Aswini Kumar Mohanty, Swapnasikta Beberta, Saroj Kumar Lenka / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 1, Issue 3, pp.687-693 687| Pa ge Classifying Benign and Malignant Mass using GLCM and GLRLM based Texture Features from Mammogram Aswini Kumar Mohanty*, Swapnasikta Beberta**, Saroj Kumar Lenka*** *(Phd. Scholar, SOA University,Bhubaneswar, Orissa, India) **(M.Tech. Scholar,BPUT.Rourkela,Orissa,India) *** (Department Of Computer Science, Modi Univesity, Lakshmangarh-332311 Rajasthan, India) ABSTRACT Mammogram–breast x-ray is considered the most effective, low cost, and reliable method in early detection of breast cancer. Although general rules for the differentiation between benign and malignant breast lesion exist, only 15 to 30% of masses referred for surgical biopsy are actually malignant. In this work, an approach is proposed to develop a computer-aided classification system for cancer detection from digital mammograms. The proposed system consists of three major steps. The first step is region of interest (ROI) extraction of 256×256 pixels size. The second step is the feature extraction; we used a set of 19 GLCM and GLRLM features and the 19 (nineteen) features extracted from grey level run-length matrix and grey- level co-occurrence matrix could distinguishing malignant masses from benign mass with an accuracy 94.9%.Further analysis carried out by involving only 12 of the 19 features extracted, which consists of 5 features extracted from GLCM matrix and 7 features extracted from GLRL matrix. The 12 selected features are: Energy, Inertia, Entropy, Maxprob, Inverse, SRE, LRE, GLN, RLN, LGRE, HGRE, and SRLGE, ARM with 12 features as prediction can distinguish malignant mass image and benign mass with a level of accuracy of 92.3%. Further analysis showing that Area Under the Receiver Operating Curve was 0.995, which means that the accuracy level of classification is good or very good. Based on that data, it concluded that texture analysis based on GLCM and GLRLM could distinguish malignant image and benign image with considerably good result. The third step is the classification process; we used the technique of association rule mining using image content to classify between normal and cancerous mass. The proposed system was shown to have the large potential for cancer detection from digital mammograms Key words:-Gray-level Co-Occurrence Matrix, Gray- level Run Length Matrix, mammograms, benign mass, malignant mass, texture features, textures analysis, association rule mining, Receiver operating characteristics. I. INTRODUCTION Breast Cancer is one of the most common cancers, leading to cause of death among women, especially in developed countries. There is no primary prevention since cause is still not understood. So, early detection of the stage of cancer allows treatment which could lead to high survival rate. Mammography is currently the most effective imaging modality for breast cancer screening. However, 10-30% of breast cancers are missed at mammography [1]. Mining information and knowledge from large database has been recognized by many researchers as a key research topic in database system and machine learning Researches that use data mining approach in image learning can be found in [2- 8]. Data mining of medical images is used to collect effective models, relations, rules, abnormalities and patterns from large volume of data. This procedure can accelerate the diagnosis process and decision-making. Different methods of data mining have been used to detect and classify anomalies in mammogram images such as wavelets [9,10], statistical methods and most of them used feature extracted using image processing techniques [5].Some other methods are based on fuzzy theory [1] and neural networks [11]. In this paper we have used classification method called Association rule classifier for image classification and the process typically involves two phases: training phase and testing phase. In training phase the properties of typical image features are isolated and based on this training class is created .In the subsequent testing phase , these feature space