P202. Machine Learning Algorithm for Detection of Aortic Dissection on Non-contrast-enhanced CT
Fujian medicine school
Fuzhou, Fujian
China - Contact Me
I have a wealth of 15 -year cardiovascular surgery experience, focusing on providing excellent medical services and dedicated to patients' cardiovascular health. I have undergone systemic cardiovascular specialty training in Beijing Fuwai Cardiovascular Vascular Hospital and Beijing Anzhen Hospital in China. In particular, the open chest and intervention therapy of great vessels, small incision CABG and minimally invasive valve surgery.
As a team leader, I have shown excellent surgical skills and judgment in multiple complex cases. The focus of my work is not only in surgical technology, but also includes close connections with patients, provide warm care, and educate patients and their families about cardiovascular health.
I am keen to participate in academic research and medical education, and actively devote themselves to the continuous innovation in the field of cardiovascular surgery. I am a member of many International Medical Associations who often participate in international academic conferences and share the latest research results and experience with their peers. My goal is to continuously improve medical standards and provide patients with the most advanced and comprehensive cardiovascular care.
Through 15 years of practice, I know the responsibility of the doctor. My career is the unremitting pursuit of excellence in medical care. I will continue to work hard to promote the development of cardiovascular medicine, so as to better serve patients and let each heart be beating a healthy melody.
Description
Methods: This study developed a machine learning algorithm using single-center data collected between January 1, 2022, and December 31, 2022. Included in the study were 130 patients (65 with AD and 65 without AD). An AD detection algorithm was developed using a 3D full-resolution U-net architecture. We have continuously trained and developed an algorithm based on machine learning to segment the true and false lumens of the aorta and then determine whether there is aortic dissection. The algorithm's efficacy in detecting dissections was evaluated using the receiver operating characteristic (ROC) curve, including the area under the curve (AUC), sensitivity, and specificity. Furthermore, a comparative analysis of the diagnostic capabilities between our algorithm and three radiologists was conducted.
Results: The developed algorithm achieved an accuracy of 94.8%, a sensitivity of 93.6%, and a specificity of 96.6%. For radiologists, accuracy, sensitivity, and specificity were 88.9%, 90.8%, and 94.6%, respectively. The algorithm's performance was not significantly different from the mean performance of radiologists in terms of accuracy, sensitivity, or specificity.
Conclusion: The proposed algorithm showed comparable diagnostic performance to radiologists for detecting AD on non-contrast-enhanced CT, which suggests that the proposed algorithm has the potential to reduce misdiagnosis of AD to improve clinical outcomes.
Authors
zhangbo cheng (1), Lei Yin (2), Jun Yan (2), Shengmei Lin (2)
Institutions
(1) N/A, China, (2) Fujian Medical School, Fuzhou, Fujian, China, Fuzhou, NA