Abstract:
"A bone fracture is a medical condition that disrupts the continuity of the bone, occurring when the bone is subjected to a force exceeding its tolerance threshold. Failure to identify bone fractures in real time can result in malunion or non-union conditions. To ensure proper treatment and enhance the bone healing process, accurately identifying fracture locations and types is necessary. When interpreting X-ray images, it relies on the expertise and experience of medical professionals in the identification process. Sometimes, radiographic images are of low quality, leading to potential issues. Therefore, it is necessary to have a proper approach to accurately localize and classify fractures in real time.
The research has revealed that the optimal approach needs to address the stated problem and appropriate radiographic image processing techniques and employing object detection algorithms. These algorithms should effectively localize and accurately classify all types of fractures with high precision and in a timely manner. In order to overcome the challenges of misidentifying fractures, a novel model for fracture localization and classification has been developed. The research also incorporates radiographic image enhancement and preprocessing techniques to overcome the limitations posed by low-quality images. A classification model has been created using ResNet50 and DenseNet121. In parallel, a fracture segmentation model has been developed using the U-Net architecture. A fracture detector ensemble model has been created using these classification and localization models.
The classification ensembled model achieved an accuracy of 83.0%, demonstrating its effectiveness in accurately categorizing fractures, while the localization model achieved an accuracy level of 99.94%, showcasing its high precision in accurately segmenting the location of fractures."
