Image processing method and device

Abstract

The invention discloses an image processing method and device, and the method comprises the steps: carrying out training of a deep convolutional neural network through a first sample set containing abrain image marked with a ventricular segmentation result, and then segmenting the brain image through the deep convolutional neural network, so that the obtained segmentation result is quick, accurate and robust; determining the position of the actual midline plane of the brain image through the segmentation result, so that the obtained position of the actual midline plane is more accurate; and finally, comparing the position of the actual midline plane with the position of the theoretical midline plane to determine the image processing result of the to-be-detected brain image of the image. Therefore, the purpose of automatically judging brain structure displacement is achieved, the influence of whether the posture of the brain image is set right or not on the recognition result is greatly reduced, the posture of more brain images can be dealt with, and in addition, the deep convolutional neural network is adopted, so that the image processing result is more accurate.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an image processing method and device. Background technique [0002] Whether the midline of the brain is shifted is an important feature of brain imaging, which can effectively reflect whether there is an extrusion mass effect in the brain. By judging the shift of the brain midline, it can be diagnosed whether there is brain injury, stroke, Brain tumors, abscesses and other diseases. That is to say, through the judgment of brain displacement, it is beneficial to help doctors judge whether the brain is damaged or not. [0003] At present, the judgment of brain midline shift is generally realized by doctors manually measuring the midline shift distance. However, when the brain image is taken, the patient's posture may not be standard, so the obtained head image is not the head image of the standard position. In this case, it is difficult for the doctor to measure the midli...

AI Technical Summary

Problems solved by technology

However, when the brain image is taken, the patient's posture may not be standard, so the obtained head image is not the head image of the standard position. In this case, it is difficult for the doctor to measure the midline manually. The offset distance, or the measurement of the offset distance of the brain midline shift is prone to errors, and the efficiency of manual measurement is also very low, so it is difficult to judge the brain midline shift

It can be seen that the current judgment of brain midline shift has poor accuracy and low efficiency.

Images