Pneumonia image processing method and system and storage medium

Abstract

The invention discloses a pneumonia image processing method and system and a storage medium; the method comprises the steps: carrying out the filtering reconstruction and feature enhancement of a to-be-processed pneumonia image, and carrying out the fusion of the to-be-processed pneumonia image with an original pneumonia image, and maintaining the features of the original pneumonia image and the feature-enhanced image, thereby facilitating the subsequent neural network learning. Through verification of an InceptionV3 network, the pneumonia image is processed by adopting the method disclosed by the invention, and compared with an unprocessed pneumonia image and a pneumonia image which is processed only by using a Retinex algorithm, the obtained pneumonia image is improved in both accuracy and specificity.

Description

technical field

[0001] The present invention relates to the technical field of image processing, in particular to a pneumonia image processing method, system and storage medium. Background technique

[0002] In the case of the raging new crown pneumonia, domestic researchers in this field have proposed different methods for the rapid identification of pneumonia X-ray images. However, due to the long-term dependence on the features extracted by the convolutional neural network itself for deep learning training, many scholars have focused on the optimization of convolutional neural networks. The preprocessing of X-ray images still stays in simple denoising, enhancement and other operations.

[0003] Although the X-ray images obtained by traditional denoising, filtering, histogram equalization and other methods have been enhanced in human vision, it is easier to judge the disease, but because the difference between the normal lung image and the diseased lung image is not obvio...

Images