An X-ray chest radiograph identification method and device

Abstract

The invention discloses an X-ray chest radiograph identification method and device, and the method comprises the steps: enabling the image data corresponding to a plurality of X-ray chest radiographswith positive positions and lateral positions distinguished to serve as the first input data of a deep convolutional network, and training the deep convolutional network; Taking the image data corresponding to the plurality of X-ray chest radiographs which are distinguished from the normal positions and the lateral positions as second input data of the deep convolutional network, and verifying thetrained deep convolutional network; And under the condition that the verification accuracy is higher than a first threshold value, inputting the X-ray chest radiograph to be distinguished into the trained deep convolutional network to obtain a recognition result. And the normal position chest radiograph and the lateral position chest radiograph can be efficiently and accurately distinguished froma large number of X-ray chest radiographs. The problem that efficiency is low due to the fact that the front lateral chest radiograph is recognized and distinguished through human eyes in the prior art is solved.

Description

technical field [0001] The present invention relates to the communication field, in particular to a method and device for identifying an X-ray chest film. Background technique [0002] Chest X-ray, clinically called chest radiography, is widely used clinically. The frontal chest radiography can show the size, shape, position and outline of the great vessels of the heart, and can observe the relationship between the heart and adjacent organs and the relationship between the blood vessels in the lungs. It can be used to measure the heart and its diameter. The left anterior oblique view shows the general picture of the aorta and the enlargement of the left and right ventricles and right atrium. Right anterior oblique view is helpful to observe the changes of left atrium enlargement, pulmonary artery segment protrusion and right ventricular infundibulum enlargement. The left side view can observe the anterior-posterior diameter of the heart and chest and thoracic deformity, wh...

AI Technical Summary

Problems solved by technology

[0003] Since most X-ray chest films are one frontal chest film and one lateral chest film, a large error will occur if the deep learning network is trained by confusing samples

However, it is very inefficient to identify and distinguish front and side chest films by human eyes.

Images