Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models
This work addresses the challenging problem of automatic segmentation of both atria from LGE MRI, which is important for atrial fibrillation diagnosis and treatment planning.
The authors developed a multi-stage framework for bi-atrial segmentation from 3D LGE MRI, achieving a mean Dice score of 0.88 for the left atrium and 0.85 for the right atrium on a held-out test set.
We report our multi-stage framework designed for the problem of multi-class bi-atrial segmentation from 3D late gadolinium-enhanced (LGE) MRI of the human heart. The pipeline consists of a preprocessing step using multidimensional contrast limited adaptive histogram equalization (MCLAHE); coarse region segmentation from MCLAHE-enhanced and down-sampled MRI using a V-Net family model; and fine segmentation from the coarse region using another V-Net model. Asymmetric loss is adopted to optimize the model weights.