LMS Based Adaptive Algorithm for Breast Cancer Detection using Mammogram Images

According to the annual report published by American Cancer Society ( ACS ) in 2018, about 0.3 million women are diagnosed with the deadly disease of breast cancer, among them, 40,000 were died due to breast cancer. For early detection of breast cancer, mammography screening is the most widely used method. It can improve survival rates. The sensitivity of mammogram depends upon the quality of the X-ray image. During acquisition and screening process the image is corrupted by noise, which can lead to the wrong diagnosis or minor tumors may not be marked by the radiologist. Moreover, due to low contrast nature of mammogram images, detection of specific diagnostic signs like masses and microcalcifications is a challenging problem. To cop up with this type of errors and discrepancies, computer-aided diagnosis ( CAD ) tools along with mammogram images is the only way forward. The advancement in the field of information and computing technology coupled with efficient image processing algorithms explores new ways for early detection of the breast tumor and image enhancement. In this paper, we have evaluated the performance of state of the art adaptive algorithm i.e. LSM combined with the connected components technique for the enhancement and segmentation of mammogram and detection of masses or lesions respectively. Additionally, we considered feature vector based on gray features i.e. gray value, window mean and standard deviation, which describes the extraction area i.e. region of interest ( ROI ). Results are evaluated in terms of sensitivity, specificity and accuracy. Proposed system exhibited encouraging results of 80% accuracy in the detection of clustered masses and tumors. The mammogram images used in our research are taken from Digital Database for Screening Mammograms ( DDSM ).

[1]  Wolfgang Arthur Schulz.  Molecular Biology of Human Cancers: An Advanced Student's Textbook , 2005 .

[2]  C. K. Chua,et al.  Computer-Aided Breast Cancer Detection Using Mammograms: A Review , 2013, IEEE Reviews in Biomedical Engineering.

[3]  Constantine A Gatsonis,et al.  American College of Radiology Imaging Network digital mammographic imaging screening trial: objectives and methodology. , 2005, Radiology.

[4]  Robert B. Jaffe.  Performance of Screening Mammography Among Women With and Without a First-Degree Relative With Breast Cancer , 2001 .

[5]  R. Bird,et al.  Analysis of cancers missed at screening mammography. , 1992, Radiology.

[6]  Berkman Sahiner,et al.  Computer-aided detection of breast masses on full field digital mammograms. , 2005, Medical physics.

[7]  Rangaraj M. Rangayyan,et al.  A review of computer-aided diagnosis of breast cancer: Toward the detection of subtle signs , 2007, J. Frankl. Inst..

[8]  Mehmet Fatih Akay,et al.  Support vector machines combined with feature selection for breast cancer diagnosis , 2009, Expert Syst. Appl..

[10]  M. Giger,et al.  Breast cancer: effectiveness of computer-aided diagnosis observer study with independent database of mammograms. , 2002, Radiology.

[11]  Alan C. Bovik,et al.  Computer-Aided Detection and Diagnosis in Mammography , 2005 .

[12]  Rachel F Brem,et al.  Improvement in sensitivity of screening mammography with computer-aided detection: a multiinstitutional trial. , 2003, AJR. American journal of roentgenology.

[13]  Mariam M. Biltawi,et al.  MAMMOGRAM ENHANCEMENT AND SEGMENTATION METHODS : CLASSIFICATION , ANALYSIS , AND EVALUATION , 2012 .

[14]  Volodymyr Ponomaryov,et al.  Computer-aided detection system based on PCA/SVM for diagnosis of breast cancer lesions , 2015, 2015 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON).

[15]  Yongyi Yang,et al.  Computer-Aided Detection and Diagnosis of Breast Cancer With Mammography: Recent Advances , 2009, IEEE Transactions on Information Technology in Biomedicine.