Generalizable synthetic MRI with physics-informed convolutional networks

Background: Magnetic resonance imaging (MRI) provides state-of-the-art image quality for neuroimaging, consisting of multiple separately acquired contrasts. Synthetic MRI aims to accelerate examinations by synthesizing any desirable contrast from a single acquisition.

Purpose: We developed a physics-informed deep learning-based method to synthesize multiple brain MRI contrasts from a single 5-min acquisition and investigate its ability to generalize to arbitrary contrasts.

Methods: A dataset of 55 subjects acquired with a clinical MRI protocol and a 5-min transient-state sequence was used. The model, based on a generative adversarial network, maps data acquired from the five-minute scan to "effective" quantitative parameter maps (q*-maps), feeding the generated PD, T₁, and T₂ maps into a signal model to synthesize four clinical contrasts (proton density-weighted, T₁-weighted, T₂-weighted, and T₂-weighted fluid-attenuated inversion recovery), from which losses are computed. The synthetic contrasts are compared to an end-to-end deep learning-based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three contrasts unseen during training and comparing these to ground truth acquisitions via qualitative assessment and contrast-to-noise ratio (CNR) assessment.

Results: The physics-informed method matched the quality of the end-to-end method for the four standard contrasts, with structural similarity metrics above $0.75\pm 0.08$ ( $\pm$ std), peak signal-to-noise ratios above $22.4\pm 1.9$ , representing a portion of compact lesions comparable to standard MRI. Additionally, the physics-informed method enabled contrast adjustment, and similar signal contrast and comparable CNRs to the ground truth acquisitions for three sequences unseen during model training.

Conclusions: The study demonstrated the feasibility of physics-informed, deep learning-based synthetic MRI to generate high-quality contrasts and generalize to contrasts beyond the training data. This technology has the potential to accelerate neuroimaging protocols.