EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From RGB-D to RGB-Only: Reliability and Clinical Relevance of Markerless Skeletal Tracking for Postural Assessment in Parkinson’s Disease

Claudia Ferraris iD, Gianluca Amprimo iD, Gabriella Olmo iD, Marco Ghislieri iD, Martina Patera, Antonio Suppa iD, Silvia Gallo iD, Gabriele Imbalzano iD, Leonardo Lopiano, Carlo Alberto Artusi iD

Sensors · 10.02.2026 · 26 (4) · 1146

DOI: 10.3390/s26041146 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.02.2026. Verfasst von Claudia Ferraris und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), Consiglio Nazionale delle Ricerche (CNR), 10129 Turin, Italy. Hauptthemen laut MEDLINE: Parkinson Disease, Posture, Postural Balance. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PRIN 2022 PNRR Program - Next Generation EU.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Axial postural abnormalities in Parkinson’s Disease (PD) are traditionally assessed using clinical rating scales, although picture-based assessment is considered the gold standard. This study evaluates the reliability and clinical relevance of two markerless body-tracking frameworks, the RGB-D-based Microsoft Azure Kinect (providing the reference KIN_3D model) and the RGB-only Google MediaPipe Pose (MP), using a synchronous dual-camera setup. Forty PD patients performed a 60 s static standing task. We compared KIN_3D with three MP models (at different complexity levels) across horizontal, vertical, sagittal, and 3D joint angles. Results show that lower-complexity MP models achieved high congruence with KIN_3D for trunk and shoulder alignment (ρ > 0.75), while the lateral view significantly improved tracking of sagittal angles (ρ ≥ 0.72). Conversely, the high-complexity model introduced significant skeletal distortions. Clinically, several angular parameters emerged as robust metrics for postural assessment and global motor impairments, while sagittal angles correlated with motor complications. Unexpectedly, a more upright frontal alignment was associated with greater freezing of gait severity, suggesting that static postural metrics may serve as proxies for dynamic gait performance. In addition, both RGB-only and RGB-D frameworks effectively discriminated between postural severity clusters. While the higher-complexity MP model should be avoided due to inaccurate 3D reconstructions, our findings demonstrate that low- and medium-complexity MP models represent a reliable alternative to RGB-D sensors for objective postural assessment in PD, facilitating the widespread application of objective posture measurements in clinical contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseasePosturePostural BalanceHumansMaleFemaleAgedMiddle AgedGaitMotion CaptureReproducibility of ResultsBiomechanical Phenomena

Stichwörter der Autor:innen

Google MediaPipeMicrosoft Azure KinectParkinson’s Diseaseangular measurementsaxial symptomsclinical validationdigital biomarkersmarkerless human pose estimationpostural assessmenttechnical validation

Autor:innen und Institutionen

  • Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), Consiglio Nazionale delle Ricerche (CNR), 10129 Turin, Italy.
  • Department of Control and Computer Engineering, Politecnico di Torino, 10129 Turin, Italy.
  • Department of Electronics and Telecommunications and PolitoBIOMed Lab, Politecnico di Torino, 10129 Turin, Italy.
  • Department of Human Neurosciences, Sapienza University of Rome, 00185 Rome, Italy.
  • IRCCS Neuromed, 86077 Pozzilli, Italy.
  • Department of Neurosciences "Rita Levi Montalcini", University of Turin, 10126 Turin, Italy.

ORCID-Profile: Claudia Ferraris, Gianluca Amprimo, Gabriella Olmo, Marco Ghislieri, Antonio Suppa, Silvia Gallo, Gabriele Imbalzano, Carlo Alberto Artusi

Förderung

  • PRIN 2022 PNRR Program - Next Generation EU

Zitieren

APA

Ferraris, C., Amprimo, G., Olmo, G., Ghislieri, M., Patera, M., Suppa, A., Gallo, S., Imbalzano, G., Lopiano, L., & Artusi, C. A. (2026). From RGB-D to RGB-Only: Reliability and Clinical Relevance of Markerless Skeletal Tracking for Postural Assessment in Parkinson’s Disease. Sensors, 26(4), 1146. https://doi.org/10.3390/s26041146

Vancouver

Ferraris C, Amprimo G, Olmo G, Ghislieri M, Patera M, Suppa A, et al. From RGB-D to RGB-Only: Reliability and Clinical Relevance of Markerless Skeletal Tracking for Postural Assessment in Parkinson’s Disease. Sensors. 2026;26(4):1146. doi:10.3390/s26041146

BibTeX
@article{Ferraris2026,
  author = {Ferraris, Claudia and Amprimo, Gianluca and Olmo, Gabriella and Ghislieri, Marco and Patera, Martina and Suppa, Antonio and Gallo, Silvia and Imbalzano, Gabriele and Lopiano, Leonardo and Artusi, Carlo Alberto},
  title = {From RGB-D to RGB-Only: Reliability and Clinical Relevance of Markerless Skeletal Tracking for Postural Assessment in Parkinson’s Disease},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {4},
  pages = {1146},
  doi = {10.3390/s26041146}
}
Kostenlos starten →