High spatial resolution cardiac T1 mapping on 1.5T and 3T utilizing deep learning-based image reconstruction

Motivation: MOLLI T1 mapping of the heart has limited spatial resolution due to the limitation of acquiring inversion recovery images in single-shot acquisitions. Goal(s): To increase the spatial resolution of T1 maps using k-space undersampling and reconstruction with a dedicated neural network. Approach: Single-shot acquisitions are accelerated using a k-t sampling pattern (across TI images) and reconstructed using a variational network. A prototype reconstruction was integrated inline into the existing vendor software. Results: The proposed method allows for higher resolution T1 maps up to (1.13 mm)2. Corresponding T1 values show good agreement with T1 values computed by a vendor sequence. Impact: The acquisition of higher spatial resolution T1 maps is achieved for both 1.5T and 3T systems. The proposed method may improve the detection of small focal lesions without increasing the required scan time or breath hold duration.