A Patch-Wise Deep Learning Approach for Myocardial Blood Flow Quantification with Robustness to Noise and Nonrigid Motion.

Quantitative analysis of dynamic contrast-enhanced cardiovascular MRI (cMRI) datasets enables the assessment of myocardial blood flow (MBF) for objective evaluation of ischemic heart disease in patients with suspected coronary artery disease. State-of-the-art MBF quantification techniques use constrained deconvolution and are highly sensitive to noise and motion-induced errors, which can lead to unreliable outcomes in the setting of high-resolution MBF mapping. To overcome these limitations, recent iterative approaches incorporate spatial-smoothness constraints to tackle pixel-wise MBF mapping. However, such iterative methods require a computational time of up to 30 minutes per acquired myocardial slice, which is a major practical limitation. Furthermore, they cannot enforce robustness to residual nonrigid motion which can occur in clinical stress/rest studies of patients with arrhythmia. We present a non-iterative patch-wise deep learning approach for pixel-wise MBF quantification wherein local spatio-temporal features are learned from a large dataset of myocardial patches acquired in clinical stress/rest cMRI studies. Our approach is scanner-independent, computationally efficient, robust to noise, and has the unique feature of robustness to motion-induced errors. Numerical and experimental results obtained using real patient data demonstrate the effectiveness of our approach.Clinical Relevance- The proposed patch-wise deep learning approach significantly improves the reliability of high-resolution myocardial blood flow quantification in cMRI by improving its robustness to noise and nonrigid myocardial motion and is up to 300-fold faster than state-of-the-art iterative approaches.

Retrospective Detection and Suppression of Dark-Rim Artifacts in First-Pass Perfusion Cardiac MRI Enabled by Deep Learning.

The dark-rim artifact (DRA) remains an important challenge in the routine clinical use of first-pass perfusion (FPP) cardiac magnetic resonance imaging (cMRI). The DRA mimics the appearance of perfusion defects in the subendocardial wall and reduces the accuracy of diagnosis in patients with suspected ischemic heart disease. The main causes for DRA are known to be Gibbs ringing and bulk motion of the heart. The goal of this work is to propose a deep-learning-enabled automatic approach for the detection of motion-induced DRAs in FPP cMRI datasets. To this end, we propose a new algorithm that can detect the DRA in individual time frames by analyzing multiple reconstructions of the same time frame (k-space data) with varying temporal windows. In addition to DRA detection, our approach is also capable of suppressing the extent and severity of DRAs as a byproduct of the same reconstruction-analysis process. In this proof-of-concept study, our proposed method showed a good performance for automatic detection of subendocardial DRAs in stress perfusion cMRI studies of patients with suspected ischemic heart disease. To the best of our knowledge, this is the first approach that performs deep-learning-enabled detection and suppression of DRAs in cMRI.Clinical Relevance- Our approach enables clinicians to provide a more accurate diagnosis of ischemic heart disease by detecting and suppressing subendocardial dark-rim artifacts in first-pass perfusion cMRI datasets.