Detection of Breast Cancer Using Artificial Neural Networks

Abstract

The disease is curable if detected early stage. Screening is carried out on the basis of mammogram; this is used in x-ray image to reveal lumps in the breast. Calcium deposit can also indicate the existence of a tumor in breast. Mammography is proven as efficient tool to detect breast cancer before clinical symptoms appears digital mammography is currently considered as standard procedure for breast cancer diagnosis, various artificial intelligence techniques are used for classification problems in the area of medical diagnosis. Several type of feature extraction is from digital mammograms including position feature, shape feature and texture features etc. Feature extraction of image is important in mammogram classification. These features are extracted by using image processing. Texture features have proven to be useful in differentiating normal and abnormal cells. Extracted texture features provide information about textural characteristics of the image. MLE (Maximum Likelihood Estimation) and wavelet transforms is used to calculate the area and also showing the affected area. This helps to determine the depth of tumor. Here „0‟ is showing as black and „1‟ is showing as white. Pre-processing method used as a small neighborhood of a pixel in an input image to get a new brightness value in output image, also called as Filtration. Breast cancer is a type of cancer originating from breast tissues, and most commonly this is originated from the inner lining of milk ducts. Breast cancer occurs in human and other mammals also.