Classification of non-Hodgkin lymphomas based on sample entropy signatures

作者：

Highlights：

• An experimental analysis dedicated to improving techniques for CAD systems on NHL.

• Association of SampEn signatures and different classifiers for evaluating H&E images.

• Analyses with multiple segmentation techniques and color normalization models.

• Enhancement of the quantitative ability of sample entropy with signature metrics.

• Accurate results even after applying different types of noise.

摘要

•An experimental analysis dedicated to improving techniques for CAD systems on NHL.•Association of SampEn signatures and different classifiers for evaluating H&E images.•Analyses with multiple segmentation techniques and color normalization models.•Enhancement of the quantitative ability of sample entropy with signature metrics.•Accurate results even after applying different types of noise.

论文关键词：SampEn signatures,Signature metrics,Non-Hodgkin’s lymphomas,Segmentation,Color normalization

论文评审过程：Received 18 January 2021, Revised 6 April 2022, Accepted 10 April 2022, Available online 19 April 2022, Version of Record 28 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117238