A Modified CNN And Fuzzy AHP Based Breast Cancer Stage Detection System

Every year a significant number of women dies because of suffering from breast cancer all over the world. The rate of mortality due to breast cancer can be decreased if the cancer and the stage is early detected. Early Diagnosis is not possible in every corner of all countries over the world because of the lack of experienced consultant or doctor. A novel approach is presented in this study based on convolutional neural network and fuzzy analytical hierarchy process for diagnosis of breast cancer along with stage identification. The proposed model detects breast cancer from mammographic images using modified convolutional neural network. Then identifies the stage using fuzzy analytical hierarchy process model which is comprised of 3 layers (goal, criteria and alternative). Proposed modified convolutional neural network model achieves 98.75% validation accuracy on detecting breast cancer from mammograms as well as the fuzzy AHP model efficiently identifies the stage of the cancer.