December 19, 2022Scientific ReportsOpen Access

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

View Full Paper

Ask AI

Bookmark

Why the study?

Diagnosing acute thoracic aortic dissection is challenging, and plain chest x-rays used for initial screening or diagnosis have limited diagnostic accuracy.

Does a residual neural network (ResNet18) accurately detect acute thoracic aortic dissection on plain chest radiography?

Structured PICO

Does a residual neural network (ResNet18) accurately detect acute thoracic aortic dissection on plain chest radiography?

Population

3,331 patients with chest x-ray images (716 positive for acute thoracic aortic dissection and 2,615 negative)

Intervention

Residual neural network 18 (ResNet18) deep learning model applied to plain chest radiography

Outcome

Diagnostic accuracy for detecting acute thoracic aortic dissectionsurrogate

A deep learning model (ResNet18) applied to plain chest radiographs demonstrated high diagnostic accuracy (90.20%) and recall (94.44%) for detecting acute thoracic aortic dissection.

Limitations

Further research is required to improve diagnostic accuracy based on aorta segmentation

Implication

AI-assisted chest radiography may accelerate triage for suspected aortic dissection; leaves open whether prospective deployment improves clinical.

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.