Automatic characteristic-calibrated registration (ACC-REG): Hippocampal surface registration using eigen-graphs

作者：

Highlights：

• Automatic intrinsic feature extraction on hippocampal mesh surface.

• Feature calibration by Eigen-graphs to improve consistency and accuracy of the feature correspondences on different subjects.

• Fast and accurate surface registration is available in just 5 s with minimal RMSE.

• Quantitative comparison with other existing methods demonstrates the effectiveness and efficiency of the proposed model on real data from the ADNI database.

摘要

•Automatic intrinsic feature extraction on hippocampal mesh surface.•Feature calibration by Eigen-graphs to improve consistency and accuracy of the feature correspondences on different subjects.•Fast and accurate surface registration is available in just 5 s with minimal RMSE.•Quantitative comparison with other existing methods demonstrates the effectiveness and efficiency of the proposed model on real data from the ADNI database.

论文关键词：Feature extraction,Feature correspondence,Surface registration,Surface deformation,Eigen-graph

论文评审过程：Received 17 May 2019, Revised 5 November 2019, Accepted 27 November 2019, Available online 7 January 2020, Version of Record 21 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107142