A 3D deep learning pipeline combined with feature tracking for left heart segmentation outperformed 2D-DL (Dice 0.94 vs 0.90, P=0.002) and achieved human-level strain reproducibility.
Observational (n=684)
Does a deep learning-based pipeline combined with feature tracking provide reliable automated estimation of left ventricular and left atrial longitudinal myocardial strain from long-axis CMR images compared to semiautomated reference standards?
A novel deep learning-based pipeline combined with feature tracking provides fully automated, reliable left ventricular and left atrial strain measures from long-axis CMR images, reaching human reproducibility.
Absolute Event Rate: 0.94% vs 0.9%
p-value: p=0.002
Abstract Aims Feature tracking (FT) is increasingly used on dynamic cardiac magnetic resonance (CMR) images for myocardial strain evaluation but often requires manual initialization, which is tedious and source of variability, especially on the challenging long-axis (LAX) images. Accordingly, we designed a pipeline combining deep learning (DL) with FT for left ventricular (LV) and left atrial (LA) longitudinal myocardial strain estimation. Methods and results We studied a multivendor database of 684 individuals divided into: training = 845, tuning = 281, and testing = 116 LAX-CMR cine 2- and/or 4-chamber views. Images were centre cropped. Then, a 2D- and 3D-ResUnet, which considers time as the third dimension, were designed for LV/LA segmentation and used to (i) estimate LV and LA strains (Full 2D−/3D-DL) and (ii) initialize an FT algorithm and further derive LV and LA strains (FT-initialized by 2D−/3D-DL). Left ventricular and LA contours and strain peaks were compared against reference standard (RS) measures performed by an expert using a semiautomated software. Intraclass-correlation-coefficient (ICC) was used to study reproducibility. 3D-DL outperformed 2D-DL segmentation (Dice-scores: 0.94 ± 0.02 vs. 0.90 ± 0.09, P = 0.002) and was stable across vendors, field strengths and imaging views. The added value of combining DL with FT was revealed by higher correlations and lower Bland–Altman biases against RS for FT initialized by 3D-DL strains (r ≥ 0.91, |mean-bias|≤0.65%) than for full 3D-DL strains (r ≤ 0.80, |mean-bias|3.07%). Semiautomated human vs. FT initialized by 3D-DL (ICC ≥ 0.76) and inter-human strain reproducibility was equivalent. Conclusion Generalizable DL-based LV and LA segmentation on LAX-CMR images was proposed. Its combination with FT resulted in fully automated and reliable LV and LA strain measures, reaching human reproducibility.
Leite et al. (2024) conducted an observational in Individuals undergoing cardiac magnetic resonance imaging (n=684). 3D deep learning combined with feature tracking (FT initialized by 3D-DL) vs. 2D deep learning and expert reference standard was evaluated on Dice-scores for left ventricular and left atrial segmentation (p=0.002). A 3D deep learning pipeline combined with feature tracking for left heart segmentation outperformed 2D-DL (Dice 0.94 vs 0.90, P=0.002) and achieved human-level strain reproducibility.