed to investigate the diagnostic performance of radiomics features derived from coronary computed tomography angiography (CCTA) in the identification of ischemic coronary stenosis plaque using invasive fractional flow reserve (FFR) as the reference standard. MATERIALS AND METHODS: 174 plaques of 149 patients (age: 62.21 ± 8.47 years, 96 males) with at least one lesion stenosis degree between 30 % and 90 % were retrospectively included. Stenosis degree and plaque characteristics were recorded, and a conventional multivariate logistic model was established. Over 1000 radiomics features of the plaque were derived from CCTA images. The plaques were randomly divided into training set (n = 139) and validation set (n = 35). A random forest model was built. The area under the curve (AUC) of the models was compared. RESULTS: Fifty-eight radiomics features were correlated with functionally significant stenosis (p < 0.05), wherein 56 features had an AUC of >0.6. NCP volume, NRS, remodeling index, and spotty calcification were included in the conventional model. Ultimately, 14 features were integrated to build the radiomics model. The AUC showed an improvement: 0.71 vs 0.82 for the training set and 0.70 vs 0.77 for the validation set (conventional model and radiomics model, respectively); however, it was not statistically significant (p = 0.58). CONCLUSION: The radiomics analysis of plaques showed improvement compared with conventional plaques assessment in identifying hemodynamically significant coronary stenosis. The statistical advancement of machine learning for plaques to predict hemodynamic stenosis with a noninvasive approach still needs further studies on a large-scale dataset.
OBJECTIVE: This study aimed to investigate the diagnostic performance of radiomics features derived from coronary computed tomography angiography (CCTA) in the identification of ischemic coronary stenosis plaque using invasive fractional flow reserve (FFR) as the reference standard. MATERIALS AND METHODS: 174 plaques of 149 patients (age: 62.21 ± 8.47 years, 96 males) with at least one lesion stenosis degree between 30 % and 90 % were retrospectively included. Stenosis degree and plaque characteristics were recorded, and a conventional multivariate logistic model was established. Over 1000 radiomics features of the plaque were derived from CCTA images. The plaques were randomly divided into training set (n = 139) and validation set (n = 35). A random forest model was built. The area under the curve (AUC) of the models was compared. RESULTS: Fifty-eight radiomics features were correlated with functionally significant stenosis (p < 0.05), wherein 56 features had an AUC of >0.6. NCP volume, NRS, remodeling index, and spotty calcification were included in the conventional model. Ultimately, 14 features were integrated to build the radiomics model. The AUC showed an improvement: 0.71 vs 0.82 for the training set and 0.70 vs 0.77 for the validation set (conventional model and radiomics model, respectively); however, it was not statistically significant (p = 0.58). CONCLUSION: The radiomics analysis of plaques showed improvement compared with conventional plaques assessment in identifying hemodynamically significant coronary stenosis. The statistical advancement of machine learning for plaques to predict hemodynamic stenosis with a noninvasive approach still needs further studies on a large-scale dataset.
Authors: Mardhiyati Mohd Yunus; Ahmad Khairuddin Mohamed Yusof; Muhd Zaidi Ab Rahman; Xue Jing Koh; Akmal Sabarudin; Puteri N E Nohuddin; Kwan Hoong Ng; Mohd Mustafa Awang Kechik; Muhammad Khalis Abdul Karim Journal: Diagnostics (Basel) Date: 2022-07-08