Low-dose CT image denoising method and system based on self-supervised learning

Abstract

The invention provides a low-dose CT image denoising method and system based on self-supervised learning, and belongs to the technical field of image processing, and the method comprises the steps ofcarrying out the preprocessing of an obtained CT image, and carrying out the normalization of all pixel values of the preprocessed CT image; replacing a part of pixels of the normalized CT image by adopting a preset mask with the same size as the CT image; inputting the CT image replaced by the preset mask into a trained denoising neural network model to obtain a corresponding denoised image. According to the invention, in a network model training denoising network process; compared with the prior art, the method does not need paired LDCT images and high-dose CT images, deduces the high-dose CT pixel values of the replaced pixels through the unreplaced pixels, can greatly reduce the data collection cost, and completes the denoising task of the LDCT images under the condition of no high-dose CT images.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, in particular to a low-dose CT image denoising method and system based on self-supervised learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the continuous development of computed tomography (Computed Tomography, CT) technology, CT imaging is more and more widely used in medical diagnosis. When the X-ray radiation dose absorbed by the human body exceeds the normal range, it may induce metabolic abnormalities and even cancer and other diseases, and X-rays are accumulated throughout life, which means that with the increase in the number of CT scans, the radiation dose in the body will also accumulate , for patients who need regular CT review, repeated scans will significantly increase the risk of cancer. The harm of CT radiation ...

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present disclosure found that although the LDCT images processed by the convolutional neural network are of high quality, the traditional convolutional neural network training needs to meet two conditions. First, the paired training data, that is, the convolutional neural network is a kind of Supervised training, in the LDCT denoising task, training convolutional neural networks requires LDCT images and their corresponding high-dose images; second, the huge amount of data, that is, training convolutional neural networks requires a large number of paired CT images, in the data In the case of a small amount, the convolutional neural network cannot obtain a good denoising effect

In practical medical applications, these two conditions are difficult to meet. First, paired supervised training requires two different doses of CT imaging for the same patient at the same time period, which is difficult to operate in general medical testing, and Medical images are often collected during treatment, and the image quality will be affected by many factors. It is extremely difficult to obtain high-quality noise-free images

Secondly, unlike natural images, medical images are difficult to obtain and expensive, so the amount of data is small, and it is difficult to reach the scale of tens of thousands of images

Images