Neural networks with personalized training for improved MOLLI T mapping.

BACKGROUND

The aim of this study was to develop a method for personalized training of Deep Neural Networks by means of an MRI simulator to improve MOLLI native T estimates relative to conventional fitting methods.

METHODS

The proposed Personalized Training Neural Network (PTNN) for T mapping was based on a neural network which was trained with simulated MOLLI signals generated for each individual scan, taking into account both the pulse sequence parameters and the heart rate triggers of the specific healthy volunteer. Experimental data from eleven phantoms and ten healthy volunteers were included in the study.

RESULTS

In phantom studies, agreement between T reference values and those obtained with the PTNN yielded a statistically significant smaller bias than conventional fitting estimates (-26.69 ± 29.5ms vs. -65.0 ± 33.25ms, p < 0.001). For in vivo studies, T estimates derived from the PTNN yielded higher T values (1152.4 ± 25.8ms myocardium, 1640.7 ± 30.6ms blood) than conventional fitting (1050.8 ± 24.7ms myocardium, 1597.2 ± 39.9ms blood). For PTNN, shortening the acquisition time by eliminating the pause between inversion pulses yielded higher myocardial T values (1162.2 ± 19.7ms with pause vs. 1127.1 ± 19.7ms, p = 0.01 myocardium), (1624.7 ± 33.9ms with pause vs. 1645.4 ± 18.7ms, p = 0.16 blood). For conventional fitting statistically significant differences were found.

CONCLUSIONS

Compared to T maps derived by conventional fitting, PTNN is a post-processing method that yielded T maps with higher values and better accuracy in phantoms for a physiological range of T and T values. In normal volunteers PTNN yielded higher T values even with a shorter acquisition scheme of eight heartbeats scan time, without deploying new pulse sequences.