Calibrationless Reconstruction of Uniformly-Undersampled Multi-Channel MR Data with Deep Learning Estimated ESPIRiT Maps

TL;DR

This paper introduces a deep learning method to estimate ESPIRiT maps directly from uniformly-undersampled multi-channel MR data, enabling calibrationless parallel imaging reconstruction without the need for autocalibration data.

Contribution

The authors develop a U-Net based deep learning model that predicts ESPIRiT maps from undersampled MR data, eliminating the need for traditional calibration procedures.

Findings

Predicted ESPIRiT maps are highly comparable to reference maps.

Reconstruction quality remains high even at high acceleration factors.

Method generalizes well across different datasets and protocols.

Abstract

Purpose: To develop a truly calibrationless reconstruction method that derives 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 coil and protocol specific data.