Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation

Kubach J, Pogarell T, Uder M, Perl M, Betsch M, Pasurka M, Söllner S, Heiß R (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Scientific Reports Nature Publishing Group: Open Access Journals - Option B

Book Volume: 15

Article Number: 29880

Journal Issue: 1

DOI: 10.1038/s41598-025-14604-w

Abstract

Identifying syndesmotic instability in ankle fractures using conventional radiographs is still a major challenge. In this study we trained a convolutional neural network (CNN) to classify the fracture utilizing the AO-classification (AO-44 A/B/C) and to simultaneously detect syndesmosis instability in the conventional radiograph by leveraging the intraoperative stress testing as the gold standard. In this retrospective exploratory study we identified 700 patients with rotational ankle fractures at a university hospital from 2019 to 2024, from whom 1588 digital radiographs were extracted to train, validate, and test a CNN. Radiographs were classified based on the therapy-decisive gold standard of the intraoperative hook-test and the preoperatively determined AO-classification from the surgical report. To perform internal validation and quality control, the algorithm results were visualized using Guided Score Class activation maps (GSCAM).The AO44-classification sensitivity over all subclasses was 91%. Furthermore, the syndesmosis instability could be identified with a sensitivity of 0.84 (95% confidence interval (CI) 0.78, 0.92) and specificity 0.8 (95% CI 0.67, 0.9). Consistent visualization results were obtained from the GSCAMs. The integration of an explainable deep-learning algorithm, trained on an intraoperative gold standard showed a 0.84 sensitivity for syndesmotic stability testing. Thus, providing clinically interpretable outputs, suggesting potential for enhanced preoperative decision-making in complex ankle trauma.

Authors with CRIS profile

Joshua Kubach Department of Orthopaedic and Trauma Surgery Tobias Pogarell Institute of Radiology Michael Uder Lehrstuhl für Diagnostische Radiologie Mario Perl Lehrstuhl für Unfallchirurgie und Orthopädie Marcel Betsch Professur für Orthopädie und Orthopädische Chirurgie Mario Pasurka Department of Orthopaedic and Trauma Surgery Stefan Söllner Department of Orthopaedic and Trauma Surgery Rafael Heiß Institute of Radiology

How to cite

APA:

Kubach, J., Pogarell, T., Uder, M., Perl, M., Betsch, M., Pasurka, M.,... Heiß, R. (2025). Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-14604-w

MLA:

Kubach, Joshua, et al. "Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation." Scientific Reports 15.1 (2025).

BibTeX: Download