A Novel Unsupervised MRI Synthetic CT Image Generation Framework with Registration Network

作     者：Liwei Deng Henan Sun Jing Wang Sijuan Huang Xin Yang 

作者机构：Heilongjiang Provincial Key Laboratory of Complex Intelligent System and IntegrationSchool of AutomationHarbin University of Science and TechnologyHarbin150080China Institute for Brain Research and RehabilitationSouth China Normal UniversityGuangzhou510631China Department of Radiation OncologySun Yat-sen University Cancer CenterState Key Laboratory of Oncology in South ChinaCollaborative Innovation Center for Cancer MedicineGuangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and TherapyGuangzhou510060China 

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

年 卷 期：2023年第77卷第11期

页      面：2271-2287页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the National Science Foundation for Young Scientists of China(Grant No.61806060) 2019-2021,the Basic and Applied Basic Research Foundation of Guangdong Province(2021A1515220140) the Youth Innovation Project of Sun Yat-sen University Cancer Center(QNYCPY32) 

主　　题：MRI-CT image synthesis variational auto-encoder medical image translation MRI-only based radiotherapy 

摘      要：In recent years,radiotherapy based only on Magnetic Resonance(MR)images has become a hot spot for radiotherapy planning research in the current medical ***,functional computed tomography(CT)is still needed for dose calculation in the *** deep-learning approaches to synthesized CT images from MR images have raised much research interest,making radiotherapy based only on MR images *** this paper,we proposed a novel unsupervised image synthesis framework with registration *** paper aims to enforce the constraints between the reconstructed image and the input image by registering the reconstructed image with the input image and registering the cycle-consistent image with the input ***,this paper added ConvNeXt blocks to the network and used large kernel convolutional layers to improve the network’s ability to extract *** research used the collected head and neck data of 180 patients with nasopharyngeal carcinoma to experiment and evaluate the training model with four evaluation *** the same time,this research made a quantitative comparison of several commonly used model *** evaluate the model performance in four evaluation metrics which achieve Mean Absolute Error(MAE),Root Mean Square Error(RMSE),Peak Signal-to-Noise Ratio(PSNR),and Structural Similarity(SSIM)are 18.55±1.44,86.91±4.31,33.45±0.74 and 0.960±0.005,*** with other methods,MAE decreased by 2.17,RMSE decreased by 7.82,PSNR increased by 0.76,and SSIM increased by *** results show that the model proposed in this paper outperforms other methods in the quality of image *** work in this paper is of guiding significance to the study of MR-only radiotherapy planning.