Classification of colorectal cancer based on the association of multidimensional and multiresolution features
作者：
Highlights：
• A new method that associates multidimensional and multiresolution approaches.
• We expanded the use of curvelet transform, haralick features and fractal techniques.
• The method was applied to investigate H&E images from distinct datasets.
• The method provides relevant rates, even with high levels of noise on the feature set.
• We indicated the best features and their relationship with histological information.
摘要
•A new method that associates multidimensional and multiresolution approaches.•We expanded the use of curvelet transform, haralick features and fractal techniques.•The method was applied to investigate H&E images from distinct datasets.•The method provides relevant rates, even with high levels of noise on the feature set.•We indicated the best features and their relationship with histological information.
论文关键词：Colorectal cancer,Feature associations,Multiresolution features,Fractal techniques,Curvelet transforms,Haralick descriptors
论文评审过程：Received 26 March 2018, Revised 23 October 2018, Accepted 26 November 2018, Available online 26 November 2018, Version of Record 3 December 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.11.034
