Dynamic MRI interpolation in temporal direction using an unsupervised generative model

• Published in: Computerized medical imaging and graphics Vol. 117; p. 102435
• Main Authors: Maciel, Corbin, Zou, Qing
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.10.2024
• Subjects: Cardiac cine MRI; Deep generative model; Internal Medicine; Interpolation in time; Other; Unsupervised learning; Deep generative model; Cardiac cine MRI; Interpolation in time; Unsupervised learning
• DOI: 10.1016/j.compmedimag.2024.102435
• ISSN: 0895-6111; 1879-0771

Cardiac cine magnetic resonance imaging (MRI) is an important tool in assessing dynamic heart function. However, this technique requires long acquisition time and long breath holds, which presents difficulties. The aim of this study is to propose an unsupervised neural network framework that can perform cardiac cine interpolation in time, so that we can increase the temporal resolution of cardiac cine without increasing acquisition time. In this study, a subject-specific unsupervised generative neural network is designed to perform temporal interpolation for cardiac cine MRI. The network takes in a 2D latent vector in which each element corresponds to one cardiac phase in the cardiac cycle and then the network outputs the cardiac cine images which are acquired on the scanner. After the training of the generative network, we can interpolate the 2D latent vector and input the interpolated latent vector into the network and the network will output the frame-interpolated cine images. The results of the proposed cine interpolation neural network (CINN) framework are compared quantitatively and qualitatively with other state-of-the-art methods, the ground truth training cine frames, and the ground truth frames removed from the original acquisition. Signal-to-noise ratio (SNR), structural similarity index measures (SSIM), peak signal-to-noise ratio (PSNR), strain analysis, as well as the sharpness calculated using the Tenengrad algorithm were used for image quality assessment. As shown quantitatively and qualitatively, the proposed framework learns the generative task well and hence performs the temporal interpolation task well. Furthermore, both quantitative and qualitative comparison studies show the effectiveness of the proposed framework in cardiac cine interpolation in time. The proposed generative model can effectively learn the generative task and perform high quality cardiac cine interpolation in time. •A subject-specific unsupervised generative neural network is designed to perform temporal interpolation for cardiac cine MRI.•2D latent vectors are interpolated to input into the generative network to output frame-interpolated cine images.•Results show the proposed generative model effectively learns and performs high-quality cardiac cine interpolation.