<![CDATA[Bone fracture is one of the most common injury conditions and requires a fast and accurate diagnosis process to assist optimal medical treatment. Examination using X-Ray images is the main method in identifying bone fractures, but the process of interpreting radiographic images has challenges, especially in Multi-class classification with similar fracture characteristics. This study aims to implement a transfer learning method based on the VGG16 architecture for Multi-class classification of bone fractures using X-Ray images. The dataset used consists of 11 classes, namely Avulsion Fracture, Comminuted Fracture, Fracture Dislocation, Greenstick Fracture, Hairline Fracture, Impacted Fracture, Longitudinal Fracture, Oblique Fracture, Pathological Fracture, Spiral Fracture, and Normal. The preprocessing stage includes resizing the image to 256 × 256 pixels, RGB conversion, VGG16 preprocessing, and data augmentation to increase the variety of the dataset. The model was built using pretrained VGG16 as a feature extractor with the addition of GlobalAveragePooling2D, Dense layer, BatchNormalization, and Dropout and fine-tuning was performed on several final layers. The evaluation results showed that the model obtained an accuracy of 98.40%, a macro precision of 97.95%, and a macro recall of 97.95%. In addition, most classes obtained accuracy values close to 100%. The results showed that the application of VGG16-based transfer learning was able to provide excellent classification performance on X-Ray images of bone fractures and was effective in improving the model's generalization ability in multi-class classification of medical images.]]>
