A Novel Region Growing Based Method to Remove Pectoral Muscle from MLO Mammogram Images
Digital Mammography is the most efficient screening technique for early detection of breast abnormalities. Automated computer aided methods have been very effective in identifying subtle signs of breast cancer like microcalcification and masses. However s
- PDF / 225,588 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 32 Downloads / 187 Views
Abstract Digital Mammography is the most efficient screening technique for early detection of breast abnormalities. Automated computer aided methods have been very effective in identifying subtle signs of breast cancer like microcalcification and masses. However such methods for detection of masses are highly affected by the presence of pectoral muscle in mediolateral oblique view. So it is highly recommended to remove pectoral muscle as a preprocessing step. In this paper, a novel method for pectoral muscle removal from Mediolateral Oblique mammogram images is presented. The method has three main phases. In the first phase a triangular region is defined over the mammogram that separates the pectoral muscle from the rest of the tissue. In the second phase, a local region growing method is applied within the triangular area defined to suppress the pectoral muscle. In the last phase, the pectoral edge is refined using gradient information of the edge. Results and Conclusion: The system is tested over 150 images taken from Mini-MIAS dataset. Hand-drawn segmentation masks are used to compare the segmentation accuracy for the proposed method.
Keywords Mammogram Pectoral muscle oblique (MLO) view Segmentation
Region growing Mediolateral
1 Introduction Cancer is one of the most life-threatening diseases since many decades. Breast cancer among women has emerged as very common type of cancers across the entire world. Unlike most of the cancers, breast cancer is completely curable if M. Hazarika (&) Department of Computer Science, Gauhati University, Guwahati, Assam, India e-mail: [email protected] L.B. Mahanta Center for Computational and Numerical Studies, Institute of Advanced Studies in Science and Technology, Guwahati, Assam, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 A. Kalam et al. (eds.), Advances in Electronics, Communication and Computing, Lecture Notes in Electrical Engineering 443, https://doi.org/10.1007/978-981-10-4765-7_32
307
308
M. Hazarika and L.B. Mahanta
detected in the initial stages. Mammography is found to be one of the most efficient radiographic screening techniques for early diagnosis of breast cancer. But many a times it is difficult for a radiologist to detect the subtle signs of malignancy because of low contrast mammograms leading to unnecessary biopsy. A good computer-aided diagnosis system can help in identification of early symptoms of breast cancer. In developed countries screening mammography has become a routine checkup activity amongst women. In such a scenario, a CAD system will be really helpful to the radiologists to inspect a large number of mammograms. However the performance of any CAD system is highly affected by the quality of the images. Mammogram images often come with low contrast due to the limitations of X-Ray hardware systems making it difficult to interpret the characteristics of mammograms. So enhancing the quality of images is required for most of the images before analyzing further. The presence of pectoral muscle in Me
Data Loading...
