Development of a joint space width measurement method based on radiographic hand images

  • Authors:
  • Samjin Choi;Gi-Ja Lee;Seung-Jae Hong;Ki-Ho Park;Tur Urtnasan;Hun-Kuk Park

  • Affiliations:
  • Department of Biomedical Engineering & Healthcare Industry Research Institute, College of Medicine, Kyung Hee University, 1 Hoegi-dong, Dongdaemun-gu, Seoul 130-701, Republic of Korea;Department of Biomedical Engineering & Healthcare Industry Research Institute, College of Medicine, Kyung Hee University, 1 Hoegi-dong, Dongdaemun-gu, Seoul 130-701, Republic of Korea;Division of Rheumatology, Department of Internal Medicine, College of Medicine, Kyung Hee University Medical Center, Seoul 130-702, Republic of Korea;Department of Orthodontics, College of Dental Medicine, Kyung Hee University Medical Center, Seoul 130-701, Republic of Korea;Department of Orthodontics, College of Dental Medicine, Kyung Hee University Medical Center, Seoul 130-701, Republic of Korea;Department of Biomedical Engineering & Healthcare Industry Research Institute, College of Medicine, Kyung Hee University, 1 Hoegi-dong, Dongdaemun-gu, Seoul 130-701, Republic of Korea and Program ...

  • Venue:
  • Computers in Biology and Medicine
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This study presents a novel algorithm to measure joint space widths (JSWs) in patients with rheumatoid arthritis (RA) using radiographic hand images. Radiographic images were first preprocessed, and then phalangeal regions corresponding to the bone structures of each finger were extracted using step-wedge functions. Phalangeal branch paths were also extracted. Each of the five extracted phalangeal branch paths matched the bone structures of each finger exactly and ran through the center of each finger. The algorithm automatically detected 14 joints, which were identified as sharp changes in gray scale intensity along phalangeal branch paths through the profile plot. The regions of interest corresponding to the 14 joints were subsequently extracted. A total of 35 radiographic images from three groups were tested. The performance of our algorithm was evaluated by measuring joint location percentage errors and mean JSWs for three joints in the phalanges. The algorithm correctly detected 94.69% of total joints and had a low detection rate in RA patients with severe deformities or ankylosis. The mean JSW in the control group was significantly greater than that in the RA group (p