Breast Cancer Detection Using Neural Networks

Abstract

Breast cancer is the second most common cancer in women worldwide, although it can be diagnosed in men too. Early detection and diagnosis are crucial in improving the survival rate of breast cancer patients. Traditionally, breast cancer is diagnosed using pathological evaluation, historical grading MRI screenings, and various estragon and progesterone receptors statuses. These manual screening tests leave a place for misdiagnosis and therefore delayed treatment. Recently, Artificial Intelligence, especially neural networks has shown great potential in the correct detection and early diagnosis of cancer cells in breast tissue. This research paper uses the Breast Cancer Wisconsin (Diagnostic) Data Set, which contains clinical and diagnostic features of breast cancer patients. This research paper studies various neural network architectures, including feedforward neural networks, convolutional neural networks, and recurrent neural networks to classify breast tumors as benign or malignant. In the result analysis, the convolutional neural network gives the highest accuracy of 98.2% among other models. This research paper highlights the potential of neural network models for breast cancer diagnosis, and the use of deep learning techniques can improve the accuracy of diagnosis.