Comparison of iterative parametric and indirect deep learning‐based reconstruction methods in highly undersampled DCE‐MR Imaging of the breast

• Published in: Medical physics (Lancaster) Vol. 47; no. 10; pp. 4838 - 4861
• Main Authors: Rastogi, Aditya, Yalavarthy, Phaneendra K.
• Format: Journal Article
• Language: English
• Published: United States 01-10-2020
• Subjects: AIF; Algorithms; breast imaging; DCE‐MRI; Deep Learning; fast imaging; Humans; Image Processing, Computer-Assisted; ISTA‐Net; Kinetics; Magnetic Resonance Imaging; perfusion imaging; Retrospective Studies; under‐sampling; perfusion imaging; deep learning; DCE-MRI; under-sampling; ISTA-Net; breast imaging; AIF; fast imaging
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1002/mp.14447

Purpose
To compare the performance of iterative direct and indirect parametric reconstruction methods with indirect deep learning‐based reconstruction methods in estimating tracer‐kinetic parameters from highly undersampled DCE‐MR Imaging breast data and provide a systematic comparison of the same.
Methods
Estimation of tracer‐kinetic parameters using indirect methods from undersampled data requires to reconstruct the anatomical images initially by solving an inverse problem. This reconstructed images gets utilized in turn to estimate the tracer‐kinetic parameters. In direct estimation, the parameters are estimated without reconstructing the anatomical images. Both problems are ill‐posed and are typically solved using prior‐based regularization or using deep learning. In this study, for indirect estimation, two deep learning‐based reconstruction frameworks namely, ISTA‐Net+ and MODL, were utilized. For direct and indirect parametric estimation, sparsity inducing priors (L1 and Total‐Variation) and limited memory Broyden‐Fletcher‐Goldfarb‐Shanno algorithm as solver was deployed. The performance of these techniques were compared systematically in estimation of vascular permeability (
Ktrans
) from undersampled DCE‐MRI breast data using Patlak as pharmaco‐kinetic model. The experiments involved retrospective undersampling of the data 20×, 50×, and 100× and compared the results using PSNR, nRMSE, SSIM, and Xydeas metrics. The
Ktrans
maps estimated from fully sampled data were utilized as ground truth. The developed code was made available as https://github.com/Medical‐Imaging‐Group/DCE‐MRI‐Compare open‐source for enthusiastic users.
Results
The reconstruction methods performance was evaluated using ten patients breast data (five patients each for training and testing). Consistent with other studies, the results indicate that direct parametric reconstruction methods provide improved performance compared to the indirect parameteric reconstruction methods. The results also indicate that for 20× undersampling, deep learning‐based methods performs better or at par with direct estimation in terms of PSNR, SSIM, and nRMSE. However, for higher undersampling rates (50× and 100×) direct estimation performs better in all metrics. For all undersampling rates, direct reconstruction performed better in terms of Xydeas metric, which indicated fidelity in magnitude and orientation of edges.
Conclusion
Deep learning‐based indirect techniques perform at par with direct estimation techniques for lower undersampling rates in the breast DCE‐MR imaging. At higher undersampling rates, they are not able to provide much needed generalization. Direct estimation techniques are able to provide more accurate results than both deep learning‐ and parametric‐based indirect methods in these high undersampling scenarios.