Ultra-fast multi-parametric 4D-MRI image reconstruction for real-time applications using a downsampling-invariant deformable registration (D2R) model

被引：5

作者：

Xiao, Haonan ^{[1
,2
,3
]}

Han, Xinyang ^{[1
]}

Zhi, Shaohua ^{[1
]}

Wong, Yat-Lam ^{[1
]}

Liu, Chenyang ^{[1
]}

Li, Wen ^{[1
]}

Liu, Weiwei ^{[4
]}

Wang, Weihu ^{[4
]}

Zhang, Yibao ^{[4
]}

Wu, Hao ^{[4
]}

Lee, Ho-Fun Victor ^{[5
]}

Cheung, Lai-Yin Andy ^{[5
]}

Chang, Hing-Chiu ^{[6
]}

Liao, Yen-Peng ^{[7
]}

Deng, Jie ^{[7
]}

Li, Tian ^{[1
]}

Cai, Jing ^{[1
]}

机构：

[1] Hong Kong Polytech Univ, Dept Hlth Technol & Informat, Hong Kong 999077, Peoples R China

[2] Shandong First Med Univ, Shandong Canc Hosp & Inst, Dept Radiat Oncol & Phys, Jinan 250117, Shandong, Peoples R China

[3] Shandong Acad Med Sci, Jinan 250117, Shandong, Peoples R China

[4] Peking Univ, Canc Hosp & Inst, Beijing Canc Hosp & Inst, Dept Radiat Oncol,Minist Educ Beijing,Key Lab Carc, Beijing 100000, Peoples R China

[5] Univ Hong Kong, Dept Clin Oncol, Hong Kong 999077, Peoples R China

[6] Chinese Univ Hong Kong, Dept Biomed Engn, Hong Kong 999077, Peoples R China

[7] Univ Texas Southwestern Med Ctr, Dept Radiat Oncol, Div Med Phys & Engn, Dallas, TX 75390 USA

来源：

RADIOTHERAPY AND ONCOLOGY | 2023年 / 189卷

基金：

美国国家卫生研究院;

关键词：

Real-time; Motion management; 4D-MRI; Deformable image registration; Deep learning; RESPIRATORY SURROGATE; RADIATION-THERAPY; MOTION ESTIMATION; FRAMEWORK; COIL;

D O I：

10.1016/j.radonc.2023.109948

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Background and purpose: Motion estimation from severely downsampled 4D-MRI is essential for real-time imaging and tumor tracking. This simulation study developed a novel deep learning model for simultaneous MR image reconstruction and motion estimation, named the Downsampling-Invariant Deformable Registration (D2R) model.Materials and methods: Forty-three patients undergoing radiotherapy for liver tumors were recruited for model training and internal validation. Five prospective patients from another center were recruited for external validation. Patients received 4D-MRI scans and 3D MRI scans. The 4D-MRI was retrospectively down-sampled to simulate real-time acquisition. Motion estimation was performed using the proposed D2R model. The accuracy and robustness of the proposed D2R model and baseline methods, including Demons, Elastix, the parametric total variation (pTV) algorithm, and VoxelMorph, were compared. High-quality (HQ) 4D-MR images were also constructed using the D2R model for real-time imaging feasibility verification. The image quality and motion accuracy of the constructed HQ 4D-MRI were evaluated.Results: The D2R model showed significantly superior and robust registration performance than all the baseline methods at downsampling factors up to 500. HQ T1-weighted and T2-weighted 4D-MR images were also successfully constructed with significantly improved image quality, sub-voxel level motion error, and real-time efficiency. External validation demonstrated the robustness and generalizability of the technique.Conclusion: In this study, we developed a novel D2R model for deformation estimation of downsampled 4D-MR images. HQ 4D-MR images were successfully constructed using the D2R model. This model may expand the clinical implementation of 4D-MRI for real-time motion management during liver cancer treatment.

引用

页数：8