Convolutional neural network-based low-dose CT image decomposition method

Abstract

The invention discloses a convolutional neural network-based low-dose CT image decomposition method and belongs to the X-ray computed tomography technical field. The method of the invention includes the following steps that: step 1, training images including low-dose CT images V<ld>s and low-dose CT images V<rd>s are reconstructed, and subtraction operation is performed on the low-dose CT images V<ld>s and low-dose CT images V<rd>s, so that noise artifact images Ns can be obtained, wherein Ns, V<ld>s and V<rd>s satisfy an equation that Ns=V<ld>s-V<rd>s; step 2, a mapping convolutional neural network between the low-dose CT images V<ld>s and the noise artifact image Ns is constructed; step 3, a certain quantity of low-dose CT images V<ld>s and the corresponding noise artifact image Ns are adopted to train the constructed convolutional neural network; and step 4, the trained convolutional neural network is adopted to process selected low-dose CT images V<ld>s, so that the decomposition of anatomical structure components and noise artifact structure components in the selected low-dose CT images V<ld>s can be realized. With the method provided by the invention adopted, star-shaped artifact noises and structural features in low-dose CT images can be efficiently separated from each other.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This patented technology describes two methods for decompositing X ray tomography (XR) scans into lower levels of detail compared to previous techniques such as histogram or wavelet transform. These new approaches have been developed overall, leading to more accurate results when analyzing medical samples that contain both normal tissue and abnormal ones.

Problems solved by technology

This technical problem addressed in this patented text relates to developing efficient techniques for separating unwanted objects from scanning x ray radiations during computed tomographic angiograms (XR). Current approaches involve either performing full volume scan measurements or acquiring multiple small sections before decompositing them. These processes require expensive equipment while also increasing complexity and computational requirements compared to traditional methods like filtered backlight reduction (BP2). Therefore there is a demand for new algorithms that reduce these drawbacks without compromising their accuracy.

Images