Kernel-based framework to estimate deformations of pneumothorax lung using relative position of anatomical landmarks
作者：
Highlights：
• Deformation estimation method of 3D surface of pneumothorax lung is proposed.
• Whole lung deformation is estimated from a few partial observations of landmarks.
• Data-driven estimation with kernel regression using data sample per mesh vertex.
• Performance of the proposed method is evaluated on the lungs of live Beagle dogs.
• The proposed method only requires a small number of training cases.
摘要
•Deformation estimation method of 3D surface of pneumothorax lung is proposed.•Whole lung deformation is estimated from a few partial observations of landmarks.•Data-driven estimation with kernel regression using data sample per mesh vertex.•Performance of the proposed method is evaluated on the lungs of live Beagle dogs.•The proposed method only requires a small number of training cases.
论文关键词：Deformation estimation,Kernel regression,Lung surgery,Medical imaging,Pneumothorax
论文评审过程：Received 28 August 2020, Revised 29 March 2021, Accepted 23 May 2021, Available online 31 May 2021, Version of Record 11 June 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115288
