Study of Mammogram Microcalcification to aid tumour detection using Naive Bayes Classifier

At present most of the women were having symptoms of breast cancer it can be detected by presence of microclacifications in mammogram. Classifier makes vital role in early detection and diagnosis of microclacifications in mammogram. Most of the classifier at present which is not more efficient to diagnosis the breast cancer. In this paper leads to analysis an efficient method by diagnosing the mammogram using Naive bayes classifier. The proposed method has a) ROI extraction (Chain code) b) Pre-processing (Enhancement), c) Feature extraction (HOG) and d) Classification using Naive bayes classifier. Naive bayes classifier is used to detect microcalcification at each location in the mammogram. It classifies the Mammogram images as Benign or Malignant. The test of the proposed system yield 96.5% microcalcification detection in mammograms. Experimental results show that the proposed method using Mammogram Image Analysis Society (MIAS) Database clinical mammogram. For years cancer has been one of the biggest threats in human life, deaths caused by cancer are expected to increase in the future with an estimated 12 million people dying from cancer in 2030. Of all known cancers, breast cancer is a major concern among women. Treatment of breast cancer at an early stage can significantly improve the survival rate of patients. Mammography is currently the most sensitive method for detecting early breast cancer.Retrospective studies have shown that radiologists can miss the detection of a significant proportion of abnormalities in addition to having high rates of false positives. The estimated sensitivity of radiologists in breast cancer screening is only about 75%. In order to improve the accuracy of interpretation, a variety of Computer- Assisted Detection (CAD) techniques have been proposed. In real sense, the Malignancy (15) or Benign, its type and from it detection of stage of cancer as invasive and non- invasive is a very fuzzy kind of decision making. Benign tumours are "well-differentiated," that the tumour cells differ only slightly in appearance and behaviour from their tissue of origin. Malignant or malignancy is used to describe a cancer that generally grows rapidly and is capable of spreading throughout the body. However, for the purpose of diagnostic analysis, classifications are suggested. Detection of breast cancer is conducted by means of methods of mammography and ultra sono graphy (USG) imaging. The most frequent type of breast cancer, detected before the invasion stage, is ducal carcinoma in situ (DCIS). In this type of cancer, the most frequent markers are clusters of microcalcification. Microcalcifications clusters are one of the important radiographic indications related to breast cancer because they are present in 30%-50% of all cancers found mammographically. Imaging techniques play an important role in digital mammogram, especially of abnormal areas that naive bayes classifier be felt but can be seen on a conventional mammogram. Before any image-processing algorithm of mammogram pre-processing steps are very important in order to limit the search for abnormalities without undue influence from background of the mammogram. These steps are needed only on digitized screen film mammography (SFM) images because digital mammography devices perform this step automatically during the image storing process. The segmentation process is easier on images obtained directly from the digital mammography devices. Microcalcifications (MCCs) are tiny bits of calcium that may show up in clusters or in patterns (like circles) and are associated with extra cell activity in breast tissue. Scattered micro-calcifications are usually a sign of benign breast