Variant Wasserstein Generative Adversarial Network Applied on Low Dose CT Image Denoising

作     者：Anoud A.Mahmoud Hanaa A.Sayed Sara S.Mohamed 

作者机构：Department of Mathematics and Computer ScienceFaculty of ScienceNew Valley UniversityNew Valley72511Egypt Department of Computer ScienceCollege of Computer Science and Engineering Taibah UniversityMedina42221KSA Department of MathematicsFaculty of ScienceAssiut UniversityAssiut71516Egypt 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第75卷第5期

页      面：4535-4552页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0801[工学-力学（可授工学、理学学位）] 

基　　金：Assiut University  AU 

主　　题：Machine learning deep learning image denoising low dose CT loss function 

摘      要：Computed Tomography(CT)images have been extensively employed in disease diagnosis and treatment,causing a huge concern over the dose of radiation to which patients are *** the radiation dose to get a better image may lead to the development of genetic disorders and cancer in the patients;on the other hand,decreasing it by using a Low-Dose CT(LDCT)image may cause more noise and increased artifacts,which can compromise the ***,image reconstruction from LDCT image data is necessary to improve radiologists’judgment and *** study proposed three novel models for denoising LDCT images based on Wasserstein Generative Adversarial Network(WGAN).They were incorporated with different loss functions,including Visual Geometry Group(VGG),Structural Similarity Loss(SSIM),and Structurally Sensitive Loss(SSL),to reduce noise and preserve important information on LDCT images and investigate the effect of different types of loss ***,experiments have been conducted on the Graphical Processing Unit(GPU)and Central Processing Unit(CPU)to compare the performance of the proposed *** results demonstrated that images from the proposed WGAN-SSIM,WGAN-VGG-SSIM,and WGAN-VGG-SSL were denoised better than those from state-of-the-art models(WGAN,WGAN-VGG,and SMGAN)and converged to a stable equilibrium compared with WGAN and *** proposed models are effective in reducing noise,suppressing artifacts,and maintaining informative structure and texture details,especially WGAN-VGG-SSL which achieved a high peak-signalto-noise ratio(PNSR)on both GPU(26.1336)and CPU(25.8270).The average accuracy of WGAN-VGG-SSL outperformed that of the state-ofthe-art methods by 1 *** prove that theWGAN-VGG-SSL is more stable than the other models on both GPU and CPU.