Fully automated image quality assessment based on deep learning for carotid computed tomography angiography: A multicenter study.
Authors
Affiliations (7)
Affiliations (7)
- Rehabilitation Medicine Center, Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou 310014, Zhejiang, China.; The Second School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou 310053 Zhejiang, China.
- The Second School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou 310053 Zhejiang, China.
- ShuKun Technology Co., Ltd., Jinhui Bd, Qiyang Rd, Beijing 100029, China.
- Rehabilitation Medicine Center, Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou 310014, Zhejiang, China.
- Department of Radiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, China.
- Jinzhou Medical University, Jinzhou, Liaoning Province, China.
- Rehabilitation Medicine Center, Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital, Hangzhou Medical College, Hangzhou 310014, Zhejiang, China.; Institute of Artificial Intelligence and Remote Imaging, Hangzhou Medical College, Hangzhou 310014, China. Electronic address: [email protected].
Abstract
To develop and evaluate the performance of fully automated model based on deep learning and multiple logistics regression algorithm for image quality assessment (IQA) of carotid computed tomography angiography (CTA) images. This study retrospectively collected 840 carotid CTA images from four tertiary hospitals. Three radiologists independently assessed the image quality using a 3-point Likert scale, based on the degree of noise, vessel enhancement, arterial vessel contrast, vessel edge sharpness, and overall diagnostic acceptability. An automated assessment model was developed using a training dataset consisting of 600 carotid CTA images. The assessment steps included: (i) selection of objective representative slices; (ii) use of 3D Res U-net approach to extract objective indices from the representative slices and (iii) use of single objective index and multiple indices combinedly to develop logistic regression models for IQA. In the internal and external test datasets (n = 240), the performance of models was evaluated using sensitivity, specificity, precision, F-score, accuracy, the area under the receiver operating characteristic curve (AUC), and the IQA results of models was compared with radiologists' consensus. The representative slices were determined based on the same length model. The performance of multi-index model was excellent in internal and external test datasets with AUCs of 0.98 and 0.97. And the consistency between model and radiologists achieved 91.8% (95% CI: 87.0-96.5) and 92.6% (95 % CI: 86.9-98.4) in internal and external test datasets respectively. The fully automated multi-index model showed equivalent performance to the subjective perceptions of radiologists with greater efficiency for IQA.