Liver CT sequence segmentation based with improved U-Net and graph cut

作者：

Highlights：

• We proposed a new framework to obtain advanced semantic features from images.

• The context information is used to construct the energy function.

• And the probability map is used to construct the energy function.

• Graph cut is used to smooth the boundary of segments.

摘要

•We proposed a new framework to obtain advanced semantic features from images.•The context information is used to construct the energy function.•And the probability map is used to construct the energy function.•Graph cut is used to smooth the boundary of segments.

论文关键词：Liver segmentation,Deep learning,Graph cut,U-Net,GIU-Net

论文评审过程：Received 22 September 2018, Revised 19 January 2019, Accepted 20 January 2019, Available online 27 January 2019, Version of Record 19 February 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.055