Impact of deep learning architectures on accelerated cardiac T1 mapping using MyoMapNet

• Published in: NMR in biomedicine Vol. 35; no. 11; pp. e4794 - n/a
• Main Authors: Amyar, Amine, Guo, Rui, Cai, Xiaoying, Assana, Salah, Chow, Kelvin, Rodriguez, Jennifer, Yankama, Tuyen, Cirillo, Julia, Pierce, Patrick, Goddu, Beth, Ngo, Long, Nezafat, Reza
• Format: Journal Article
• Language: English
• Published: Oxford Wiley Subscription Services, Inc 01.11.2022
• Subjects: Accuracy; Artificial neural networks; Biological products; cardiac MRI; Coders; Data collection; Deep learning; Heart; Image quality; Inversion; inversion‐recovery cardiac T1 mapping; Mapping; myocardial tissue characterization; Myocardium; Neural networks; Performance evaluation; Training
• ISSN: 0952-3480; 1099-1492; 1099-1492
• DOI: 10.1002/nbm.4794

The objective of the current study was to investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T1 estimation using accelerated cardiac T1 mapping from four T1‐weighted images collected after a single inversion pulse (Look‐Locker 4 [LL4]). We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder‐decoder networks with skip connections (ResUNet, U‐Net). Modified Look‐Locker inversion recovery (MOLLI) images from 749 patients at 3 T were used for training, validation, and testing. The first four T1‐weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T1 mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance. Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T1 maps, and T1 values had significant errors. While ResUNet yielded good quality maps, it significantly underestimated T1. Both FC and U‐Net, however, yielded excellent image quality with good T1 accuracy for both native (FC/U‐Net/MOLLI = 1217 ± 64/1208 ± 61/1199 ± 61 ms, all p < 0.05) and postcontrast myocardial T1 (FC/U‐Net/MOLLI = 578 ± 57/567 ± 54/574 ± 55 ms, all p < 0.05). In terms of precision, the U‐Net model yielded better T1 precision compared with the FC architecture (standard deviation of 61 vs. 67 ms for the myocardium for native [p < 0.05], and 31 vs. 38 ms [p < 0.05], for postcontrast). Similar findings were observed in prospectively collected LL4 data. It was concluded that U‐Net and FC DL models in MyoMapNet enable fast myocardial T1 mapping using only four T1‐weighted images collected from a single LL sequence with comparable accuracy. U‐Net also provides a slight improvement in precision. Deep learning models allow rapid myocardial T1 mapping to be completed in a single inversion‐recovery experiment with a scan duration of four heartbeats. Among the various deep learning architectures implemented, U‐Net and fully connected neural network models in MyoMapNet enable fast myocardial T1 mapping from only four T1‐weighted images, leading to shorter scan times and rapid map reconstruction.