Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180743,
        author = {Manali Mahesh Sali and Sagar Vasantrao Joshi and Sanika Bhalerao and Nikita Mahendra Asawale},
        title = {Deep Learning Approaches to Cervical Spine Fracture Detection: A Comparative Study of Mobile-Net, Res-Net, and ConvNeXt-Tiny},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2400-2408},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180743},
        abstract = {Cervical spine fractures represent significant 
injuries that necessitate timely and precise diagnosis to 
avert 
serious 
neurological impairments. Recent 
progress in deep learning technologies has enabled the 
creation of automated systems designed for the analysis 
of medical images. This study conducted a comparative 
analysis of three prominent convolutional neural 
network architectures—Mobile-net, Res-net, and 
ConvNeXt—in detecting cervical spine fractures from 
computed tomography (CT) images. Our findings reveal 
that Res-Net and Mobile-net attained an accuracy of 
97.94% and 97.50%, respectively, while ConvNeXt 
achieved an accuracy of 84%. These results underscore 
the superior performance of Res-Net and Mobile-net in 
this specific diagnostic task.},
        keywords = {Cervical Spine Fracture Detection, Deep  Learning, Convolutional Neural Networks, Medical  Imaging, Model Comparison, Automated Diagnosis,  Performance Evaluation},
        month = {June},
        }