Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading.

Journal: Artificial intelligence in medicine
Published Date: Apr 19, 2018

Abstract

OBJECTIVE: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components.

Authors

  • Shahnorbanun Sahran
    Recognition Research Group, Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Malaysia.
  • Dheeb Albashish
    Computer Science Department, Prince Abdullah Bin Ghazi Faculty of Information Technology, Al-Balqa Applied University, Jordan. Electronic address: bashish@bau.edu.jo.
  • Azizi Abdullah
    Pattern Recognition Research Group, Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, University Kebangsaan Malaysia, 43600 Bangi, Malaysia. Electronic address: azizia@ukm.edu.my.
  • Nordashima Abd Shukor
    Department of Pathology, University Kebangsaan Malaysia Medical Center, 56000 Batu 9 Cheras, Malaysia. Electronic address: nordashima@ppukm.ukm.edu.my.
  • Suria Hayati Md Pauzi
    Department of Pathology, University Kebangsaan Malaysia Medical Center, 56000 Batu 9 Cheras, Malaysia. Electronic address: su_hayati@ppukm.ukm.edu.my.

Keywords

External Resources

Popular Topics
Recent Journals