Medical imaging plays a pivotal role in a myriad of clinical applications, serving critical functions in early detection, continuous monitoring, accurate diagnosis, and assessing the effectiveness of treatments across a broad spectrum of medical conditions. Within the domain of computer vision, a foundational comprehension of ANNs and deep learning principles is imperative for navigating the intricacies of medical imaging. In the field of computer vision, a fundamental understanding of artificial neural networks and deep learning principles is essential for navigating the complexities of medical imaging. Deep learning models, trained on diverse datasets, possess the autonomy to identify patterns associated with specific medical conditions. However, challenges persist, impeding progress in this field. The primary hurdle is the absence of definitive detection, classification, and localization mechanisms. The objective of this review is to succinctly encapsulate the key facets of deep learning in bone fracture analysis. Additionally, the review aims to identify various DL models employed for diagnosing bone fractures. Exploration of diverse datasets for detection of bone fracture and classification is undertaken. Furthermore, a comprehensive comparison between traditional methods and DL models in the framework of bone fracture exploration is provided.