SavedAdd your journal

Journals / Bilge International Journal of Science and Technology Research / 2023 / Cilt: 7 Sayı: 1

The Effects of the Traditional Data Augmentation Techniques on Long Bone Fracture Detection

Gülnur Begüm CANGÖZ
Selda GÜNEY
Pages
63–69
Publication Date
2023-03-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

For the classification task, the experimental study shows that changing the contrast is the outstanding method for accuracy manner, while the rotation method has the best sensitivity value.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Image collection and preparation phases are highly costly for machine learning algorithms.
📊
Key Findings & Data:They require the majority of labeled data.
💡
Conclusion & Impact:For the classification task, the experimental study shows that changing the contrast is the outstanding method for accuracy manner, while the rotation method has the best sensitivity value.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:biomedical image processing · bone fractures · convolutional neural networks

Abstract

Image collection and preparation phases are highly costly for machine learning algorithms. They require the majority of labeled data. Hence, the image pre-processing method, data augmentation, is commonly used. Since there are so many proposed methods for the augmentation task, this comparison study is presented to be a supporting guide for the researchers. In addition, the lack of studies with animal-based data sets makes this study more valuable. The study is investigated on a comprehensive medical image data set consists of X-ray images of many different dogs. The main goal is to determine the fracture of the long bones in dogs. Many traditional augmentation methods are employed on the data set including flipping, rotating, changing brightness and contrast of the images. Transfer learning is applied on both raw and augmented data sets as a feature extractor and Support Vector Machine (SVM) is utilized as a classifier. For the classification task, the experimental study shows that changing the contrast is the outstanding method for accuracy manner, while the rotation method has the best sensitivity value.

🔖

Cite This Article

CANGÖZ, G. B., GÜNEY, S. (2023). The Effects of the Traditional Data Augmentation Techniques on Long Bone Fracture Detection. Bilge International Journal of Science and Technology Research, Cilt: 7 Sayı: 1, 63–69. https://ajindex.com/articles/902847

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (6)

  1. Arsomngern, P., Numcharoenpinij, N., Piriyataravet, J. Teerapan, W., Hinthong W. and Phunchongharn, P. "Computer-Aided Diagnosis for Lung Lesion in Companion Animals from X-ray Images Using Deep Learning Techniques," 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST), Morioka, Japan, pp. 1-6, 2019.
  2. Baydan, B., Ünver, H. M.: “Dataset creation and SSD mobilenet V2 performance evaluation for dog tibia fracture detection”, II. International Ankara Congress of Scientific Research, Ankara, Turkey, 6-8 March, 2020.
  3. Baydan, B., Ünver, H. M., Barışçı, N.,“Determining the Location of Tibial Fracture of Dog and Cat Using Hybridized Mask R-CNN Architecture”, Kafkas Üniversitesi Veteriner Fakültesi Dergisi, vol. 27, 3, pp. 347 – 353, 2021.
  4. Calimeri, F., Marzullo, A., Stamile, C., Terracina, G. (2017). Biomedical Data Augmentation Using Generative Adversarial Neural Networks. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science, vol 10614. Springer, Cham. https://doi.org/10.1007/978-3-319-68612-7_71.
  5. Christian S., Vincent V., Sergey I., Jonathon S., Zbigniew W., “Rethinking the Inception Architecture for Computer Vision”, Dec. 2015. Deshmukh S. and Khaparde A., "Segmentation Using CNN for BAA using Modified TW3 method," 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), 2021, pp. 1-8, doi: 10.1109/ICECET52533.2021.9698478. Ergün G. B., Güney S., Ergün T.G., Köpeklerdeki Uzun Kemiklerin Evrişimsel Sinir Ağları Kullanılarak Sınıflandırılması, Fırat Üniversitesi Fen Bilimleri Dergisi, vol. 33, pp. 125-132, 2021.
  6. Ergün G. B. and Güney, S. "Classification of Canine Maturity and Bone Fracture Time Based on X-Ray Images of Long Bones," in IEEE Access, vol. 9, pp. 109004-109011, 2021, doi: 10.1109/ACCESS.2021.3101040. Frid-Adar, M., Klang, E., Amitai, M., Goldberger J., and Greenspan, H. "Synthetic data augmentation using GAN for improved liver lesion classification," 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 289-293, doi: 10.1109/ISBI.2018.8363576 Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y., (2014). Generative Adversarial Nets (PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680. Guo K. et al., "Angel-Eye: A Complete Design F