Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning
Computer Methods and Programs in Biomedicine · 2025
DOI: 10.1016/j.cmpb.2025.108742 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2025. Verfasst von Karolina Nurzynska und 5 weiteren Autor:innen. Beteiligte Einrichtung: Algorithmics and Software Division, Silesian University of Technology, Akademicka 16, Gliwice, 44-100, Poland. Electronic address: Karolina.Nurzynska…. Hauptthemen laut MEDLINE: Machine Learning, Pelvis, Osteoarthritis, Hip, Hip Joint. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND AND OBJECTIVE: Automated analysis of digital radiographs of the pelvis to determine the hip arthrosis state in concordance with the Kellgren-Lawrence scale could facilitate and standardize radiogram descriptions. METHODS: This research evaluates and compares the applicability of the traditional machine-learning approach based on the textural features fed to the classifier and the deep-learning networks of various architectures. RESULTS: The investigation performed for the binary problem, where the healthy and the most severe state of hip arthrosis were considered, proved that the distinction of these classes is possible for both considered approaches. However, the outcomes recorded for deep-learning methods overcome significantly other approaches, resulting in a correct classification ratio equal to 0.98. When all five classes are considered, the results drop, primarily due to the underrepresentation of such cases. CONCLUSIONS: The influence of data pre-processing was investigated, showing that it is insignificant for deep-learning models and that the statistical dominance analysis approach dominates for traditional models. The evaluation also indicates that the deep-learning models must be trained on the selected region of interest. Otherwise, they lack precision and have problems determining the significant changes depicting the arthrosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Algorithmics and Software Division, Silesian University of Technology, Akademicka 16, Gliwice, 44-100, Poland. Electronic address: Karolina.Nurzynska@polsl.pl.
- Department of Measurement and Electronics, AGH University of Krakow, al. Mickiewicza 30, Krakow, 30-059, Poland; Information Systems Institute, HES-SO Valais-Wallis, Rue du Technopole 3, Sierre, 3960, Switzerland.
- Department of Biocybernetics and Biomedical Engineering, AGH University of Krakow, al. Mickiewicza 30, Krakow, 30-059, Poland.
- Institute of Electronics, Lodz University of Technology, ul. Żeromskiego 116, Lodz, 90-924, Poland.
- Department of Diagnostic Imaging, Jagiellonian University Medical College, ul. Kopernika 19, Krakow, 31-501, Poland.
- Clinic of Locomotor Disorders, Andrzej Frycz Modrzewski Krakow University, ul. Gustawa Herlinga-Grudzińskiego 1, Krakow, 30-705, Poland; Małopolska Orthopedic and Rehabilitation Hospital, Modrzewiowa 22, Krakow, 30-224,…
Zitieren
APA
Nurzynska, K., Wodzinski, M., Piórkowski, A., Strzelecki, M., Obuchowicz, R., & Kamiński, P. (2025). Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2025.108742
Vancouver
Nurzynska K, Wodzinski M, Piórkowski A, Strzelecki M, Obuchowicz R, Kamiński P. Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning. Computer Methods and Programs in Biomedicine. 2025. doi:10.1016/j.cmpb.2025.108742
BibTeX
@article{Nurzynska2025,
author = {Nurzynska, Karolina and Wodzinski, Marek and Piórkowski, Adam and Strzelecki, Michał and Obuchowicz, Rafał and Kamiński, Paweł},
title = {Automated determination of hip arthrosis on the Kellgren–Lawrence scale in pelvic digital radiographs scans using machine learning},
journal = {Computer Methods and Programs in Biomedicine},
year = {2025},
doi = {10.1016/j.cmpb.2025.108742}
}
EUVIMED