An Automatic Detection Method for Carotid Artery Calcifications Using Top-Hat Filter on Dental Panoramic Radiographs

Access this Article

Author(s)

    • SAWAGASHIRA Tsuyoshi
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University
    • HAYASHI Tatsuro
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University
    • HARA Takeshi
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University
    • MURAMATSU Chisako
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University
    • ZHOU Xiangrong
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University
    • IIDA Yukihiro
    • Department of Oral Radiology, Asahi University School of Dentistry
    • FUJITA Hiroshi
    • Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University

Abstract

The purpose of this study is to develop an automated scheme of carotid artery calcification (CAC) detection on dental panoramic radiographs (DPRs). The CAC is one of the indices for predicting the risk of arteriosclerosis. First, regions of interest (ROIs) that include carotid arteries are determined on the basis of inflection points of the mandibular contour. Initial CAC candidates are detected by using a grayscale top-hat filter and a simple grayscale thresholding technique. Finally, a rule-based approach and a support vector machine to reduce the number of false positive (FP) findings are applied using features such as area, location, and circularity. A hundred DPRs were used to evaluate the proposed scheme. The sensitivity for the detection of CACs was 90% with 4.3FPs (80% with 1.9FPs) per image. Experiments show that our computer-aided detection scheme may be useful to detect CACs.

Journal

  • IEICE Transactions on Information and Systems

    IEICE Transactions on Information and Systems E96.D(8), 1878-1881, 2013

    The Institute of Electronics, Information and Communication Engineers

Cited by:  1

Codes

  • NII Article ID (NAID)
    130003370972
  • Text Lang
    ENG
  • Article Type
    Journal Article
  • ISSN
    0916-8532
  • Data Source
    CJPref  J-STAGE 
Page Top