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{172608,
        author = {Tulluri Durga Devi and Sola Namrata and Yengalreddy Srilaxmi and Magi Kusuma},
        title = {AI Based Bone Anomaly Detection Using Radiographic Data},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {276-279},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172608},
        abstract = {This paper explores the use of ensemble learning techniques to detect bone anomalies from radiographic images in the MURA dataset, which contains 40,000 images of seven anatomical regions: wrist, fingers, humerus, hand, shoulder, forearm, and elbow. The study evaluates the accuracy and efficiency of an ensemble model combining AlexNet and ResNet architectures, trained on an 80:20 split of the dataset. Unlike existing approaches that utilize individual CNN models such as AlexNet, ResNet, or DenseNet with accuracies ranging from 85-90%, the proposed ensemble method achieved a superior accuracy of 95%. The model predicts whether a radiographic image contains an anomaly, demonstrating enhanced precision and robustness compared to standalone models. These results highlight the potential of ensemble learning for improving early detection and clinical decision-making, making it a promising tool for bone anomaly diagnostics in healthcare applications.},
        keywords = {Bone anomaly detection, ensemble learning, AlexNet, ResNet, MURA dataset, radiographic images, deep learning, healthcare AI, diagnostic accuracy.},
        month = {January},
        }