![]() | Only 14 pages are availabe for public view |
Abstract Breast cancer is one of the most serious diseases that affect women, so it must be discovered in the early stages to avoid complications such as redness of the skin, pain in the armpits or breast, and discharge from a nipple, possibly containing blood. Recently, the CAD system that is based on the classification of microscopic image play a vital rule to limit cancer disease and reduce cases. Microscopic image is the currently recommended image system used to detect cancer. A computer-aided diagnosis system will help radiologists to accurately detection of cancerous cells and achieve the best result. This thesis proposes a deep learning model that exploits CAD system features and microscopic images to fight breast cancer. The proposed model builds a classification model based on the DenseNet-161 deep learning method. The proposed model classifies the microscopic images of breast cancer into benign with four types and malignant with four types. Our proposed model is experimentally tested and the result confirmed that a proposed model outperforms baseline models. Our model are used for classification of microscopic images into benign with four types and malignant with four types. This thesis applied our model in histopathological image (BreaKHis dataset) using new training method is called one cycle policy. This model helps to increase the accuracy of classification. This thesis achieves accuracy of 93.98%, 91.85%, 90.32% and 89.65% for the following 40X, 100X, 200X, and 400 X, respectively, as the image level for the raw data and achieve accuracy of 97.7%, 95.70%, 93.73%, 92.92% for the following 40X, 100X, 200X and 400X, respectively, as image level for the augmented data. |