Automated mTS Score Estimation of Rheumatoid Arthritis in Hand Radiograph Using SVR

DOI
  • MORITA Kento
    Graduate School of Engineering, University of Hyogo JSPS Research Fellowship for Young Scientists （DC）
  • TASHITA Atsuki
    Graduate School of Engineering, University of Hyogo
  • NII Manabu
    Graduate School of Engineering, University of Hyogo
  • KOBASHI Syoji
    Graduate School of Engineering, University of Hyogo

Bibliographic Information

Other Title
  • SVRを用いた手関節X線画像におけるリウマチmTSスコアの推定

Search this article

Description

<p>There are 700,000 of Rheumatoid Arthritis (RA) patients in Japan, and the number of patients is increased by 30,000 annually. Early treatment is effective to improve patientʼs prognosis. However, the appropriate treatment is required according to the progress of Rheumatoid Arthritis. The modified Total Sharp (mTS) score evaluates the progression of RA on the hand or foot X-ray. The mTS score evaluation is required several times a year for the effective treatment of RA. The mTS score assessment needs very long time. The automatic mTS score calculation system is required. This paper proposes the finger joint detection method and the mTS score calculation method using Support Vector Machine. Experimental results on 90 RA patientʼs X-ray images showed that the proposed method detects finger joints with accuracy of 81.4 (％), and estimated the erosion and JSN score with accuracy of 56.1, 60.4 (％), respectively.</p>

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top