Your browser doesn't support javascript.
loading
Measurement of Shoulder Abduction Angle with Posture Estimation Artificial Intelligence Model.
Kusunose, Masaya; Inui, Atsuyuki; Nishimoto, Hanako; Mifune, Yutaka; Yoshikawa, Tomoya; Shinohara, Issei; Furukawa, Takahiro; Kato, Tatsuo; Tanaka, Shuya; Kuroda, Ryosuke.
Afiliación
  • Kusunose M; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Inui A; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Nishimoto H; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Mifune Y; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Yoshikawa T; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Shinohara I; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Furukawa T; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Kato T; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Tanaka S; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
  • Kuroda R; Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Kobe 650-0017, Japan.
Sensors (Basel) ; 23(14)2023 Jul 16.
Article en En | MEDLINE | ID: mdl-37514738
Substantial advancements in markerless motion capture accuracy exist, but discrepancies persist when measuring joint angles compared to those taken with a goniometer. This study integrates machine learning techniques with markerless motion capture, with an aim to enhance this accuracy. Two artificial intelligence-based libraries-MediaPipe and LightGBM-were employed in executing markerless motion capture and shoulder abduction angle estimation. The motion of ten healthy volunteers was captured using smartphone cameras with right shoulder abduction angles ranging from 10° to 160°. The cameras were set diagonally at 45°, 30°, 15°, 0°, -15°, or -30° relative to the participant situated at a distance of 3 m. To estimate the abduction angle, machine learning models were developed considering the angle data from the goniometer as the ground truth. The model performance was evaluated using the coefficient of determination R2 and mean absolute percentage error, which were 0.988 and 1.539%, respectively, for the trained model. This approach could estimate the shoulder abduction angle, even if the camera was positioned diagonally with respect to the object. Thus, the proposed models can be utilized for the real-time estimation of shoulder motion during rehabilitation or sports motion.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Hombro / Articulación del Hombro Límite: Humans Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Japón Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Hombro / Articulación del Hombro Límite: Humans Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Japón Pais de publicación: Suiza