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{201583,
        author = {Bansi Bhimraj Thorat and Prof. Pallavi Narkhede and Riya Shivaji Patil and Priti Birappa Vhanzende},
        title = {Automated Bone Fracture Detection For X-Ray Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4707-4713},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201583},
        abstract = {Detection of bone fractures is an important aspect of medical diagnostics; however, the detection process is done manually by analyzing images acquired through X-rays. This task consumes a lot of time and might be challenging in some instances. In this study, a deep learning system for the automatic detection of bone fractures from X-rays is proposed. Transfer learning using DenseNet121 network is incorporated to classify input images as either fractured or non-fractured. Resizing, normalization, converting grayscale image to RGB color space, and applying data augmentation such as rotating, flipping, affine transformation, and adjusting the brightness of the input image is done for improved model performance. In addition to classifying input images, the YOLO model is used to locate the fracture on the image accurately, whereas, Grad-CAM is implemented to explain the prediction made by the model. Experiments show that the proposed model is capable of detecting fractured bones with accuracy around 80% and very high F1-score and ROC-AUC metrics.},
        keywords = {Bone Fracture Detection, X-ray Imaging, Deep Learning, Transfer Learning, DenseNet121, YOLO, Fracture Localization, Grad-CAM, Medical Image Analysis, Data Augmentation.},
        month = {May},
        }