Automated Breast Profile Segmentation for ROI Detection Using Digital Mammograms Jawad Nagi *,1 , Sameem Abdul Kareem 1 , Farrukh Nagi 2 , Syed Khaleel Ahmed 2 1 Faculty of Computer Science and Information Technology, University of Malaya 50603 Kuala Lumpur, Malaysia. 1 jawad@perdana.um.edu.my; 1 sameem@um.edu.my 2 College of Engineering, Universiti Tenaga Nasional Jalan IKRAM-UNITEN, 43000 Kajang, Selangor, Malaysia. 2 farrukh@uniten.edu.my; 2 syedkhaleel@uniten.edu.my Abstract—Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer. Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography. Extraction of the breast profile region and the pectoral muscle is an essential pre-processing step in the process of computer-aided detection. Primarily it allows the search for abnormalities to be limited to the region of the breast tissue without undue influence from the background of the mammogram. The presence of pectoral muscle in mammograms biases detection procedures, which recommends removing the pectoral muscle during mammogram pre-processing. In this paper we explore an automated technique for mammogram segmentation. The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) algorithm in order to: (1) remove digitization noises, (2) suppress radiopaque artifacts, (3) separate background region from the breast profile region, and (4) remove the pectoral muscle, for accentuating the breast profile region. To demonstrate the capability of our proposed approach, digital mammograms from two separate sources are tested using Ground Truth (GT) images for evaluation of performance characteristics. Experimental results obtained indicate that the breast regions extracted accurately correspond to the respective GT images. Keywords—Breast cancer, Mammogram segmentation, Seeded region growing, Pectoral muscle, Region of interest. I. INTRODUCTION reast cancer is a type of cancer with highest incidence rates in women. It is the most common cause of cancer death in women in many countries [1]. Recent statistics show that breast cancer affects one of every ten women in Europe and one of every eight in the United States [2]. It has been shown that early detection and treatment of breast cancer are the most effective methods of reducing mortality [3]. Mammography is the most widely used method to screen asymptomatic women for early detection of breast cancer. The large number of mammograms generated by screening of population must be diagnosed by relatively few radiologists [4]. 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% [5]. Double reading has been suggested to be an effective approach to improve the sensitivity. In order to improve the accuracy of interpretation, a variety of Computer- Assisted Detection (CAD) techniques have been proposed [6]. Interpretation of mammograms mainly involves two major processes: Computer-Aided Detection (CADe) and Computer- Aided Diagnosis (CADi) [7], [8]. It would be valuable to develop a CAD algorithm using extracted features from the breast profile region; region of interest (ROI). This would reduce the number of unnecessary biopsies in patients with benign disease and thus avoid patients’ physical and mental suffering, with a bonus of reducing healthcare costs [9]. Before CAD algorithms can be applied for the task of classification and identification, mammograms need to be pre- processed. Preprocessing steps include: (a) noise removal, (b) radiopaque artifact suppression, (c) pectoral muscle removal, which are mainly related to the problem of mammogram image processing and segmentation. In this paper we propose an automated technique for mammogram segmentation. The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) to remove digitization noises, suppress radiopaque artifacts and remove the pectoral muscle to accentuate the breast profile region for use in CAD algorithms. II. LITERATURE SURVEY Mammogram segmentation usually involves classifying mammograms into several distinct regions, including the breast border [10], the nipple [11] and the pectoral muscle. The edge of the pectoral muscle is useful in determining mammogram adequacy [12], mammogram-pair registration and comparison [13] and for restricting the searching space for calcification and lesion detection [14]. The pectoral muscle represents a predominant density region in most mediolateral oblique views of mammograms, which affects the results of image processing [15]. Thus, it is recommended that the pectoral muscle should be removed during mammogram segmentation [8]. B 2010 IEEE EMBS Conference on Biomedical Engineering & Sciences (IECBES 2010), Kuala Lumpur, Malaysia, 30th November - 2nd December 2010. 978-1-4244-7600-8/10/$26.00 ©2010 IEEE 87