| Abstrakt: |
This study investigates a bone fracture classification system using deep learning algorithms to determine the best-performing architecture. The primary focus was on training the YOLOv8 model, renowned for its real-time object detection and image segmentation capabilities, as well as the VGG16 model. CNN architectures, known for their effectiveness in image recognition tasks, were chosen for their proven effectiveness in detecting bone fractures from X-ray images. Hyperparameter tuning was used to improve the system's ability to accurately detect and classify bone fractures. The FracAtlas dataset was utilized, which contains 4,083 X-ray images of fractured and non-fractured human bones. Integrating advanced deep learning techniques aims to assist surgeons with more accurate diagnostics. The performance of the developed system was evaluated against existing methods, showcasing its effectiveness in medical diagnostics and fracture treatment. The methodology employed, including data augmentation, extensive model training, and hyperparameter tuning, significantly improved the accuracy of bone fracture detection and classification, demonstrating the potential of deep learning models in aiding medical professionals with more precise and efficient diagnostics. [ABSTRACT FROM AUTHOR] |
