Detecting Fifth Metatarsal Fractures on Radiographs through the Lens of Smartphones: A FIXUS AI Algorithm
Taseh, A.; Shah, A.; Eftekhari, M.; Flaherty, A.; Ebrahimi, A.; Jones, S.; Nukala, V.; Nazarian, A.; Waryasz, G.; Ashkani-Esfahani, S.
Show abstract
BackgroundFifth 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 accessibility of diagnostic tools. MethodsA retrospective study included patients aged >18 with 5MT fractures (n=1240) and controls (n=1224). Radiographs (AP, oblique, lateral) from Electronic Health Records (EHR) were obtained and photographed using a smartphone, creating a new dataset (SP). Models using ResNet 152V2 were trained on EHR, SP, and combined datasets, then evaluated on a separate smartphone test dataset (SP-test). ResultsOn validation, the SP model achieved optimal performance (AUROC: 0.99). On the SP-test dataset, the EHR models performance decreased (AUROC: 0.83), whereas SP and combined models maintained high performance (AUROC: 0.99). ConclusionsSmartphone-specific deep learning models effectively detect 5MT fractures, suggesting their practical utility in resource-limited settings.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The Effects of Pericapsular nerve group (PENG) block on Postoperative Recovery in Elderly Patients with Hip fracture: a study protocol for randomized, parallel controlled, double-blind trial 93%
- Comparative Computed Tomography with Stress Manoeuvres for Diagnosing Distal Isolated Tibiofibular Syndesmotic Injury in Acute Ankle Sprain: a Protocol for an Accuracy-Test Prospective Study. 93%
- Validity of intraoperative imageless navigation (Naviswiss™) for component positioning accuracy in primary total hip arthroplasty: Protocol for a prospective observational cohort study in a single-surgeon practice 93%
Similar papers in this journal
- MyoVision-US: an Artificial Intelligence-Powered Software for Automated Analysis of Skeletal Muscle Ultrasonography 93%
- Modified FRAX Score for Prediction of Fall-induced Hip Fractures; The Added Value of Fall Energy, Number, and Social Vulnerability Index 93%
- Development and Validation of Collaborative Robot-assisted Cutting Method for Iliac Crest Flap Raising: Randomized Crossover Trial 93%
Similar papers in this journal
- Comparison of Operative Time and Blood Loss with the FFX(R) Device Versus Pedicle Screw Fixation During Surgery for Lumbar Spinal Stenosis: A Retrospective Cohort Study 92%
- Effects of contrast-medium and vertebral measurement level on computed tomography-based body composition parameters of skeletal muscle and adipose tissue 91%
- “This is a quiz” Premise Input: A Key to Unlocking Higher Diagnostic Accuracy in Large Language Models 90%
Similar papers in this journal
- Investigating the relationship between internal spinal alignment and back shape in patients with scoliosis using PCdare: a comparative, reliability and validation study 95%
- Investigation of locomotive syndrome improvement by total hip arthroplasty in patients with hip osteoarthritis: a before-after comparative study focusing on 25-question geriatric locomotive function scale 94%
- Action observation intervention using three - dimensional movies improves the usability of hands with distal radius fractures in daily life: a nonrandomized controlled trial in women 93%
Similar papers in this journal
- Standardizing Phenotypic Algorithms for the Classification of Degenerative Rotator Cuff Tear from Electronic Health Record Systems 93%
- Development and Application of Pharmacological Statin-Associated Muscle Symptoms Phenotyping Algorithms Using Structured and Unstructured Electronic Health Records Data 91%
- Evaluation of a Machine Learning Approach Utilizing Wearable Data for Prediction of SARS-CoV-2 Infection in Healthcare Workers 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.