Automatic segmentation model combining U-Net and level set method for medical images
作者：
Highlights：
• A segmentation model combining level set method and U-Net is proposed.
• Our method combines the advantages of the level set method and U-Net.
• We obtain the restricted items in two ways, fully automatic and semi-automatic.
• Numerical results such as Dice and Precision values are presented.
• Experiments show that our model is better than traditional methods and U-Net.
摘要
•A segmentation model combining level set method and U-Net is proposed.•Our method combines the advantages of the level set method and U-Net.•We obtain the restricted items in two ways, fully automatic and semi-automatic.•Numerical results such as Dice and Precision values are presented.•Experiments show that our model is better than traditional methods and U-Net.
论文关键词：Image segmentation,Level set formulation,Constrained term,U-Net,Split Bregman method
论文评审过程：Received 24 April 2019, Revised 25 March 2020, Accepted 25 March 2020, Available online 29 March 2020, Version of Record 14 April 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113419
