Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

Abstract

The musculoskeletal radiograph (MURA) dataset, which is the largest bone x-ray dataset is an important resource for training and testing the machine learning model, as it has been specifically analyzed and well-classified by specially trained radiologists. Four CNN architectures have separately trained and evaluated the dataset ( DenseNet201 GoogLeNet, ResNet50, and Inception-ResNet-V2). The results of the algorithms showed variation in recall and accuracy. In addition, multiple-architecture ensemble models performed better than single models, highlighting the benefits of ensembling techniques to improve prediction accuracy. Combining multiple deep learning models reduces the risk of overfitting, increases predictive stability, improves accuracy, and optimizes the dataset. The integration of several models considers dataset robustness and uncertainty reduction. This ensembling process enables the development of accurate diagnostic tools for upper limb bone-related problems using the MURA dataset and other radiographic datasets. This work shows the use of ensemble methodologies, optimization of architecture, and various techniques, such as using data augmentation and demonstrating the ability of CNN to generalize musculoskeletal diseases. The results of this work can contribute to the creation of more effective diagnostic tools for the healthcare industry.