ABSTRACT
The past few years have seen a growth in the occurrence of breast cancer in women, which has not only resulted in major health issues but has also taken away many lives. According to a survey in 2020, about 2.3 million women were diagnosed with breast cancer and 685,000 deaths were observed globally. The major challenge faced in the diagnosis of breast cancer is that it can occur in women at any age after puerty. It is extremely important to detect breast cancer as early as possible in order to increase the chances of survival for the patient. Efforts have been made in the IoT healthcare environment to diagnose breast cancer sooner and to provide more accuracy. Diagnostic systems based on machine learning have been proposed. In order to improve the performance of the classification system, the recursive feature selection algorithm has been used, which has selected the best features to bring out the best results of the applications of IoT in breast cancer diagnosis. In this chapter, we focus on comparing two different Internet of Things techniques for breast cancer diagnosis and analyzing their pros and cons through a comparative study of the chapters. We briefly go through machine learning and deep learning techniques and find out their pros and cons in the diagnosis of breast cancer. With the help of labeled diagrams and explanations, we try to understand both the techniques and then come to a conclusion regarding the same.
