Identifikasi Keberadaan Tumor Pada Citra Mammografi Menggunakan Metode Run Length

Sari

Breast cancer is one of the most cancer disease among women until now. This cancer was formed by abnormal cells in breast tissue. For early breast cancer detection the mammography is used by the radiologyst. In mammography the breast tissue is scanned by Xrays then a resulting  image called mammogram produce. The radiologyst manually examine the mammogram identifying which area of scanned breast tissue that could have cancer suspect. In medical term the cancer appear as a mass or microcalcification. Because of the quality of mammograms and small of cancer area in early stadium the radiologist sometime have the problem to decide if there is a cancer perform as a mass or microcalcification. According to mammograms that can be viewed as texture image, the image processing especially   texture analysis computerizely helped the radiologist to classify the texturize cancer area. In this research one of  the texture analysis methods named run length method use to get the features. With this features, k-NN (k-Nearest Neighbour) classifier then decide whether the suspect area is cancer according to the mass or microcalcification appeareance or just normal tissue. As the result there is 72% correct identification among the mammograms data that have been
analyzed texturizely with run length method.