Computer-aided diagnosis system for Rheumatoid Arthritis using machine learning

There are 700,000 Rheumatoid Arthritis (RA) patients in Japan, and the number of patients is increased by 30,000 annually. The early detection and appropriate treatment according to the progression of RA are effective to improve the patient's prognosis. The modified Total Sharp (mTS) score is widely used for the progression evaluation of Rheumatoid Arthritis. The mTS score assessments on hand or foot X-ray image is required several times a year, and it takes very long time. The automatic mTS score calculation system is required. This paper proposes the finger joint detection method and the mTS score estimation method using support vector machine. Experimental results on 45 RA patient's 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 50.9, 64.3 %, respectively.

Paper

Full text

PDF

Computer-aided diagnosis system for Rheumatoid Arthritis using machine learning

Semantic Scholar · Computer Science · 2017

Abstract

There are 700,000 Rheumatoid Arthritis (RA) patients in Japan, and the number of patients is increased by 30,000 annually. The early detection and appropriate treatment according to the progression of RA are effective to improve the patient's prognosis. The modified Total Sharp (mTS) score is widely used for the progression evaluation of Rheumatoid Arthritis. The mTS score assessments on hand or foot X-ray image is required several times a year, and it takes very long time. The automatic mTS score calculation system is required. This paper proposes the finger joint detection method and the mTS score estimation method using support vector machine. Experimental results on 45 RA patient's 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 50.9, 64.3 %, respectively.

Similar papers

© 2026 NYSGPT2525 LLC