Low-dose CT reconstruction method based on interpolation convolutional neural network
A convolutional neural network and low-dose technology, which is applied in the field of low-dose CT reconstruction based on interpolation convolutional neural network, can solve the problems of missing sinusoidal information and artifacts in CT images, and achieves faster training speed and better reconstruction effect. , the effect of increasing stability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0037] figure 1 It is a flowchart of a low-dose CT reconstruction method based on an interpolation convolutional neural network in the present invention.
[0038] In this example, if figure 1 Shown, a kind of low-dose CT reconstruction method based on interpolation convolutional neural network of the present invention comprises the following steps:
[0039] S1. Construct a training data set, specifically as figure 2 shown, including the following steps:
[0040] S1.1. Acquire standard-dose CT images of different patients, and perform Radon transformation on each image to obtain a standard-dose projection sinogram;
[0041] S1.2. Quantize the projection sinogram to (0, 1), thereby obtaining a 512×512 standard dose projection sinogram;
[0042] S1.3. Extract the odd-numbered columns to obtain a simulated low-dose projection sinogram with a size of 512×256, and the remaining even-numbered columns are used as the desired interpolation diagram with a size of 512×256;
[0043]...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


