Oriental Journal of Computer Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Identification of Abnormal Masses in Digital Mammogram Using Statistical Decision Making


Affiliations
1 Dept. of Computer Sc. and Engg, University of Calcutta, Kolkata, India
2 B. P. Poddar Institute of Management and Technology, Kolkata, India
 

The increasing threat of breast cancer in developing countries may not only be handled by the existing medical setup as well as insufficient number of medical workforces. To handle the increasing volume of data produced by diagnostic imaging that can be efficiently managed by computer aided detection/diagnosis (CAD) to assist medical practitioners in image interpretation to detect structural abnormalities like tumour. Mammography has been proven to be the most reliable and cost-effective methodology for early breast tumor detection. In this paper, an abnormality detection methodology has been proposed alongwith preparation and pre-processing steps. The accuracy of CAD to detect abnormalities on medical image analysis depends on a robust segmentation algorithm. Here two types of segmentation mechanism have been implemented i.e. edge-based and region-based. Finally, a proposed statistical decision-making system is used to extract the abnormal region(s) based on intensity distribution. Applying the proposed method on CR and DR mammographic images produces the quantitative measures accuracy, sensitivity and specificity as 96%, 97.6% and 88.6% respectively which is comparable with other contemporary research works.

Keywords

Breast Cancer, Mammography, CAD, Segmentation, Edge-Detection, SRGA, MDT, Statistical Decision Making.
User
Notifications
Font Size

  • Sharma, “Charaka samhita”, Varanasi -Choukhamba Orientalia, 1981.

  • Bhishagratha, “Sushruta samhita”, Varanasi - Choukhamba Orientalia, 1991.

  • Tata Memorial Hospital, website: tmc.gov.in, 2013.

  • Stewart et al, “World Cancer Report”, Lyon, France: IARC Press, 2003.

  • Ferlay et al, “GLOBOCAN 2002: cancer incidence mortality and prevalence worldwide”, IARC Cancer Base, Lyon France: IARC Press, Vol. 2, Issue-5, 2004.

  • International Agency for Research on Cancer Working Group, “the Evaluation of Cancer Preventive Strategies”, Handbooks of Cancer Prevention, Breast Cancer Screening, Lyon France: IARC Press, Vol.7, 2002.

  • Karssemeijer et al, “Detection of stellate distortions in mammograms”, The Institute of Electrical and Electronics Engineers Transactions on Medical Imaging, Vol. 15, pp. 611–619, 1996.

  • Kegelmeyer et al, “Computer-aided mammographic screening for spiculated lesions”, The Journal of Pathology, Vol.191, pp. 331–337, 1994.

  • Comer et al, “Statistical segmentation of mammograms”, Digital Mammography, International Congress Series. Amsterdam, the Netherlands, Elsevier, pp. 471–474, 1996.

  • Li et al, “Markov random field for tumor detection in digital mammography”, The Institute of Electrical and Electronics Engineers Transactions on Medical Imaging, Vol. 14, pp. 565–576, June, 1995.

  • Jiang et al, “Automated Detection of Breast Mass Spiculation Levels and Evaluation of Scheme Performance”, Academic Radiology, Vol. 15, Issue-12, pp. 5341-1544, 2008.

  • Kobatake et al, “Computerized Detection of Malignant Tumors on Digital Mammograms”, IEEE Transactions On Medical Imaging, Vol. 18, Issue-5, pp. 369-378, 1999.

  • Yang et al, “A Computer-Aided System For Mass Detection and Classification In Digitized Mammograms”, Biomedical Engineering applications, Basis & Communications, Vol. 17, Issue-5, pp. 215-229, 2005.

  • Campanini et al, “A novel featureless approach to mass detection in digital mammograms based on Support Vector Machines”, Physics in medicine and Biology, Vol. 49, Issue-6, pp. 961-975, 2004.

  • Rejani et al, “Early Detection Of Breast Cancer Using SVM Classifier Technique”, International Journal on Computer Science and Engineering, Vol. 1, Issue-3, pp.127-130, 2009.

  • Martins et al, “Detection of Masses in Digital Mammograms using K-means and Support Vector Machine”, Electronic Letters on Computer Vision and Image Analysis, Vol. 8, Issue-2, pp. 39-50, 2009.

  • Maitra et al, “Artefact Suppression and Homogenous Orientation of Digital Mammogram using Seeded Region Growing Algorithm”, International Journal of Computer Information Systems, Vol. 3, Issue-4, pp. 32-38, 2011.

  • Maitra et al, “Automated Digital Mammogram Segmentation for Detection of Abnormal Masses using Binary Homogeneity Enhancement Algorithm”, Journal of Computer Science and Engineering (IJCSE), Vol. 2, Issue-3, pp. 416-427, 2011.

  • Maitra et al, “A Tree based Approach towards Edge Detection of Medical Image using MDT”, International Journal of Computer Graphics, SERSC Publication, Vol-6, Issue 01, pp. 37-56, 2015.

  • Maitra et al, “Detection and Isolation of Pectoral Muscle from Digital Mammogram: An Automated Approach”, International Journal of Advance Research in Computer Science, Vol. 2, Issue-3, pp. 375-380, 2011.

  • Maitra et al, “Accurate Breast Contour Detection Algorithms in Digital Mammogram”, International Journal of Computer Applications, Vol. 25, Issue-5, pp. 1-13, 2011.

  • Rangayyan, “Biomedical Image Analysis”, Chemical Rubber Company Press limited liability company, 2005.

  • Maitra et al, “Anatomical Segmentation of Digital Mammogram to Differentiate Breast Regions”, International Journal of Research and Reviews in Computer Science (IJRRCS), Vol. 2, Issue 6, pp. 1327- 1330, 2011.


Abstract Views: 155

PDF Views: 0




  • Identification of Abnormal Masses in Digital Mammogram Using Statistical Decision Making

Abstract Views: 155  |  PDF Views: 0

Authors

Sangita Bhattacharjee
Dept. of Computer Sc. and Engg, University of Calcutta, Kolkata, India
Indra K. Maitra
B. P. Poddar Institute of Management and Technology, Kolkata, India
Samir K. Bandyopadhyay
Dept. of Computer Sc. and Engg, University of Calcutta, Kolkata, India

Abstract


The increasing threat of breast cancer in developing countries may not only be handled by the existing medical setup as well as insufficient number of medical workforces. To handle the increasing volume of data produced by diagnostic imaging that can be efficiently managed by computer aided detection/diagnosis (CAD) to assist medical practitioners in image interpretation to detect structural abnormalities like tumour. Mammography has been proven to be the most reliable and cost-effective methodology for early breast tumor detection. In this paper, an abnormality detection methodology has been proposed alongwith preparation and pre-processing steps. The accuracy of CAD to detect abnormalities on medical image analysis depends on a robust segmentation algorithm. Here two types of segmentation mechanism have been implemented i.e. edge-based and region-based. Finally, a proposed statistical decision-making system is used to extract the abnormal region(s) based on intensity distribution. Applying the proposed method on CR and DR mammographic images produces the quantitative measures accuracy, sensitivity and specificity as 96%, 97.6% and 88.6% respectively which is comparable with other contemporary research works.

Keywords


Breast Cancer, Mammography, CAD, Segmentation, Edge-Detection, SRGA, MDT, Statistical Decision Making.

References