Binary inception V3 deep learning based image classifier for the detection of breast cancer

Cases of breast cancer are on the rise. In accordance with the American Cancer Society, 297, 790 women and 2, 800 men in the United States will be diagnosed with invasive breast cancer in 2023. However, mortality in breast cancer can be reduced through early detection. This can be accomplished by developing a dependable algorithm capable of detecting breast cancer in near-real time. As in the previous studies it is evident that the Inception V3 deep learning model performs well for the image classification tasks therefore this study implements Inception V3 model to detect breast cancer. In this research, the classifier was trained on 1200 images that were split into two categories; these were patients without breast cancer and patients having breast cancer. To determine the effectiveness of this algorithm, it was compared with VGG 16 model. The VGG 16 model is an additional deep learning model that has been demonstrated to be effective for image classification tasks. On the purpose of breast cancer detection, the Inception V3 model outperformed the VGG 16 model, achieving an accuracy of 99% compared to 53% for the VGG 16 model. The algorithm gained this accuracy after 23 epochs, which was recommended number according to (records), as opposed to the standard learning rate of 0.001. The Inception V3 model is a promising approach for the early diagnosis of breast cancer, based on these results. To validate the classifier on a larger dataset and evaluate its clinical utility, additional research is recommended.