Direct left-ventricular global longitudinal strain (GLS) computation with a fully convolutional network

• Published in: Journal of biomechanics Vol. 130; p. 110878
• Main Authors: Kar, Julia, Cohen, Michael V., McQuiston, Samuel A., Poorsala, Teja, Malozzi, Christopher M.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2022; Elsevier Limited
• Subjects: Automation; Breast cancer; Breast Neoplasms; Cardiotoxicity; Chemotherapy; Computation; Correlation coefficients; Deep Learning; DENSE; Echoes; Female; Fully convolutional network; Heart; Heart Ventricles - diagnostic imaging; Human performance; Humans; Image acquisition; Image processing; Image segmentation; Interpolation; Machine learning; Magnetic Resonance Imaging; Medical imaging; Medical research; Noise levels; Patients; Phase unwrapping; Phases; Reliability analysis; Reproducibility of Results; Semantics; Signal to noise ratio; Ventricle; DENSE; Phase-unwrapping; Fully convolutional network; Cardiotoxicity; Deep-learning
• ISSN: 0021-9290; 1873-2380; 1873-2380
• DOI: 10.1016/j.jbiomech.2021.110878

This study's purpose was to develop a direct MRI-based, deep-learning semantic segmentation approach for computing global longitudinal strain (GLS), a known metric for detecting left-ventricular (LV) cardiotoxicity in breast cancer. Displacement Encoding with Stimulated Echoes cardiac image phases acquired from 30 breast cancer patients and 30 healthy females were unwrapped via a DeepLabV3 + fully convolutional network (FCN). Myocardial strains were directly computed from the unwrapped phases with the Radial Point Interpolation Method. FCN-unwrapped phases of a phantom’s rotating gel were validated against quality-guided phase-unwrapping (QGPU) and robust transport of intensity equation (RTIE) phase-unwrapping. FCN performance on unwrapping human LV data was measured with F1 and Dice scores versus QGPU ground-truth. The reliability of FCN-based strains was assessed against RTIE-based strains with Cronbach's alpha (C-α) intraclass correlation coefficient. Mean squared error (MSE) of unwrapping the phantom experiment data at 0 dB signal-to-noise ratio were 1.6, 2.7 and 6.1 with FCN, QGPU and RTIE techniques. Human data classification accuracies were F1 = 0.95 (Dice = 0.96) with FCN and F1 = 0.94 (Dice = 0.95) with RTIE. GLS results from FCN and RTIE were −16 ± 3% vs. −16 ± 3% (C-α = 0.9) for patients and −20 ± 3% vs. −20 ± 3% (C-α = 0.9) for healthy subjects. The low MSE from the phantom validation demonstrates accuracy of phase-unwrapping with the FCN and comparable human subject results versus RTIE demonstrate GLS analysis accuracy. A deep-learning methodology for phase-unwrapping in medical images and GLS computation was developed and validated in a heterogeneous cohort.