Detecting Fifth Metatarsal Fractures on Radiographs Through the Lens of Smartphones: The FIXUS AI Algorithm

Introduction Fifth metatarsal (5MT) fractures are common but challenging to diagnose, particularly with limited expertise or subtle fractures. Deep learning shows promise, but faces limitations due to image quality requirements. This study develops a deep learning model to detect 5MT fractures from smartphone-captured radiograph images, enhancing the accessibility of diagnostic tools. Methods A retrospective study included patients aged ≥18 with 5MT fractures (n = 1,240) and controls (n = 1,224). Radiographs (anteroposterior, oblique, and lateral) from Electronic Health Records (EHRs) were obtained and photographed using a smartphone (SP), creating a new dataset. Models using ResNet-152V2 were trained on EHR, SP, and combined datasets, then evaluated on a separate SP test dataset. Results On validation, the SP model achieved optimal performance (area under the receiver operating characteristic curve, or AUROC: 0.99). On the SP test dataset, the EHR model's performance decreased (AUROC: 0.83), whereas the SP and combined models maintained high performance (AUROC: 0.99). Conclusion SP-specific deep learning models effectively detect 5MT fractures, suggesting their practical utility in resource-limited (RL) settings.