# Neural networks with personalized training for improved MOLLI T1 mapping

## TL;DR

This study introduces a personalized neural network method to improve T1 mapping in MRI, showing better accuracy and higher T1 values compared to traditional methods.

## Contribution

A novel personalized training approach for neural networks using MRI simulations to enhance MOLLI T1 mapping accuracy.

## Key findings

- PTNN showed significantly smaller bias in phantom T1 estimates compared to conventional fitting methods.
- In vivo studies revealed higher T1 values in myocardium and blood using PTNN compared to conventional fitting.
- PTNN achieved higher myocardial T1 values with a shorter acquisition time without new pulse sequences.

## Abstract

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 T1 estimates relative to conventional fitting methods.

The proposed Personalized Training Neural Network (PTNN) for T1 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.

In phantom studies, agreement between T1 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, T1 estimates derived from the PTNN yielded higher T1 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 T1 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.

Compared to T1 maps derived by conventional fitting, PTNN is a post-processing method that yielded T1 maps with higher values and better accuracy in phantoms for a physiological range of T1 and T2 values. In normal volunteers PTNN yielded higher T1 values even with a shorter acquisition scheme of eight heartbeats scan time, without deploying new pulse sequences.