Calibrationless reconstruction of uniformly-undersampled multi-channel MR data with deep learning estimated ESPIRiT maps

Zhang, Junhao1,2; Yi, Zheyuan1,2,3; Zhao, Yujiao1,2; Xiao, Linfang1,2; Hu, Jiahao1,2,3; Man, Christopher1,2; Lau, Vick1,2; Su, Shi1,2; Chen, Fei3; Leong, Alex T. L.1,2; Wu, Ed X.1,2

2023-02-01

10.1002/mrm.29625

MAGNETIC RESONANCE IN MEDICINE   影响因子和分区

0740-3194

1522-2594

Purpose: To develop a truly calibrationless reconstruction method that derives An Eigenvalue Approach to Autocalibrating Parallel MRI (ESPIRiT) maps from uniformly-undersampled multi-channel MR data by deep learning.Methods: ESPIRiT, one commonly used parallel imaging reconstruction technique, forms the images from undersampled MR k-space data using ESPIRiT maps that effectively represents coil sensitivity information. Accurate ESPIRiT map estimation requires quality coil sensitivity calibration or autocalibration data. We present a U-Net based deep learning model to estimate the multi-channel ESPIRiT maps directly from uniformly-undersampled multi-channel multi-slice MR data. The model is trained using fully-sampled multi-slice axial brain datasets from the same MR receiving coil system. To utilize subject-coil geometric parameters available for each dataset, the training imposes a hybrid loss on ESPIRiT maps at the original locations as well as their corresponding locations within the standard reference multi-slice axial stack. The performance of the approach was evaluated using publicly available T1-weighed brain and cardiac data.Results: The proposed model robustly predicted multi-channel ESPIRiT maps from uniformly-undersampled k-space data. They were highly comparable to the reference ESPIRiT maps directly computed from 24 consecutive central k-space lines. Further, they led to excellent ESPIRiT reconstruction performance even at high acceleration, exhibiting a similar level of errors and artifacts to that by using reference ESPIRiT maps.Conclusion: A new deep learning approach is developed to estimate ESPIRiT maps directly from uniformly-undersampled MR data. It presents a general strategy for calibrationless parallel imaging reconstruction through learning from the coil and protocol-specific data.

calibrationless reconstruction deep learning ESPIRiT

SCI ; EI

英语

其他

Hong Kong Research Grant Council["R7003-19F","HKU17112120","HKU17127121","HKU17127022","HKU17103819","HKU17104020","HKU17127021"] ; Guangdong Key Technologies for Treatment of Brain Disorders[2018B030332001]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:000940154200001

WILEY

20231113740101

Eigenvalues and eigenfunctions ; Learning systems ; Magnetic resonance

Ergonomics and Human Factors Engineering:461.4 ; Magnetism: Basic Concepts and Phenomena:701.2

CLINICAL MEDICINE

Web of Science

1.Univ Hong Kong, Lab Biomed Imaging & Signal Proc, Hong Kong, Peoples R China
2.Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Peoples R China
3.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen, Peoples R China

Zhang, Junhao,Yi, Zheyuan,Zhao, Yujiao,et al. Calibrationless reconstruction of uniformly-undersampled multi-channel MR data with deep learning estimated ESPIRiT maps[J]. MAGNETIC RESONANCE IN MEDICINE,2023,90(1):280-294.

Zhang, Junhao.,Yi, Zheyuan.,Zhao, Yujiao.,Xiao, Linfang.,Hu, Jiahao.,...&Wu, Ed X..(2023).Calibrationless reconstruction of uniformly-undersampled multi-channel MR data with deep learning estimated ESPIRiT maps.MAGNETIC RESONANCE IN MEDICINE,90(1),280-294.

Zhang, Junhao,et al."Calibrationless reconstruction of uniformly-undersampled multi-channel MR data with deep learning estimated ESPIRiT maps".MAGNETIC RESONANCE IN MEDICINE 90.1(2023):280-294.