US 12,380,613 B2
Medical image noise reduction method, system, terminal, and storage medium
Hairong Zheng, Shenzhen (CN); Xin Liu, Shenzhen (CN); Na Zhang, Shenzhen (CN); Zhanli Hu, Shenzhen (CN); Dong Liang, Shenzhen (CN); Yongfeng Yang, Shenzhen (CN); and Qi Yang, Shenzhen (CN)
Assigned to SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY, Shenzhen (CN)
Filed by SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY, Shenzhen (CN)
Filed on Sep. 27, 2022, as Appl. No. 17/953,356.
Application 17/953,356 is a continuation of application No. PCT/CN2020/135431, filed on Dec. 10, 2020.
Prior Publication US 2023/0033666 A1, Feb. 2, 2023
Int. Cl. G06T 11/00 (2006.01); G06N 3/0475 (2023.01); G06V 10/30 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01)
CPC G06T 11/008 (2013.01) [G06N 3/0475 (2023.01); G06V 10/30 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01)] 12 Claims
OG exemplary drawing
 
1. A medical image noise reduction method, comprising:
obtaining a standard-dose PET image and a constant-value image;
inputting the standard-dose PET image and the constant-value image into a decay function to obtain a respective low-dose noisy PET image and noisy constant-value image;
assembling the low-dose noisy PET image and the noisy constant-value image in a width dimension or a height dimension, and then inputting the assembly of the low-dose noisy PET image and the noisy constant-value image into a trained conjugate generative adversarial network, and outputting a denoised PET image and constant-value image output through the conjugate generative adversarial network;
wherein the conjugate generative adversarial network comprises a generator and a discriminator;
wherein the generator comprises a reflective padding layer, a convolution layer, an instance normalization layer, a nonlinear layer, a residual module, an upsampling layer, and a nonlinear layer; and
wherein the discriminator is a convolutional neural network classifier, and comprises a convolutional layer, an instance normalization layer, and a nonlinear layer;
wherein the generator comprises two parts: feature extraction and image reconstruction;
wherein in the feature extraction part, the input low-dose noisy PET image and noisy constant-value image are first processed using the padding layer, the convolutional layer, the instance normalization layer and the nonlinear layer; then four groups of feature extraction modules are used to perform feature extraction on the low-dose noisy PET image and the noisy constant-value image; then the extracted features are processed using three residual modules;
wherein in the image reconstruction part, the PET image and the constant-value image are first gradually reconstructed through four upsampling modules based on the extracted features; then the reconstructed PET image and constant-value image are processed using the padding layer, the convolution layer and the nonlinear layer, and the denoised PET image and constant-value image are output.