X-ray lung disease automatic positioning method based on weak supervised learning

Abstract

The invention provides an X-ray lung disease automatic positioning method based on weak supervised learning. The method comprises the following steps: collecting a plurality of lung X-ray films for initial marking, and arranging the lung X-ray films into a training set; preprocessing the training set; constructing a deep learning neural network based on the class activation graph and provided witha self-supervision attention module, performing multi-angle rotation on the processed lung X-ray film, and inputting the lung X-ray film into the deep learning neural network; judging the input lungX-ray film through a loss function set in the deep learning neural network; in the training process, optimizing the loss function after the judgment result is compared with an initial mark to obtain an optimized deep learning neural network; and inputting a new lung X-ray film into the optimized deep learning neural network, and positioning a focus displayed in the newly input lung X-ray film; andthe method has the characteristics of efficiently and accurately positioning the focus, reducing the judgment time of doctors, assisting the doctors to make decisions and improving the working efficiency.

Description

technical field [0001] The invention specifically relates to a method for automatically locating X-ray lung diseases based on weakly supervised learning. Background technique [0002] The respiratory system consists of the airways (nose, pharynx, larynx, trachea and bronchi at all levels) and alveoli. The lungs are the main organs of the respiratory system, which inhale new air into the lungs and expel carbon dioxide after metabolism. Pulmonary disease is a respiratory system disease, which is a disease of the lung itself or a pulmonary manifestation of a systemic disease. This gas exchange is called respiration. Lung X-ray, as an essential item for lung disease examination, plays an important role in the screening and diagnosis of various lung diseases. As a complete diagnostic process, the identification and judgment of lung diseases is only one step. Another important task is to locate the location of the lesion on the original X-ray film. With the continuous develop...

AI Technical Summary

Problems solved by technology

However, this work has progressed slowly due to the time and effort required by professionals to label medical images at the pixel level

Images