A cascaded deep learning pipeline with GAN-based synthetic data augmentation significantly improved scar segmentation compared to a single nnU-Net (mean DSC 0.72 vs 0.46, p<0.01).
Does a cascaded deep learning pipeline with GAN-based data augmentation improve automated cardiac MR scar quantification compared to a single nnU-Net?
A cascaded deep learning pipeline with GAN-based synthetic data augmentation improves the accuracy of automated cardiac MR scar quantification compared to standard direct segmentation.
Absolute Event Rate: 0.72% vs 0.46%
p-value: p=< 0.01
BACKGROUND: The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification. METHODS: A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN. RESULTS: The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively. CONCLUSION: A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.
Lustermans et al. (Wed,) conducted a other in Myocardial scar on LGE cardiac MRI. Cascaded deep learning pipeline with GAN-based synthetic data augmentation vs. Single nnU-Net without synthetic images was evaluated on Mean Dice similarity coefficient (DSC) for scar segmentation on a per-slice level (p=< 0.01). A cascaded deep learning pipeline with GAN-based synthetic data augmentation significantly improved scar segmentation compared to a single nnU-Net (mean DSC 0.72 vs 0.46, p<0.01).