International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
BONE FRACTURE DETECTION USING DEEP LEARNING D. Pravin Kumar1, Ayyanar K2, Gokul M S3 1Associate Professor, Dept. of Computer Science Engineering, K.L.N college of Engineering, Sivagangai, Tamil Nadu,
India
2&3Student, Dept. of Computer Science Engineering, K.L.N college of Engineering, Sivagangai, Tamil Nadu, India
---------------------------------------------------------------------***--------------------------------------------------------------------classifying bone fractures from X-ray images. By utilizing a Abstract - Bone fracture detection plays a crucial role in the
pre-trained YOLOv8 model fine-tuned on a custom dataset, the system aims to enhance diagnostic precision, reduce human error, and enable real-time detection and visualization of fractures. The project incorporates CLAHE preprocessing to improve image contrast and highlight fine fracture details, ensuring reliable detection even in lowquality X-rays. A Tkinter-based graphical user interface (GUI) allows users to upload X-rays, view detection results, and access basic treatment recommendations easily.
medical field, where early and accurate identification can greatly assist doctors in providing proper treatment. Manual examination of X-ray images is often time-consuming and prone to human error. Traditional edge detection methods like Canny, Sobel, and Prewitt work well on high-quality X-rays but fail on noisy or low-contrast images. This paper proposes an automated fracture detection system using the YOLOv8 deep learning model, trained on a custom Xray dataset. CLAHE (Contrast Limited Adaptive Histogram Equalization) preprocessing is applied to enhance image contrast and clarity before detection. The proposed system can identify both the type of fracture (e.g., transverse, oblique, compound) and the affected bone (e.g., femur, tibia, humerus). A user-friendly GUI built with Tkinter allows users to upload Xray images, view detection results, and obtain general treatment recommendations. The proposed model demonstrates improved accuracy and efficiency compared to conventional image processing techniques.
The scope of the project extends to detecting various fracture types such as transverse, oblique, and compound, as well as identifying affected bone regions like the femur, tibia, and humerus. The system serves as a supportive diagnostic tool for radiologists, orthopedic doctors, and medical students, improving efficiency and accuracy in fracture assessment. Beyond detection, it provides an integrated and user-friendly platform that bridges the gap between artificial intelligence and healthcare diagnostics. In the future, the system can be enhanced to analyze CT or MRI scans, integrate cloud-based medical data storage, and support real-time hospital information systems, making it a scalable and advanced medical diagnostic solution.
Key Words: Bone Fracture Detection, Deep Learning, YOLOv8, CLAHE, X-ray Image.
1.INTRODUCTION
2.MODULES
Bone fractures are common injuries that require accurate and rapid diagnosis. Traditionally, radiologists visually inspect X-ray images to detect fractures, which can be subjective and slow. Image quality variations such as noise or low contrast further complicate diagnosis.
2.1 Image Acquisition and Preprocessing The first stage of the system involves acquiring the X-ray image and preparing it for further analysis. The user uploads an X-ray image of the fractured bone through a graphical user interface developed using Tkinter. Once the image is uploaded, it is converted into a standard grayscale format to simplify processing. Since X-ray images often suffer from low contrast and noise, a preprocessing step is applied using CLAHE (Contrast Limited Adaptive Histogram Equalization). This technique enhances the image contrast by redistributing the brightness values, thereby improving the visibility of bone edges and fracture lines. The enhanced image is then resized and normalized according to the input requirements of the YOLOv8 model. This preprocessing step ensures that the model receives high-quality and consistent input data, resulting in more accurate fracture detection.
Recent advancements in artificial intelligence (AI) and deep learning have enabled the development of automated medical image analysis systems. Among various models, the YOLO (You Only Look Once) architecture is known for its real-time object detection capabilities. This paper introduces a YOLOv8-based deep learning approach for bone fracture detection, enhanced with CLAHE preprocessing for better contrast and visibility. The system also provides a user interface for uploading images and viewing detection results along with possible treatment recommendations.
1.2.OBJECTIVE AND SCOPE OF THE PROJECT The main objective of the Bone Fracture Detection System using Deep Learning (YOLOv8) is to develop an intelligent, automated solution capable of accurately identifying and
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 396