Mammogram classification using sparse-ROI: A novel representation to arbitrary shaped masses
作者：
Highlights：
• Sparse matrix is used to represent the arbitrary shaped masses, called Sparse-ROI.
• Sparse-ROI eliminates the risk of a common optimum sized window selection.
• Two algorithms were developed to describe Sparse-ROI using GLCM and GLAM.
• A drastic reduction in computational time by 99.93% in GLCM is observed on MIAS.
• 97.2% of classification accuracy is observed.
摘要
•Sparse matrix is used to represent the arbitrary shaped masses, called Sparse-ROI.•Sparse-ROI eliminates the risk of a common optimum sized window selection.•Two algorithms were developed to describe Sparse-ROI using GLCM and GLAM.•A drastic reduction in computational time by 99.93% in GLCM is observed on MIAS.•97.2% of classification accuracy is observed.
论文关键词：Computer aided detection,Computer aided diagnosis,Region of interest, sparse matrix,Classification,GLCM
论文评审过程：Received 14 January 2015, Revised 17 March 2016, Accepted 18 March 2016, Available online 29 March 2016, Version of Record 9 April 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.03.037
