Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle
PLOS ONE · 30.08.2023 · 18 (8) · e0289808
DOI: 10.1371/journal.pone.0289808 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 30.08.2023. Verfasst von Martin Magnéli und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Sciences at Danderyd Hospital, Karolinska Institutet, Stockholm, Sweden. Hauptthemen laut MEDLINE: Deep Learning, Shoulder Fractures, Thoracic Injuries. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In this study, we present a deep learning model for fracture classification on shoulder radiographs using a convolutional neural network (CNN). The primary aim was to evaluate the classification performance of the CNN for proximal humeral fractures (PHF) based on the AO/OTA classification system. Secondary objectives included evaluating the model’s performance for diaphyseal humerus, clavicle, and scapula fractures. The training dataset consisted of 6,172 examinations, including 2–7 radiographs per examination. The overall area under the curve (AUC) for fracture classification was 0.89, indicating good performance. For PHF classification, 12 out of 16 classes achieved an AUC of 0.90 or greater. Additionally, the CNN model had excellent overall AUC for diaphyseal humerus fractures (0.97), clavicle fractures (0.96), and good AUC for scapula fractures (0.87). Despite the limitations of the study, such as the reliance on ground truth labels provided by students with limited radiographic assessment experience, our findings are in concordance with previous studies, further consolidating CNN as potent fracture classifiers in plain radiographs. The inclusion of multiple radiographs with different views from each examination, as well as the generally unselected nature of the sample, contributed to the overall generalizability of the study. This is the fifth study published by our group on AI in orthopaedic radiographs, which has consistently shown promising results. The next challenge for the orthopaedic research community will be to transfer these results from the research setting into clinical practice. External validation of the CNN model should be conducted in the future before it is considered for use in a clinical setting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Clinical Sciences at Danderyd Hospital, Karolinska Institutet, Stockholm, Sweden.
ORCID-Profile: Martin Magnéli, Kristofer Hallberg, Björn Salomonsson, Max Gordon
Zitieren
APA
Magnéli, M., Ling, P., Gislén, J., Fagrell, J., Demir, Y., Arverud, E. D., Hallberg, K., Salomonsson, B., & Gordon, M. (2023). Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle. PLOS ONE, 18(8), e0289808. https://doi.org/10.1371/journal.pone.0289808
Vancouver
Magnéli M, Ling P, Gislén J, Fagrell J, Demir Y, Arverud ED, et al. Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle. PLOS ONE. 2023;18(8):e0289808. doi:10.1371/journal.pone.0289808
BibTeX
@article{Magnli2023,
author = {Magnéli, Martin and Ling, Petter and Gislén, Jacob and Fagrell, Johan and Demir, Yilmaz and Arverud, Erica Domeij and Hallberg, Kristofer and Salomonsson, Björn and Gordon, Max},
title = {Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle},
journal = {PLOS ONE},
year = {2023},
volume = {18},
number = {8},
pages = {e0289808},
doi = {10.1371/journal.pone.0289808}
}
EUVIMED