Improving detection of cancerous and non-cancerous breast tissues by principal component analysis and random forest

Cancer has become a significant health concern in today's world, arising from the uncontrolled and abnormal growth of atypical cells in the body. Cancer encompasses many types, and in this study, we focus on the diagnosis of breast cancer. Breast cancer is one of the most common and life-threatening diseases affecting women's health, where early detection can significantly reduce mortality rates. Machine learning algorithms can be utilized for breast cancer diagnosis. This research explores improving the accuracy and efficiency of breast cancer diagnostic systems through data analysis methods and machine learning algorithms. The primary goal of this study is to enhance diagnostic precision and performance by employing advanced techniques for data analysis and more accurate classification of cancerous and non-cancerous tissues. The findings indicate that the methods applied can contribute to improved diagnostic accuracy and facilitate the decision-making process in breast cancer diagnosis.

Keywords:

Breast cancer , cancerous tissues , non-cancerous tissues , principal component analysis (PCA) , random forest