Beyond exponential fitting: a deep learning approach for accurate and robust T1 estimation from cardiac magnetic resonance MOLLI sequences

Abstract

T1 parametric maps of the myocardium are a recent development in cardiac Magnetic Resonance Imaging (MRI). They can be used to characterize the composition of the heart and identify alterations that can be indicative of a pathology. A common method of T1 estimation involves pixel-wise non-linear curve fitting from Modified Look-Locker Inversion Recovery (MOLLI) series. Whilst relatively accurate, this method presents several drawbacks. Firstly, it assumes magnetization recovery to be a purely exponential process dependent on T1, thus neglecting other parameters such as T2 and B1 that can interfere in the process. Secondly, it does not consider that each acquisition during an inversion recovery experiment inverts the magnetization vector by a given angle and thus delays the recovery. Finally, since it considers each pixel individually, neglecting spatial information, it is sensitive to image quality. Additionally, since non-linear curve fitting is an iterative algorithm, it is computationally expensive and time-consuming. To address these issues a convolutional neural network, DeepBLESS, and two spatially-aware variants of it, were trained to predict T1, T2, and B1 with a dataset of MOLLI series simulated from experimental data. The simulation was performed using Bloch simulations. Thus, a dataset could be generated without relying on exponential fitting for ground truth generation. It was shown that the Deep Learning approaches eliminated the

underestimation bias of exponential fitting with the spatially-aware network Median- DeepBLESS being more robust to noise than both exponential fitting and the standard

DeepBLESS network for myocardial T1 estimation. Accurate estimation of T2 and B1 from MOLLI sequences was also accomplished through the Deep Learning approach, which may lead to simultaneous T1, T2, and B1 estimation in common clinical practice in the future.