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

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 ins...

Full description

Saved in:
Bibliographic Details
Main Authors: Joshua Kubach, Tobias Pogarell, Michael Uder, Mario Perl, Marcel Betsch, Mario Pasurka, Stefan Söllner, Rafael Heiss
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-14604-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849237807866839040
author Joshua Kubach
Tobias Pogarell
Michael Uder
Mario Perl
Marcel Betsch
Mario Pasurka
Stefan Söllner
Rafael Heiss
author_facet Joshua Kubach
Tobias Pogarell
Michael Uder
Mario Perl
Marcel Betsch
Mario Pasurka
Stefan Söllner
Rafael Heiss
author_sort Joshua Kubach
collection DOAJ
description 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.
format Article
id doaj-art-e1d034d24533485b89fe7f4e46bbd7cc
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e1d034d24533485b89fe7f4e46bbd7cc2025-08-20T04:01:51ZengNature PortfolioScientific Reports2045-23222025-08-0115111110.1038/s41598-025-14604-wDevelopment of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validationJoshua Kubach0Tobias Pogarell1Michael Uder2Mario Perl3Marcel Betsch4Mario Pasurka5Stefan Söllner6Rafael Heiss7Department of Traumatology and Orthopedics, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergInstitute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergInstitute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergDepartment of Traumatology and Orthopedics, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergDepartment of Traumatology and Orthopedics, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergDepartment of Traumatology and Orthopedics, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergDepartment of Traumatology and Orthopedics, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergInstitute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-NürnbergAbstract 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.https://doi.org/10.1038/s41598-025-14604-w
spellingShingle Joshua Kubach
Tobias Pogarell
Michael Uder
Mario Perl
Marcel Betsch
Mario Pasurka
Stefan Söllner
Rafael Heiss
Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
Scientific Reports
title Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
title_full Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
title_fullStr Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
title_full_unstemmed Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
title_short Development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
title_sort development of a deep learning algorithm for radiographic detection of syndesmotic instability in ankle fractures with intraoperative validation
url https://doi.org/10.1038/s41598-025-14604-w
work_keys_str_mv AT joshuakubach developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT tobiaspogarell developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT michaeluder developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT marioperl developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT marcelbetsch developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT mariopasurka developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT stefansollner developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation
AT rafaelheiss developmentofadeeplearningalgorithmforradiographicdetectionofsyndesmoticinstabilityinanklefractureswithintraoperativevalidation