An Automated Detection and Classification System of Calcaneal Fracture with Deep Learning Techniques

Calcaneus fracture is the most common fracture in all types of Tarsal fracture. Early and accurate diagnosis is essential for prompt treatment. This study aims to develop an automatic detection and classification system for calcaneal fracture with deep learning techiques, in which the X-ray images of calcaneal fractures can be detected and classified clearly. In this study, we collected the X-ray image dataset of calcaneal, which was categorized as either fracture or non-fracture, and employed data augmentation techniques to expand the volume and variety of the dataset. In this work, a Deep Residual Neural Network (ResNet) model has been trained for binary fracture classification. To enhance the model interpret-ability and help non-deep learning experts understand how the model predicts. We've utilized the Grad-CAM method to generate the heatmaps. With the heatmaps, the range of calcaneal fracture can be highligted and realized more clearly and intuitively.