Key result
A two-step deep learning method combining U-Net and bidirectional convolutional LSTM achieved a dice coefficient of 0.906 for automatic segmentation of the left atrium from LGE-MRI, improving upon the 0.897 achieved by U-Net alone.
Why the study?
Manual segmentation of the left atrium for image-guided AF ablation and fibrosis quantification is labor-intensive and subjective, necessitating automatic segmentation methods.
Does a U-Net and bidirectional convolutional LSTM model accurately perform automatic segmentation of the left atrium from LGE-MRI?
Does a U-Net and bidirectional convolutional LSTM model accurately perform automatic segmentation of the left atrium from LGE-MRI?
A two-step deep learning method combining U-Net and bidirectional convolutional LSTM achieved a high dice coefficient (0.906) for automatic left atrial segmentation from LGE-MRI.
Answers are grounded in this paper and cite their sources.
Advances automated LA segmentation accuracy; leaves open prospective clinical validation before workflow integration.
Atrial fibrillation (AF) is the most common cardiac arrhythmia causing morbidity and mortality. The segmentation of the left atrium (LA) is very important for image-guided ablation of AF and quantification of left atrial fibrosis. However, manual segmentation is laborintensive and highly subjective. Therefore, the automatic segmentation of the left atrium is of great significance. In this study, we developed a U-Net based network for automatic segmentation of the left atrium. Due to the high computational cost and GPU memory consumption of 3D deep learning networks, a 2D network was used for learning. However, the 2D network only learned the features in 2D slices. The spatial context information of the images was not considered and used, so bidirectional convolutional long short-term memory (LSTM) was combined to obtain the context information in the z-axis direction. This study aimed to design a two-step method based on U-Net and bidirectional convolutional LSTM for the automatic segmentation of the left atrium from LGE-MRI. The model was trained and tested on the dataset of the 2018 Atrial Segmentation Challenge. The dice coefficient obtained by the method was 0.906. By combining the context information between image slices, the segmentation results were optimized.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2020) studied Atrial fibrillation (Left atrium segmentation) (n=100). U-Net and bidirectional convolutional LSTM vs. Original U-Net network was evaluated on Dice coefficient. A two-step deep learning method combining U-Net and bidirectional convolutional LSTM achieved a dice coefficient of 0.906 for automatic segmentation of the left atrium from LGE-MRI, improving upon the 0.897 achieved by U-Net alone.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: