Local energy-based shape histogram feature extraction technique for breast cancer diagnosis

作者：

Highlights：

• Local energy-based shape histogram features for abnormality detection (mammograms).

• Experimentation on INbreast and MIAS datasets.

• Study impact of selecting subset of the features upon classification performance.

• Achieved a higher classification accuracy of 100.00% with the SVM linear.

摘要

•Local energy-based shape histogram features for abnormality detection (mammograms).•Experimentation on INbreast and MIAS datasets.•Study impact of selecting subset of the features upon classification performance.•Achieved a higher classification accuracy of 100.00% with the SVM linear.

论文关键词：Computer-aided decision support system (CADSS),Local energy-based shape histogram (LESH),Support vector machine (SVM),Local energy model,Receiver operating characteristic (ROC) curve

论文评审过程：Available online 1 May 2015, Version of Record 31 May 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.04.057