Fully automated contrast selection of joint bright- and black-blood late gadolinium enhancement imaging for robust myocardial scar assessment.

PURPOSE: Joint bright- and black-blood MRI techniques provide improved scar localization and contrast. Black-blood contrast is obtained after the visual selection of an optimal inversion time (TI) which often results in uncertainties, inter- and intra-observer variability and increased workload. In this work, we propose an artificial intelligence-based algorithm to enable fully automated TI selection and simplify myocardial scar imaging. METHODS: The proposed algorithm first localizes the left ventricle using a U-Net architecture. The localized left cavity centroid is extracted and a squared region of interest ("focus box") is created around the resulting pixel. The focus box is then propagated on each image and the sum of the pixel intensity inside is computed. The smallest sum corresponds to the image with the lowest intensity signal within the blood pool and healthy myocardium, which will provide an ideal scar-to-blood contrast. The image's corresponding TI is considered optimal. The U-Net was trained to segment the epicardium in 177 patients with binary cross-entropy loss. The algorithm was validated retrospectively in 152 patients, and the agreement between the algorithm and two magnetic resonance (MR) operators' prediction of TI values was calculated using the Fleiss' kappa coefficient. Thirty focus box sizes, ranging from 2.3mm2 to 20.3cm2, were tested. Processing times were measured. RESULTS: The U-Net's Dice score was 93.0 ± 0.1%. The proposed algorithm extracted TI values in 2.7 ± 0.1 s per patient (vs. 16.0 ± 8.5 s for the operator). An agreement between the algorithm's prediction and the MR operators' prediction was found in 137/152 patients (κ= 0.89), for an optimal focus box of size 2.3cm2. CONCLUSION: The proposed fully-automated algorithm has potential of reducing uncertainties, variability, and workload inherent to manual approaches with promise for future clinical implementation for joint bright- and black-blood MRI.

Automated inversion time selection for black-blood late gadolinium enhancement cardiac imaging in clinical practice.

OBJECTIVE: To simplify black-blood late gadolinium enhancement (BL-LGE) cardiac imaging in clinical practice using an image-based algorithm for automated inversion time (TI) selection. MATERIALS AND METHODS: The algorithm selects from BL-LGE TI scout images, the TI corresponding to the image with the highest number of sub-threshold pixels within a region of interest (ROI) encompassing the blood-pool and myocardium. The threshold value corresponds to the most recurrent pixel intensity of all scout images within the ROI. ROI dimensions were optimized in 40 patients' scans. The algorithm was validated retrospectively (80 patients) versus two experts and tested prospectively (5 patients) on a 1.5 T clinical scanner. RESULTS: Automated TI selection took ~ 40 ms per dataset (manual: ~ 17 s). Fleiss' kappa coefficient for automated-manual, intra-observer and inter-observer agreements were [Formula: see text]= 0.73, [Formula: see text] = 0.70 and [Formula: see text] = 0.63, respectively. The agreement between the algorithm and any expert was better than the agreement between the two experts or between two selections of one expert. DISCUSSION: Thanks to its good performance and simplicity of implementation, the proposed algorithm is a good candidate for automated BL-LGE imaging in clinical practice.