article · Diagnostics
Cervical spine fractures and dislocations are severe medical emergencies that can lead to permanent paralysis or death if not diagnosed promptly. A computer-aided diagnosis system utilising refined deep learning models, specifically AlexNet and GoogleNet, has been developed to classify cervical spine injuries directly from X-ray imagery into fractures or dislocations. Evaluated on a dataset of 2,009 X-ray scans comprising normal cases, dislocations, and fractures, the system achieved 99.56 percent accuracy, alongside high sensitivity, specificity, and precision exceeding 99 percent. Additionally, saliency maps were incorporated to highlight the spatial regions within the X-rays that support specific diagnostic classifications. Designed to aid clinicians during urgent triage, the underlying software is intended for integration directly onto medical imaging hardware to assist in immediate clinical decision-making during emergencies.
Cervical spine injuries require immediate detection to prevent catastrophic outcomes such as permanent disability or fatal complications. By accurately automating the classification of fractures and dislocations on X-ray scans, this system provides emergency physicians with rapid decision support, helping to reduce diagnostic delays and errors when treating critically injured patients.
The technology is presented as an applied and tested diagnostic software tool for emergency clinicians and radiologists. It offers potential integration into hospital radiography hardware and Picture Archiving and Communication Systems to deliver automated triage at the point of capture. However, translation from tested code into hospital deployment will require prospective clinical validation, regulatory approval for medical software, and commercial partnerships with medical device manufacturers.
AI-generated from the published abstract. Always read the original work before citing.
Cervical spine (CS) fractures or dislocations are medical emergencies that may lead to more serious consequences, such as significant functional disability, permanent paralysis, or even death. Therefore, diagnosing CS injuries should be conducted urgently without any delay. This paper proposes an accurate computer-aided-diagnosis system based on deep learning (AlexNet and GoogleNet) for classifying CS injuries as fractures or dislocations. The proposed system aims to support physicians in diagnosing CS injuries, especially in emergency services. We trained the model on a dataset containing 2009 X-ray images (530 CS dislocation, 772 CS fractures, and 707 normal images). The results show 99.56%, 99.33%, 99.67%, and 99.33% for accuracy, sensitivity, specificity, and precision, respectively. Finally, the saliency map has been used to measure the spatial support of a specific class inside an image. This work targets both research and clinical purposes. The designed software could be installed on the imaging devices where the CS images are captured. Then, the captured CS image is used as an input image where the designed code makes a clinical decision in emergencies.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/diagnostics13071273
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
