Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery
Journal of Thoracic Disease · 2023-04 · 15 (4) · 2129-2140
DOI: 10.21037/jtd-23-470 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Thoracic Disease, 2023-04. Verfasst von Zeye Liu und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Structural Heart Disease, National Center for Cardiovascular Disease, China & Fuwai Hospital, Chinese Academy of Medical Sciences & Pek…. Die Arbeit wurde bisher 11-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
The increase in the use of ultrasound-guided interventional therapy for cardiovascular diseases has increased the importance of intraoperative real-time cardiac ultrasound image interpretation. We thus aimed to develop a deep learning-based model to accurately identify, localize, and track the critical cardiac structures and lesions (9 kinds in total) and to validate the algorithm's performance using independent data sets.
Methods
This diagnostic study developed a deep learning-based model using data collected from Fuwai Hospital between January 2018 and June 2019. The model was validated with independent French and American data sets. In total, 17,114 cardiac structures and lesions were used to develop the algorithm. The model findings were compared with those of 15 specialized physicians in multiple centers. For external validation, 516,805 tags and 27,938 tags were used from 2 different data sets.
Results
Regarding structure identification, the area under the receiver operating characteristic curve (AUC) of each structure in the training data set, optimal performance in the test data set, and median AUC of each structure identification were 1 (95% CI: 1-1), 1 (95% CI: 1-1), and 1 (95% CI: 1-1), respectively. Regarding structure localization, the optimal average accuracy was 0.83. As for structure identification, the accuracy of the model significantly outperformed the median performance of the experts (P
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Structural Heart Disease, National Center for Cardiovascular Disease, China & Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
- National Health Commission Key Laboratory of Cardiovascular Regeneration Medicine, Beijing, China.
- Key Laboratory of Innovative Cardiovascular Devices, Chinese Academy of Medical Sciences, Beijing, China.
- National Clinical Research Center for Cardiovascular Diseases, Fuwai Hospital, Chinese Academy of Medical Sciences, Beijing, China.
- Pediatric Cardiac Surgery, Zhengzhou University People's Hospital, Henan Provincial People's Hospital, Huazhong Fuwai Hospital, Zhengzhou, China.
- Department of echocardiography, Fuwai Yunnan Cardiovascular Hospital, Kunming, China.
Zitieren
APA
Liu, Z., Li, W., Li, H., Zhang, F., Ouyang, W., Wang, S., Wang, C., Luo, Z., Wang, J., Chen, Y., Cao, Y., Liu, F., Huang, G., & Pan, X. (2023). Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery. Journal of Thoracic Disease, 15(4), 2129-2140. https://doi.org/10.21037/jtd-23-470
Vancouver
Liu Z, Li W, Li H, Zhang F, Ouyang W, Wang S, et al. Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery. Journal of Thoracic Disease. 2023;15(4):2129-2140. doi:10.21037/jtd-23-470
BibTeX
@article{Liu2023,
author = {Liu, Zeye and Li, Wenchao and Li, Hang and Zhang, Fengwen and Ouyang, Wenbin and Wang, Shouzheng and Wang, Cheng and Luo, Zhiling and Wang, Jinduo and Chen, Yan and Cao, Yinyin and Liu, Fang and Huang, Guoying and Pan, Xiangbin},
title = {Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery},
journal = {Journal of Thoracic Disease},
year = {2023},
volume = {15},
number = {4},
pages = {2129--2140},
doi = {10.21037/jtd-23-470}
}
EUVIMED