Providing an IoT-based architecture for monitoring breast cancer activities using deep learning

In today's world, breast cancer is one of the leading causes of death and one of the most dreaded diseases known, which is one of the potential causes of death in women. Although it is considered one of the most treatable diseases, it is important that with its timely diagnosis, the death rate can be reduced in the long term. As a solution for the prediction and treatment of this disease, the automatic disease diagnosis system in diagnosis and analysis is a great help to the medical field, which provides a quick response, reliability, effectiveness, and also reduces the risk of death. Therefore, in this article, the long short-term memory (LSTM) algorithm, which is a learning algorithm, was used, because it leads to more stable and more accurate models. The simulation results and comparison with other articles showed that the use of this algorithm has improved the accuracy and sensitivity in breast cancer diagnosis and we were able to determine whether the suspicious area is rough or not with the help of the LSTM algorithm. The evaluations show that the sensitivity of the proposed method is very favorable, especially in dealing with small nodules. The estimated positive error rate for the proposed method is 16.67%, which is less than other works.