Machine learning algorithm for detection of aortic dissection on non-contrast-enhanced CT
Presented During:
Thursday, April 25, 2024: 5:38PM - 7:00PM
Sheraton Times Square
Posted Room Name:
Central Park
Abstract No:
P0202
Submission Type:
Abstract Submission
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
Submitting Author:
zhangbo cheng
-
Contact Me
N/A
N/A
Co-Author(s):
Lei Yin
-
Contact Me
Fujian Medical School, Fuzhou, Fujian, China
Fujian Medical School, Fuzhou, Fujian, China
Jun Yan
-
Contact Me
Fujian Medical School, Fuzhou, Fujian, China
Fujian Medical School, Fuzhou, Fujian, China
Shengmei Lin
-
Contact Me
Fujian Medical School, Fuzhou, Fujian, China
Fujian Medical School, Fuzhou, Fujian, China
Presenting Author:
zhangbo cheng
-
Contact Me
N/A
N/A
Abstract:
Objective: To propose a machine learning algorithm to detect aortic dissection on non-contrast-enhanced CT and evaluate the diagnostic ability of the algorithm compared with those of radiologists.
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.
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.
Aortic Symposium:
Dissection
Image or Table
