Three-Dimensional Local Energy-Based Shape Histogram (3D-LESH): A Novel Feature Extraction Technique

作者：

Highlights：

• A novel feature extraction technique (3D-LESH) for 3D image analysis is proposed.

• Application of proposed technique to detect cancer.

• Successful experimentation on TCGA-BRCA breast cancer MRI dataset.

• Achieved maximum classification accuracy of 99% to detect breast cancer.

• Achieved maximum classification accuracy of 95% to detect breast cancer stages.

摘要

•A novel feature extraction technique (3D-LESH) for 3D image analysis is proposed.•Application of proposed technique to detect cancer.•Successful experimentation on TCGA-BRCA breast cancer MRI dataset.•Achieved maximum classification accuracy of 99% to detect breast cancer.•Achieved maximum classification accuracy of 95% to detect breast cancer stages.

论文关键词：Clinical decision support system (CDSS),Echo state network (ESN),Extreme learning machine (ELM),Local energy-based shape histogram (LESH),Magnetic resonance imaging (MRI),Support vector machine (SVM)

论文评审过程：Received 22 March 2017, Revised 20 October 2017, Accepted 30 November 2017, Available online 5 December 2017, Version of Record 8 August 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.057