A multi-scale keypoint estimation network with self-supervision for spinal curvature assessment of idiopathic scoliosis from the imperfect dataset

作者：

Highlights：

• A keypoint estimation method is proposed to achieve the assessment of spinal curve.

• We incorporate the SE blocks into a multi-scale network to handle the small dataset.

• The self-supervision module is used to improve the performance of network.

摘要

•A keypoint estimation method is proposed to achieve the assessment of spinal curve.•We incorporate the SE blocks into a multi-scale network to handle the small dataset.•The self-supervision module is used to improve the performance of network.

论文关键词：Spinal curvature assessment,Keypoint estimation,Self-supervision,Imperfect dataset

论文评审过程：Received 7 September 2020, Revised 5 December 2021, Accepted 29 December 2021, Available online 20 January 2022, Version of Record 9 February 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102235