TY - JOUR
T1 - Deep Learning Algorithms Improve the Detection of Subtle Lisfranc Malalignments on Weightbearing Radiographs
AU - Ashkani-Esfahani, Soheil
AU - Mojahed-Yazdi, Reza
AU - Bhimani, Rohan
AU - Maas, Mario
AU - DiGiovanni, Christopher W.
AU - Lubberts, Bart
AU - Guss, Daniel
AU - Kerkhoffs, Gino M.
N1 - Funding Information: The authors want to thank all Foot and Ankle Research and Innovation Laboratory (FARIL) personnel who helped us in this study. Many thanks to the personnel of the Department of Orthopaedic Surgery at Massachusetts General Hospital for providing us the workplace to perform the study. The author(s) received no financial support for the research, authorship, and/or publication of this article. Publisher Copyright: © The Author(s) 2022.
PY - 2022/8
Y1 - 2022/8
N2 - Background: Detection of Lisfranc malalignment leading to the instability of the joint, particularly in subtle cases, has been a concern for foot and ankle care providers. X-ray radiographs are the mainstay in the diagnosis of these injuries; thus, improving the performance of clinicians in interpreting radiographs can noticeably affect the quality of health care in these patients. Here we assessed the performance of deep learning algorithms on weightbearing radiographs for detection of Lisfranc joint malalignment in patients with Lisfranc instability. Methods: In a retrospective study, 640 patients with Lisfranc malalignment leading to instability were recruited plus 640 individuals with uninjured feet and healthy Lisfranc joint as the control group. All radiographs were screened by orthopaedic surgeons. Two deep learning models were trained, validated, and tested (in a ratio 80:10:10) using a single-view (anteroposterior) and 3-view (anteroposterior, lateral, oblique) radiographs. The performances of the models were reported as sensitivity, specificity, positive and negative predictive values, accuracy, F score, and area under the curve (AUC). Results: No significant differences were observed between the patients and the controls regarding age, gender, race, and body mass index. The best deep learning algorithm outperformed our human interpreters (<1% vs ~10% misdiagnosis), 94.8% sensitivity, 96.9% specificity, 98.6% accuracy, 95.8% F score, and 99.4% AUC. Conclusion: Deep learning methods have shown promising potential in acting as an assistant interpreter of radiographic images in patients with Lisfranc malalignment. Developing these algorithms can hasten and improve the accuracy of diagnosis and reduce further costs and burdens on the patients and health care system. Level of Evidence: Level III, case-control Machine Learning study.
AB - Background: Detection of Lisfranc malalignment leading to the instability of the joint, particularly in subtle cases, has been a concern for foot and ankle care providers. X-ray radiographs are the mainstay in the diagnosis of these injuries; thus, improving the performance of clinicians in interpreting radiographs can noticeably affect the quality of health care in these patients. Here we assessed the performance of deep learning algorithms on weightbearing radiographs for detection of Lisfranc joint malalignment in patients with Lisfranc instability. Methods: In a retrospective study, 640 patients with Lisfranc malalignment leading to instability were recruited plus 640 individuals with uninjured feet and healthy Lisfranc joint as the control group. All radiographs were screened by orthopaedic surgeons. Two deep learning models were trained, validated, and tested (in a ratio 80:10:10) using a single-view (anteroposterior) and 3-view (anteroposterior, lateral, oblique) radiographs. The performances of the models were reported as sensitivity, specificity, positive and negative predictive values, accuracy, F score, and area under the curve (AUC). Results: No significant differences were observed between the patients and the controls regarding age, gender, race, and body mass index. The best deep learning algorithm outperformed our human interpreters (<1% vs ~10% misdiagnosis), 94.8% sensitivity, 96.9% specificity, 98.6% accuracy, 95.8% F score, and 99.4% AUC. Conclusion: Deep learning methods have shown promising potential in acting as an assistant interpreter of radiographic images in patients with Lisfranc malalignment. Developing these algorithms can hasten and improve the accuracy of diagnosis and reduce further costs and burdens on the patients and health care system. Level of Evidence: Level III, case-control Machine Learning study.
KW - Lisfranc joint
KW - Lisfranc malalignment
KW - artificial intelligence
KW - machine learning
KW - x-ray
UR - http://www.scopus.com/inward/record.url?scp=85130974970&partnerID=8YFLogxK
U2 - https://doi.org/10.1177/10711007221093574
DO - https://doi.org/10.1177/10711007221093574
M3 - Article
C2 - 35590472
SN - 1071-1007
VL - 43
SP - 1118
EP - 1126
JO - Foot and Ankle International
JF - Foot and Ankle International
IS - 8
ER -