Precise bone fracture detection is a critical component of medical image analysis, playing a pivotal role in curing the impacts of bone-related disorders. The Fast R-CNN algorithm, a widely adopted enhanced deep study for object detection, has exhibited remarkable efficacy across various domains, including medical image analysis. This research introduces an innovative approach for bone fracture detection by leveraging the Fast R-CNN algorithm. The enhanced approach involves employing an extensive CNN model is used to extract salient features from X-ray images, followed by the application of a region proposal network to identify potential regions of interest for fracture detection. Subsequently, the Fast R-CNN algorithm classifies these regions as either fractured or non-fractured. Notably, experimental results demonstrate the superior performance of the proposed approach compared to state-of-the-art methods, achieving an average precision of 94.5%. This novel approach holds immense potential to significantly enhance the accuracy and efficiency of bone fracture diagnosis, providing valuable support to radiologists and medical professionals in their diagnostic endeavors.