DeepEMC-T mapping: Deep learning-enabled T mapping based on echo modulation curve modeling.

PURPOSE

Echo modulation curve (EMC) modeling enables accurate quantification of T relaxation times in multi-echo spin-echo (MESE) imaging. The standard EMC-T mapping framework, however, requires sufficient echoes and cumbersome pixel-wise dictionary-matching steps. This work proposes a deep learning version of EMC-T mapping, called DeepEMC-T mapping, to efficiently estimate accurate T maps from fewer echoes.

METHODS

DeepEMC-T mapping was developed using a modified U-Net to estimate both T and proton density (PD) maps directly from MESE images. The network implements several new features to improve the accuracy of T/PD estimation. A total of 67 MESE datasets acquired in axial orientation were used for network training and evaluation. An additional 57 datasets acquired in coronal orientation with different scan parameters were used to evaluate the generalizability of the framework. The performance of DeepEMC-T mapping was evaluated in seven experiments.

RESULTS

Compared to the reference, DeepEMC-T mapping achieved T estimation errors from 1% to 11% and PD estimation errors from 0.4% to 1.5% with ten/seven/five/three echoes, which are more accurate than standard EMC-T mapping. By incorporating datasets acquired with different scan parameters and orientations for joint training, DeepEMC-T exhibits robust generalizability across varying imaging protocols. Increasing the echo spacing and including longer echoes improve the accuracy of parameter estimation. The new features proposed in DeepEMC-T mapping all enabled more accurate T estimation.

CONCLUSIONS

DeepEMC-T mapping enables simplified, efficient, and accurate T quantification directly from MESE images without dictionary matching. Accurate T estimation from fewer echoes allows for increased volumetric coverage and/or higher slice resolution without prolonging total scan times.