Breast Cancer Image Classification using Transfer Learning and Convolutional Neural Network
Keywords:
Densenet, Pre-processing, Biopsy, Maxpooling, Random forest, Fully connectedAbstract
Breast cancer is the world's second most frequent cancer among women. In 2012, new cancer cases made up 12% of all new cases, with female malignancies accounting for 25% of all cancer diagnoses. These cells can be detected by an x-ray or a bump on the body. To be cancerous, a tumour must have cells that have invaded or spread to other areas of the body. Develop an algorithm that can determine whether or not a patient has breast cancer based on biopsy photos. To protect human life, the algorithm must be extremely precise. In this study, a database of breast cancer photos is used for analysis, and the categorization is done using a deep learning approach. The deep learning model is applied by implementing a Convolutional Neural Network with transfer learning. The accuracy has achieved more than 96%, which is better than other states of the art algorithms.