Deep learning–enhanced T 1 mapping with spatial‐temporal and physical constraint

Purpose To propose a reconstruction framework to generate accurate T 1 maps for a fast MR T 1 mapping sequence. Methods A deep learning–enhanced T 1 mapping method with spatial‐temporal and physical constraint (DAINTY) was proposed. This method explicitly imposed low‐rank and sparsity constraints on the multiframe T 1 ‐weighted images to exploit the spatial‐temporal correlation. A deep neural network was used to efficiently perform T 1 mapping as well as denoise and reduce undersampling artifacts. Additionally, the physical constraint was used to build a bridge between low‐rank and sparsity constraint and deep learning prior, so the benefits of constrained reconstruction and deep learning can be both available. The DAINTY method was trained on simulated brain data sets, but tested on real acquired phantom, 6 healthy volunteers, and 7 atherosclerosis patients, compared with the narrow‐band k‐space‐weighted image contrast filter conjugate‐gradient SENSE (NK‐CS) method, kt‐sparse‐SENSE (kt‐SS) method, and low‐rank plus sparsity (L+S) method with least‐squares T 1 fitting and direct deep learning mapping. Results The DAINTY method can generate more accurate T 1 maps and higher‐quality T 1 ‐weighted images compared with other methods. For atherosclerosis patients, the intraplaque hemorrhage can be successfully detected. The computation speed of DAINTY was 10 times faster than traditional methods. Meanwhile, DAINTY can reconstruct images with comparable quality using only 50% of k‐space data. Conclusion The proposed method can provide accurate T 1 maps and good‐quality T 1 ‐weighted images with high efficiency.