LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING
Ali, S., Sherif, H., Hassan, S., El Marakby, A. (2024). LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING. EKB Journal Management System, 19(72), 121-133. doi: 10.21608/auej.2024.259630.1577
Soaad Nasser Eldin Ali; Hala Maghraby Sherif; Sabry Mohammed Hassan; Ashraf Abd El Rahman El Marakby. "LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING". EKB Journal Management System, 19, 72, 2024, 121-133. doi: 10.21608/auej.2024.259630.1577
Ali, S., Sherif, H., Hassan, S., El Marakby, A. (2024). 'LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING', EKB Journal Management System, 19(72), pp. 121-133. doi: 10.21608/auej.2024.259630.1577
Ali, S., Sherif, H., Hassan, S., El Marakby, A. LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING. EKB Journal Management System, 2024; 19(72): 121-133. doi: 10.21608/auej.2024.259630.1577

LONG BONES X-RAY FRACTURE CLASSIFICATION USING MACHINE LEARNING

Journal of Al-Azhar University Engineering Sector
Volume 19, Issue 72, July 2024, Page 121-133  XML PDF (1.2 MB)
Document Type: Original Article
DOI: 10.21608/auej.2024.259630.1577
View on SCiNiTO View on SCiNiTO
Authors
Soaad Nasser Eldin Ali email 1; Hala Maghraby Sherif2; Sabry Mohammed Hassan3; Ashraf Abd El Rahman El Marakbyorcid 1
1Systems and Computers Engineering Dept. , Faculty of Engineering , Al-Azhar University, Cairo, Egypt.
2Radiology Department, Faculty of Medicine , Al-Azhar University
3Modern Academy of Engineering and Technology
Abstract
Accurate long bone fracture diagnosis is essential to prevent permanent deformities resulting from misdiagnosis. This study uses machine learning to introduce a multi-class classification and detection system for long bone fractures. In this study, two image classifications are applied Binary classification and Multi-class classification, and an image detection model. Binary classification to distinguish normal and fractured bone X-ray images. Three models are used for this classification, Model A and Model B are used for grayscale images, and a ResNet50 pertained model for RGB images. Multi-class classification to identify fracture type using ResNet50 fine-tuned model And a Faster RCNN detection model to classify and detect the fracture type and its location in the X-ray images. The dataset was collected from various resources and labeled and annotated following Müller AO classification for bone fracture types. Binary classification achieved a 90.2% accuracy rate for Model A, 90.85% for Model B, and  96.5% for ResNet50, While the multi-class classification model achieved 87.7% accuracy in identifying fracture types for ResNet50 and 80% for Faster RCNN in fracture detection.
 
Special Issue of AEIC 2024 (Electrical and System & Computer Engineering  Session)
Keywords
Image Classification; Image Detection; CNN; ResNet50; Faster RCNN
Statistics
Article View: 279
PDF Download: 290