NLCL: A Novel Methodology Design to Predict Bone Fracture Detection using Neural Learning assisted Classification Logic

Bone fractures are among the most common injuries worldwide, often necessitating quick and precise diagnosis to prevent complications. Conventional methods, reliant on manual interpretation of X-ray images, are prone to errors and time-consuming. This study presents a novel methodology, NLCL (Neural Learning-assisted Classification Logic), for bone fracture detection using X-ray images. The proposed model combines Convolutional Neural Networks (CNNs) for high-level feature extraction and dense layers for classification, enhanced with assisted classification logic to improve fracture identification. Leveraging a comprehensive dataset of bone fractures, including categories such as Elbow Positive, Fingers Positive, and Wrist Positive, the NLCL model underwent rigorous training and evaluation. Preprocessing techniques, including denoising, data augmentation, and normalization, ensured dataset quality. The NLCL model achieved superior performance with an accuracy of 98.66%, precision of 98.85%, recall of 98.73%, and an F1-score of 98.79%, significantly outperforming nine state-of-the-art models. These results demonstrate the model’s potential for integration into clinical workflows, enabling automated, reliable, and efficient bone fracture detection. Future work could extend the methodology to real-time diagnostic tools and explore its applicability to other medical imaging domains.