Automatic liver tumor segmentation from CT images using hierarchical iterative superpixels and local statistical features
作者：
Highlights：
• A local information based SLIC is introduced for superpixel decomposition.
• A hierarchical iterative strategy is designed to produce homogeneous sub-regions.
• Various types of features are employed to discriminate between tumor and non-tumor.
• A Euclidean distance-based voting model is proposed to identify tumor region.
• Extensive experiments demonstrate the superiority of our method.
摘要
•A local information based SLIC is introduced for superpixel decomposition.•A hierarchical iterative strategy is designed to produce homogeneous sub-regions.•Various types of features are employed to discriminate between tumor and non-tumor.•A Euclidean distance-based voting model is proposed to identify tumor region.•Extensive experiments demonstrate the superiority of our method.
论文关键词：Liver tumor segmentation,CT image,Superpixel decomposition,Feature extraction
论文评审过程：Received 12 April 2021, Revised 24 January 2022, Accepted 25 April 2022, Available online 6 May 2022, Version of Record 13 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117347
