Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images

The purpose of this research is to determine whether or not a deep learning model called VGG16 can automatically identify bone fractures in X-ray pictures. The dataset, sourced from Kaggle, includes 10,522 images of human hand and foot bones, which underwent preprocessing steps such as normalization...

Full description

Saved in:
Bibliographic Details
Main Authors: Resky Adhyaksa, Bedy Purnama
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2025-02-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/6101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030748830007296
author Resky Adhyaksa
Bedy Purnama
author_facet Resky Adhyaksa
Bedy Purnama
author_sort Resky Adhyaksa
collection DOAJ
description The purpose of this research is to determine whether or not a deep learning model called VGG16 can automatically identify bone fractures in X-ray pictures. The dataset, sourced from Kaggle, includes 10,522 images of human hand and foot bones, which underwent preprocessing steps such as normalization and resizing to 224x224 pixels to enhance data quality. The study utilizes the VGG16 architecture, pre-trained on ImageNet, as a base model, with transfer learning applied to adapt the model for fracture detection by fine-tuning its weights. This architecture consists of five blocks of convolutional and max-pooling layers to effectively extract and enhance information from the images for precise classification. The training and testing phases utilized an 80:20 split of the data, employing binary cross-entropy as the loss function and the Adam optimizer for efficient weight updates. The model achieved high performance, with an accuracy of 99.25%, precision of 98.62%, recall of 98.88%, and an F1-score of 99.16% over 25 epochs with a batch size of 128. Experimental results indicate that smaller batch sizes generally enhance accuracy and reduce loss values, with batch sizes of 128 and 16 yielding optimal performance. The study's findings underscore the potential of VGG16 in improving diagnostic accuracy and reliability in medical imaging, providing a robust tool for fracture detection. Future research should continue exploring hyperparameter optimization to further enhance model performance while balancing computational efficiency.
format Article
id doaj-art-ae84be11e42745bf990a0135f21ab47a
institution DOAJ
issn 2580-0760
language English
publishDate 2025-02-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-ae84be11e42745bf990a0135f21ab47a2025-08-20T02:59:08ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602025-02-019111812910.29207/resti.v9i1.61016101Application of VGG16 in Automated Detection of Bone Fractures in X-Ray ImagesResky Adhyaksa0Bedy Purnama1Telkom UniversityTelkom UniversityThe purpose of this research is to determine whether or not a deep learning model called VGG16 can automatically identify bone fractures in X-ray pictures. The dataset, sourced from Kaggle, includes 10,522 images of human hand and foot bones, which underwent preprocessing steps such as normalization and resizing to 224x224 pixels to enhance data quality. The study utilizes the VGG16 architecture, pre-trained on ImageNet, as a base model, with transfer learning applied to adapt the model for fracture detection by fine-tuning its weights. This architecture consists of five blocks of convolutional and max-pooling layers to effectively extract and enhance information from the images for precise classification. The training and testing phases utilized an 80:20 split of the data, employing binary cross-entropy as the loss function and the Adam optimizer for efficient weight updates. The model achieved high performance, with an accuracy of 99.25%, precision of 98.62%, recall of 98.88%, and an F1-score of 99.16% over 25 epochs with a batch size of 128. Experimental results indicate that smaller batch sizes generally enhance accuracy and reduce loss values, with batch sizes of 128 and 16 yielding optimal performance. The study's findings underscore the potential of VGG16 in improving diagnostic accuracy and reliability in medical imaging, providing a robust tool for fracture detection. Future research should continue exploring hyperparameter optimization to further enhance model performance while balancing computational efficiency.https://jurnal.iaii.or.id/index.php/RESTI/article/view/6101deep learningbone fracturex-ray imagesconvolutional neural networkvgg16
spellingShingle Resky Adhyaksa
Bedy Purnama
Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
deep learning
bone fracture
x-ray images
convolutional neural network
vgg16
title Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
title_full Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
title_fullStr Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
title_full_unstemmed Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
title_short Application of VGG16 in Automated Detection of Bone Fractures in X-Ray Images
title_sort application of vgg16 in automated detection of bone fractures in x ray images
topic deep learning
bone fracture
x-ray images
convolutional neural network
vgg16
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/6101
work_keys_str_mv AT reskyadhyaksa applicationofvgg16inautomateddetectionofbonefracturesinxrayimages
AT bedypurnama applicationofvgg16inautomateddetectionofbonefracturesinxrayimages