Quality control method of chest radiographs in medical radiology based on artificial intelligence

Abstract

The invention discloses an artificial intelligence deep learning method and an artificial intelligence-based quality control method for medical radiographic chest radiographs. The quality control method, on the basis of the previous continuous convolution pooling operation, adds the last After the result of the convolution pooling operation is spliced ​​and convolved with the result of the convolution pooling operation of the previous level, it is then spliced ​​and convolved with the result of the convolution pooling operation of the previous level until the first convolution The result of the pooling operation is concatenated and convoluted, and finally the data processing is completed. Through the optimization of the above learning method, it not only has the advantages of the previous continuous convolution pooling, but also through the concatenated convolution step by step, the previous continuous convolution The missing data in the pooling process is processed again, and finally the purpose of deep learning is achieved.

Description

technical field [0001] The disclosure of the invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based method for quality control of chest radiographs of medical radiographs. Background technique [0002] The chest X-ray is the χ-radiograph of the chest. When the chest X-ray is taken, the subject takes a standing position, and generally holds the breath under a calm inhalation to project. Cardiovascular conventional chest radiographs include: posteroanterior view (focal-film distance 200cm), left anterior oblique view (60°-65°), right anterior oblique view (45°-55°) and left lateral view. 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 changes of blood vessels in the lungs, and can be used to measure the heart and its diameter. The left anterior oblique view shows the general p...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention discloses an artificial intelligence-based quality control method for chest radiographs of medical radiographs, so as to at least solve the problems of low efficiency and non-uniform standards in manual quality control.

Images