Copyright © 2026 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{194463,
        author = {Rajam Akshaya Sri and Bontha Akshaya and Merugu Sanjana and K. Srilatha},
        title = {Detection and Classification of Custom Bone Fracture Types Using YOLOv8},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4417-4422},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194463},
        abstract = {Automated systems for bone fracture detection through radiographic image analysis constitute vital development work in computer-aided diagnostic systems. X-ray image evaluation through manual methods requires substantial time investment because different observers display inconsistent results when they try to find hard-to-detect fractures. The research develops a deep learning system which employs YOLOv8 object detection technology to find and categorize various bone fracture types. The system performs fracture area detection and identification through its single-stage detection mechanism. The training process uses a specially curated and annotated X-ray dataset which includes preprocessing methods and augmentation techniques to enhance system performance. The proposed method achieves high mean Average Precision while maintaining real time inference speed. The system demonstrates improved fracture detection capabilities across multiple fracture types while producing fewer false positive results for actual fractures.},
        keywords = {Bone Fracture Detection, YOLOv8, Deep Learning, Medical Image Analysis, Object Detection, Computer- Aided Diagnosis},
        month = {March},
        }