A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data

• Published in: Computer methods and programs in biomedicine 2021-10, Vol.210, p.106371-106371, Article 106371
• Main Authors: Moya-Sáez, Elisa, Peña-Nogales, Óscar, Luis-García, Rodrigo de, Alberola-López, Carlos
• Format: Article
• Language: English
• Subjects: Deep learning; Parametric Maps; Quantitative MRI; Synthetic MRI
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2021.106371

•Development of a learning-based approach to compute T1, T2, and PD maps from clinical routine sequences.•Computation of three realistic parametric maps from only two input images (a three-from-two approach).•Realistic maps are obtained from actual data by training the network with a synthetic dataset.•Realistic weighted images pertaining to modalities unseen by the network are obtained from the maps.•Quantitative MRI and synthetic MRI in clinical viable times. Background and Objective: Synthetic magnetic resonance imaging (MRI) is a low cost procedure that serves as a bridge between qualitative and quantitative MRI. However, the proposed methods require very specific sequences or private protocols which have scarcely found integration in clinical scanners. We propose a learning-based approach to compute T1, T2, and PD parametric maps from only a pair of T1- and T2-weighted images customarily acquired in the clinical routine. Methods: Our approach is based on a convolutional neural network (CNN) trained with synthetic data; specifically, a synthetic dataset with 120 volumes was constructed from the anatomical brain model of the BrainWeb tool and served as the training set. The CNN learns an end-to-end mapping function to transform the input T1- and T2-weighted images to their underlying T1, T2, and PD parametric maps. Then, conventional weighted images unseen by the network are analytically synthesized from the parametric maps. The network can be fine tuned with a small database of actual weighted images and maps for better performance. Results:This approach is able to accurately compute parametric maps from synthetic brain data achieving normalized squared error values predominantly below 1%. It also yields realistic parametric maps from actual MR brain acquisitions with T1, T2, and PD values in the range of the literature and with correlation values above 0.95 compared to the T1 and T2 maps obtained from relaxometry sequences. Further, the synthesized weighted images are visually realistic; the mean square error values are always below 9% and the structural similarity index is usually above 0.90. Network fine tuning with actual maps improves performance, while training exclusively with a small database of actual maps shows a performance degradation. Conclusions:These results show that our approach is able to provide realistic parametric maps and weighted images out of a CNN that (a) is trained with a synthetic dataset and (b) needs only two inputs, which