A cascaded nested network for 3T brain MR image segmentation guided by 7T labeling

作者：

Highlights：

• Propose CaNes-Net, trained with the labels from 7T brain MR images, for 3T MR image segmentation.

• Construct correlation coefficient map to measure 3T-to-7T brain MR image alignment.

• Design the geodesic distance maps to guide the refinement of coarse segmentation.

• Outperforms widely used segmentation methods on both private and ADNI datasets.

摘要

•Propose CaNes-Net, trained with the labels from 7T brain MR images, for 3T MR image segmentation.•Construct correlation coefficient map to measure 3T-to-7T brain MR image alignment.•Design the geodesic distance maps to guide the refinement of coarse segmentation.•Outperforms widely used segmentation methods on both private and ADNI datasets.

论文关键词：Brain segmentation,Cascaded nested network,Deep learning,Magnetic resonance imaging

论文评审过程：Received 30 December 2020, Revised 8 October 2021, Accepted 4 November 2021, Available online 6 November 2021, Version of Record 18 December 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108420