Distribution of interscan measurement error in AI-based 3D MRI analysis of knee cartilage thickness in osteoarthritis
PLOS One · 2025
DOI: 10.1371/journal.pone.0329610 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Hisako Katano und 11 weiteren Autor:innen. Beteiligte Einrichtung: Center for Stem Cell and Regenerative Medicine, Institute of Science Tokyo, Tokyo, Japan. Hauptthemen laut MEDLINE: Osteoarthritis, Knee, Magnetic Resonance Imaging, Imaging, Three-Dimensional, Cartilage, Articular. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fujifilm Corporation.
Abstract (Originalsprache)
Purpose
A novel AI-based 3D analysis system was developed to automatically extract bone and cartilage from MRI data and provide average cartilage thickness. This study aimed to analyze the interscan measurement error of knee cartilage thickness in osteoarthritis patients.
Methods
Fifty knee osteoarthritis patients underwent two scans using MRI systems from five different vendors. Each model included five Kellgren-Lawrence grade (KL) 1–2 and five KL3–4 patients. Cartilage thickness was automatically quantified for seven regions, and interscan measurement error was analyzed.
Results
In the KL1–2 group, measurements with errors ≤0.05 mm, ≤ 0.10 mm, and ≤0.20 mm were 42%, 75%, and 97%, respectively. For the KL3–4 group, these proportions were 31%, 59%, and 90%. The entire cohort (KL1–4) showed errors ≤0.05 mm, ≤ 0.10 mm, and ≤0.20 mm in 37%, 67%, and 93% of measurements. Differences between KL1–2 and KL3–4 groups were significant for all thresholds.
Conclusion
Overall, 93% of interscan measurement errors were within 0.20 mm when using fully automatic MRI 3D analysis software to assess knee cartilage thickness in osteoarthritis patients. This study provides valuable insights into the reliability of automated cartilage thickness measurements across different disease severities and MRI systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Center for Stem Cell and Regenerative Medicine, Institute of Science Tokyo, Tokyo, Japan.
- Department of Orthopaedic Surgery, Hirosaki University Graduate School of Medicine, Aomori, Japan.
- Department of Orthopaedic Surgery, Kobe University Graduate School of Medicine, Hyogo, Japan.
- Department of Orthopaedic Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
- Department of Medicine for Orthopedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan.
- School of Data Science, Graduate School of Data Science, Yokohama City University, Kanagawa, Japan.
ORCID-Profile: Kanto Nagai, Naofumi Hashiguchi, Jun Masumoto, Ichiro Sekiya
Förderung
- Fujifilm Corporation
Zitieren
APA
Katano, H., Sasaki, E., Nagai, K., Hashiguchi, N., Kaneko, H., Ishibashi, Y., Kuroda, R., Adachi, N., Ishijima, M., Tomita, M., Masumoto, J., & Sekiya, I. (2025). Distribution of interscan measurement error in AI-based 3D MRI analysis of knee cartilage thickness in osteoarthritis. PLOS One. https://doi.org/10.1371/journal.pone.0329610
Vancouver
Katano H, Sasaki E, Nagai K, Hashiguchi N, Kaneko H, Ishibashi Y, et al. Distribution of interscan measurement error in AI-based 3D MRI analysis of knee cartilage thickness in osteoarthritis. PLOS One. 2025. doi:10.1371/journal.pone.0329610
BibTeX
@article{Katano2025,
author = {Katano, Hisako and Sasaki, Eiji and Nagai, Kanto and Hashiguchi, Naofumi and Kaneko, Haruka and Ishibashi, Yasuyuki and Kuroda, Ryosuke and Adachi, Nobuo and Ishijima, Muneaki and Tomita, Makoto and Masumoto, Jun and Sekiya, Ichiro},
title = {Distribution of interscan measurement error in AI-based 3D MRI analysis of knee cartilage thickness in osteoarthritis},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0329610}
}
EUVIMED