• DocumentCode
    1931536
  • Title

    Masses Characterization Based on Angular Margin Measurement

  • Author

    Jumaat, Abdul K. ; Rahman, Wan E. ; Ibrahim, Arsmah ; Yasiran, Siti S. ; Mahmud, Rozi ; Malek, Aminah A.

  • Author_Institution
    Faulty of Comput. & Math. Sci., Univ. Teknol. MARA, Shah Alam, Malaysia
  • fYear
    2012
  • fDate
    25-27 Sept. 2012
  • Firstpage
    265
  • Lastpage
    269
  • Abstract
    This paper presents the application of Active Contour or Snake for the segmentation of masses on breast ultrasound images and the characterization of the segmented masses as malignant or benign. Initially, the Balloon Snake is chosen to segment the masses. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by radiologist. Experimental result shows that from fifty masses tested, the Balloon Snake successfully segment the masses with accuracy of 95.71%. Then, a segmented mass by the Balloon Snake is characterized as benign or malignant based on the measurement of angular margin. The mass is considered as a malignant if it has at least one acute angular margin. Otherwise it is a benign. The characterization of a mass by the Balloon Snake based on the criterion of angular margin is compared with the actual type of a mass characterized by an expert radiologist. The comparison is made in terms of sensitivity and specificity values. Based on the values, the receiver operating characteristics (ROC) curve is plotted. It is found that the area under curve is 0.8455. The value implies that the Balloon Snake gives high accuracy in characterizing benign from malignant mass based on the criterion used.
  • Keywords
    biomedical ultrasonics; image segmentation; mass measurement; medical image processing; ultrasonic imaging; active contour; angular margin measurement; balloon snake; breast ultrasound images; masses characterization; masses segmentation; radiologist; receiver operating characteristics curve; specificity values; Accuracy; Active contours; Breast; Cancer; Image segmentation; Ultrasonic imaging; Vectors; Active Contour; Characterization; Masses; Segmentation; Snake;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence, Modelling and Simulation (CIMSiM), 2012 Fourth International Conference on
  • Conference_Location
    Kuantan
  • ISSN
    2166-8531
  • Print_ISBN
    978-1-4673-3113-5
  • Type

    conf

  • DOI
    10.1109/CIMSim.2012.50
  • Filename
    6338087