Breast cancer diagnosis based on neural networks

Breast cancer is the most common cancer among women and the earlier breast cancer is diagnosed, the easier it is to treat. The most common way to diagnose breast cancer is mammography. Mammography is a simple x-ray image of the breast and a tool for early detection of cancers and non-palpable breast tumors. However, due to some limitations of this method such as low sensitivity especially in dense breasts, other methods such as ۳D mammography, ultrasound and magnetic resonance imaging are often suggested to obtain more and more accurate information. Recently, computer-aided or intelligent diagnosis systems have been developed to assist radiologists in increasing diagnostic accuracy. In general, a computer system consists of four steps: preprocessing, dividing regions of interest (ROI), extracting and selecting features, and finally classification. Today, the use of image processing methods and techniques and pattern recognition in the automatic diagnosis and determination of breast cancer from mammography images and even digital pathology, which is one of the emerging trends in modern medicine, reduce human errors and increase the speed of diagnosis. In this review article, the work done and its advantages and disadvantages in the field of breast cancer diagnosis with the help of neural networks, especially the convolutional artificial neural network, which has been widely used in the diagnosis of all types of cancers, especially the intelligent diagnosis of breast cancer, is discussed. has been Review of articles shows that hybrid algorithms have been better in improving classification and detection accuracy.

Keywords:

breast cancer , mammography , neural network , tumor