Deep learning methods for automated orthopaedic measurements in radiographs
Knee Surgery, Sports Traumatology, Arthroscopy · 2026-12 · 34 (10) · 3474-3482
DOI: 10.1002/ksa.70429 ↗Kurz gefasst
Editorial in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, online erschienen am 22.05.2026. Verfasst von Atif Abedeen und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USA. Hauptthemen laut MEDLINE: Deep Learning, Radiography. Die Arbeit nennt 28 Literaturangaben.
Abstract (Originalsprache)
Radiography remains central to orthopedic diagnosis and surgical planning, yet many clinically important measurements (angles, offsets, alignment indices, and grading scores) are time‐consuming to obtain and show intra‐ and inter‐observer variability, especially in early or borderline disease. A reader‐friendly overview of deep learning methods for the automation of orthopedic measurements on radiographs is provided in this article. Four common approaches are summarized: segmentation networks through which masks are generated and geometry‐based measurements are derived; key point or heatmap‐based landmark detection models through which automated angle and distance calculation is enabled; two‐step object detection plus classification pipelines in which regions of interest are localized before downstream prediction; and direct regression models through which measurements are output directly from images. Representative applications are highlighted across major regions, including hip dysplasia angles, knee alignment and osteoarthritis assessment, and shoulder measurements such as the critical shoulder angle. Practical limitations and implementation considerations are also discussed, including generalizability across sites, performance drift, bias and fairness, and the need for human oversight and interpretable outputs to support safe deployment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USA.
- Service of Orthopaedics and Traumatology, Department of Surgery, EOC, Lugano, Switzerland.
- Università della Svizzera Italiana, Faculty of Biomedical Sciences, Lugano, Switzerland.
- Department of Pediatric Orthopedic Surgery, Hospital for Special Surgery, New York, New York, USA.
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
- Department of Orthopedic Surgery and Traumatology, Kantonsspital Baselland, Bruderholz, Switzerland.
ORCID-Profile: Atif Abedeen, Bryan Soth
Zitieren
APA
Abedeen, A., Soth, B., Bensa, A., Cao, N., Samuelsson, K., Hirschmann, M. T., Daliliyazdi, A., Smith, R., Chahla, J., & Pareek, A. (2026). Deep learning methods for automated orthopaedic measurements in radiographs. Knee Surgery, Sports Traumatology, Arthroscopy, 34(10), 3474-3482. https://doi.org/10.1002/ksa.70429
Vancouver
Abedeen A, Soth B, Bensa A, Cao N, Samuelsson K, Hirschmann MT, et al. Deep learning methods for automated orthopaedic measurements in radiographs. Knee Surgery, Sports Traumatology, Arthroscopy. 2026;34(10):3474-3482. doi:10.1002/ksa.70429
BibTeX
@article{Abedeen2026,
author = {Abedeen, Atif and Soth, Bryan and Bensa, Alessandro and Cao, Nora and Samuelsson, Kristian and Hirschmann, Michael T and Daliliyazdi, Amir and Smith, Richard and Chahla, Jorge and Pareek, Ayoosh},
title = {Deep learning methods for automated orthopaedic measurements in radiographs},
journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
year = {2026},
volume = {34},
number = {10},
pages = {3474--3482},
doi = {10.1002/ksa.70429}
}
EUVIMED