Multi-Depth Boundary-Aware Left Atrial Scar Segmentation Network
This work addresses the tedious and error-prone task of delineating left atrial scars for medical professionals in atrial fibrillation analysis, but it is incremental as it builds on existing segmentation methods with a boundary-aware approach.
The paper tackled the problem of automatic segmentation of left atrial scars from cardiac MRI images, which is crucial for atrial fibrillation recurrence analysis, and achieved an average Dice score of 0.608 on a dataset of 20 evaluation images.
Automatic segmentation of left atrial (LA) scars from late gadolinium enhanced CMR images is a crucial step for atrial fibrillation (AF) recurrence analysis. However, delineating LA scars is tedious and error-prone due to the variation of scar shapes. In this work, we propose a boundary-aware LA scar segmentation network, which is composed of two branches to segment LA and LA scars, respectively. We explore the inherent spatial relationship between LA and LA scars. By introducing a Sobel fusion module between the two segmentation branches, the spatial information of LA boundaries can be propagated from the LA branch to the scar branch. Thus, LA scar segmentation can be performed condition on the LA boundaries regions. In our experiments, 40 labeled images were used to train the proposed network, and the remaining 20 labeled images were used for evaluation. The network achieved an average Dice score of 0.608 for LA scar segmentation.