CT image segmentation method based on improved AU-Net network

Abstract

The invention belongs to the field of image processing, and particularly relates to a CT image segmentation method based on an improved AU-Net network, and the method comprises the steps: obtaining a to-be-segmented brain CT image, and carrying out the preprocessing of the obtained brain CT image; inputting the processed image into the trained improved AU-Net network for image recognition and segmentation to obtain a segmented CT image; identifying a cerebral hemorrhage area according to the segmented brain CT image. The improved AU-Net network comprises an encoder, a decoder and a hopping connection part. Aiming at the problem of low segmentation precision caused by large size and shape difference of the hemorrhage part of the cerebral hemorrhage CT image, the invention provides a coding-decoding-based structure, and a residual octave convolution module is designed in the structure, so that the model can segment and identify the image more accurately.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a CT image segmentation method based on an improved AU-Net network. Background technique [0002] Cerebral hemorrhage refers to primary cerebral parenchymal hemorrhage, also known as cerebral hematoma, which can be detected by magnetic resonance imaging (Magnetic Resonance Imaging, MRI), computed tomography (Computed-Tomography, CT), ultrasound (Ultrasound, US) and other medical imaging techniques The obtained organ anatomy map can objectively reflect the pathological changes of the patients. Clinically, cerebral hemorrhage appears as a bright area on CT images, and normal brain soft tissues appear as black on CT images. The doctor judged the hemorrhage volume and other relevant indicators based on the cerebral hemorrhage area shown on each CT image combined with experience. Use image segmentation technology to segment the target area of ​​each cerebral hemorrhage CT image, calc...

AI Technical Summary

Problems solved by technology

[0005] There are limitations when the above-mentioned prior art is directly applied to CT image segmentation of cerebral hemorrhage; due to the complexity of the structure of the human brain, the pixel features of the cerebral hemorrhage area on the CT image are very similar to the pixel features of the skull. , the pixels in the skull will interfere with the lesion area; cerebral hemorrhage lesions have variability in hemorrhage position and scale on CT images, resulting in uneven distribution of target areas on the sample, which is not conducive to extracting image features during the neural network training stage, thus affect the segmentation effect, therefore, there is an urgent need for a brain CT image segmentation model for image segmentation processing

Images