International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Color Layout Filter-Based Feature Extraction with Machine Learning Classifiers for Automated Bone Fracture Detection in X-Ray Images |
|---|---|
| ABSTRACT | X-ray radiography is the most commonly used and readily available tool for the diagnosis of bone fractures in emergency and orthopedic clinical situations. Accurate automated detection of fractures is still one of the greatest challenges from a clinical point of view as fractures have a wide range of morphologies, imaging studies are noisy, and radiologists must interpret large volumes of images. In this work, the Color Layout Filter (CLF) is compared with six machine learning classifiers namely Logistic Regression, Ridge Classifier, Lasso Classifier, Elastic Net Classifier, Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA) in terms of their efficacy as image feature extraction techniques for automated binary bone fracture classification of X-ray images. The bone fracture dataset was taken from Kaggle (https://www.kaggle.com/datasets/abhaysharma01702/bone-fracture-dataset). All X-ray images were processed to extract the features of CLF and then the features were evaluated separately using six classifiers implemented in the machine learning framework Weka 3.8. The accuracy, precision, recall, ROC area, PRC area and training time were used for the performance evaluation. The highest accuracy (86.23%) and highest ROC area (0.94) was obtained by CLF+Linear Discriminant Analysis. CLF+Lasso Classifier and CLF+Elastic Net Classifier had the best performance with their PRC of 0.93 and their training time of 0.32 seconds respectively. The accuracy obtained from all six classifiers was above 83%, proving that the feature descriptor CLF is always discriminative for the classification of bone fracture X-rays. Both CLF+Linear Discriminant Analysis yield the best overall performance and CLF+Lasso yields the best efficiency trade-off for automated bone fracture detection. The CLF-based pipeline is a fast, simple, and clinically usable automated fracture screening framework that is interpretable and complements deep-learning methods. |
| AUTHOR | DR P ANBARASI, DR. P. SASIKALA, DR R RAMPRASAD, C RAJAPRIYA, J RADHIKA Assistant Professor & Head, Department of Computer Science, Sri Muthukumaran Arts and Science College, Chennai, India Professor & Principal, Jaya Women's College (Arts & Science), Chennai, India Assistant Professor & Head, Department of Computer Applications, Sri Muthukumaran Arts and Science College, Chennai, India Assistant Professor, Department of Computer Science, Sri Muthukumaran Arts and Science College, Chennai, India Assistant Professor & Head, Department of Computer Science with AI, Sri Muthukumaran Arts and Science College, Chennai, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405094 |
| pdf/94_Color Layout Filter-Based Feature Extraction with Machine Learning Classifiers for Automated Bone Fracture Detection in X-Ray Images.pdf | |
| KEYWORDS | |
| References | [1] Johari, N., & Singh, N. (2017). Bone fracture detection using edge detection technique. Advances in Intelligent Systems and Computing, 584, 11–19. [2] Tripathi, A., Upadhyay, A., & Rajput, A. (2017). Automatic detection of fracture in femur bones using image processing. In International Conference on Innovations in Information, Embedded and Communication Systems. [3] Vishnu, A., Prakash, D., & Sharmila, S. (2017). Detection and classification of long bone fractures. Journal of Imaging. [4] Umadevi, N., & GeethaJakshmi, D. (2012 — updated 2018). Multiple classification system for fracture detection in human bone X-ray images. IEEE, 1–8. [5] Myint, W. (2018). Analysis on leg bone fracture detection and classification using X-ray images. Machine Learning Research. [6] Ismael, S. H., Kareem, S. W., & Almukhta, F. H. (2020). Medical image classification using different machine learning algorithms. AL-Rafidain Journal of Computer Sciences and Mathematics. [7] Karimunnisa, S., Madupu, R., & Savarapu, P. (2020). Detection of bone fractures automatically with enhanced performance with better combination of filtering and neural networks. [8] Sinthura, S. S., Prathyusha, Y., Harini, K., Pranusha, Y., & Poojitha, B. (2019). Bone fracture detection system using CNN algorithm. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS), pp. 545–549. [9] Tanzi, L., Vezzetti, E., Moreno, R., & Moos, S. (2020). X-ray bone fracture classification using deep learning: A baseline for designing a reliable approach. Applied Sciences. [10] Yadav, D., & Rathor, S. (2020). Bone fracture detection and classification using deep learning approach. In International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control. [11] Abbas, W., Adnan, S., Javid, M., & Majeed, F. (2020). Lower leg bone fracture detection and classification using Faster RCNN for X-rays images. In IEEE 23rd International Multitopic Conference (INMIC). [12] Hrzic, F., Stajduhar, I., Tschauner, S., Sorantin, E., & Lerga, J. (2019). Local-entropy based approach for X-ray image segmentation and fracture detection. Entropy, 21(4), 338. [13] Castro-Gutierrez, E., Estacio-Cerquin, L., Gallegos-Guillen, J., & Obando, J. D. (2019). Detection of acetabulum fractures using X-ray imaging and processing methods focused on noisy images. IEEE, pp. 296–302. [14] Al-Ghaithi, A., & Al Maskari, S. (2021). Artificial intelligence application in bone fracture detection. Journal of Musculoskeletal Surgery and Research, 5(1), 4–9. [15] Kareem, S. W., Hawezia, R. S., & Khoshaba, F. S. (2022). A comparison of automated classification techniques for image processing in video Internet of Things. |
