Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec 19;12(1):21884.
doi: 10.1038/s41598-022-26486-3.

Detection of acute thoracic aortic dissection based on plain chest radiography and a residual neural network (Resnet)

Dong Keon Lee #  1   2 , Jin Hyuk Kim #  3 , Jaehoon Oh #  4   5 , Tae Hyun Kim #  6   7 , Myeong Seong Yoon  8 , Dong Jin Im  9 , Jae Ho Chung  8   10   11 , Hayoung Byun  8   10
Affiliations

Detection of acute thoracic aortic dissection based on plain chest radiography and a residual neural network (Resnet)

Dong Keon Lee et al. Sci Rep. .

Erratum in

Abstract

Acute thoracic aortic dissection is a life-threatening disease, in which blood leaking from the damaged inner layer of the aorta causes dissection between the intimal and adventitial layers. The diagnosis of this disease is challenging. Chest x-rays are usually performed for initial screening or diagnosis, but the diagnostic accuracy of this method is not high. Recently, deep learning has been successfully applied in multiple medical image analysis tasks. In this paper, we attempt to increase the accuracy of diagnosis of acute thoracic aortic dissection based on chest x-rays by applying deep learning techniques. In aggregate, 3,331 images, comprising 716 positive images and 2615 negative images, were collected from 3,331 patients. Residual neural network 18 was used to detect acute thoracic aortic dissection. The diagnostic accuracy of the ResNet18 was observed to be 90.20% with a precision of 75.00%, recall of 94.44%, and F1-score of 83.61%. Further research is required to improve diagnostic accuracy based on aorta segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Image pre-processing.
Figure 2
Figure 2
Model architecture of ResNet 18.
Figure 3
Figure 3
Overview of main architecture used for the diagnosis of aortic dissection.
Figure 4
Figure 4
Ensemble voting system using fivefold cross-validation.
Figure 5
Figure 5
Flow chart of data collection and analysis during acute thoracic aortic dissection detection based on deep learning algorithms.
Figure 6
Figure 6
The ROC for the trained classification model. The AUC was 0.955.
Figure 7
Figure 7
The regions of interest for aortic dissection diagnosis were visualised as heat maps based on Grad-CAM following the confusion matrix categories: (a) true positive, (b) true negative, (c) false positive, and (d) false negative.
See this image and copyright information in PMC

References

    1. Auer J, Berent R, Eber B. Aortic dissection: Incidence, natural history and impact of surgery. J. Clin. Basic. 2000;3(3):151–154.
    1. Hiratzka LF, et al. ACCF/AHA/AATS/ACR/ASA/SCA/SCAI/SIR/STS/SVM guidelines for the diagnosis and management of patients with thoracic aortic disease. A report of the American college of cardiology foundation/American heart association task force on practice guidelines, American association for thoracic surgery, American college of radiology,American stroke association, society of csardiovascular anesthesiologists, society for cardiovascular angiography and interventions, society of interventional radiology, society of thoracic surgeons,and society for vascular medicine. J. Am. Coll. Cardiol. 2010;55:e27–e129. doi: 10.1016/j.jacc.2010.02.015. - DOI - PubMed
    1. Fan KL, Leung LP. Clinical profile of patients of acute aortic dissection presenting to the ED without chest pain. Am. J. Emerg. Med. 2017;35:599–601. doi: 10.1016/j.ajem.2016.12.037. - DOI - PubMed
    1. Klompas M. Does this patient have an acute thoracic aortic dissection? JAMA. 2002;287:2262–2272. doi: 10.1001/jama.287.17.2262. - DOI - PubMed
    1. von Kodolitsch Y, et al. Chest radiography for the diagnosis of acute aortic syndrome. Am. J. Med. 2004;116:73–77. doi: 10.1016/j.amjmed.2003.08.030. - DOI - PubMed

Publication types