Segond Fractures Can Be Identified With Excellent Accuracy Utilizing Deep Learning on Anteroposterior Knee Radiographs

Abstract

PurposeTo 1) develop a deep learning model for detection of Segond fractures on AP knee radiographs and 2) to compare model performance to that of trained human experts. MethodsAP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent ACL reconstruction by one of 23 surgeons included in the registry data. Images were categorized into one of two classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopedic surgery sports medicine fellow and a fellowship-trained orthopedic sports medicine surgeon with over 10 years of experience. ResultsA total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set. ConclusionA deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared to expert human observers. Clinical RelevanceDeep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large-scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.