GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection


  • Aya Alsalihi Al-Nahrain Univarsity
  • Hadeel K. Aljobouri b Biomedical Engineering Department, College of Engineering, Al-Nahrain University, Baghdad, Iraq
  • Enam Azez Khalel ALTameemi 3Radiology Department, Oncology Teaching Hospital, Baghdad Medical City, Baghdad, Iraq



ANOVA, Breast Cancer MRI, CNN, Feature Extraction, GLCM


Breast cancer is one of the most common types of cancer among Iraqi women. MRI has been used in the detection of breast tumors for its efficient performance in the diagnosis process providing high accuracy. In this paper, breast MRI image data from 89 patients were classified using GLCM and CNN feature extraction methods. Four models were evaluated consisting of GLCM, CNN, combined GLCM and CNN features based models. The statistical ANOVA feature selection method was used to reduce the redundant features. The reduced feature subset was fed to CNN classifier for obtaining either normal or abnormal breast images. The proposed method was assessed in terms of accuracy, precision, recall and F1-score. The model provided 100% classification accuracy.




How to Cite

Alsalihi, A., K. Aljobouri, H. ., & ALTameemi, E. A. K. (2022). GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection. International Journal of Online and Biomedical Engineering (iJOE), 18(12), pp. 123–137.