Long-Bone Fracture Detection using Artificial Neural Networks based on Line Features of X-ray Images

Abstract

Two line-based fracture detection schemes are developed and discussed, namely Standard line-based fracture detection and Adaptive Differential Parameter Optimized (ADPO) line-based fracture detection. The purpose of the two line-based fracture detection schemes is to detect fractured lines from X-ray images using extracted features based on recognised patterns to differentiate fractured lines from non-fractured lines. The schemes reduce the number of images required for training, as the training is performed line-wise. The difference between the two schemes is the detection of lines. The ADPO scheme optimizes the parameters of the Probabilistic Hough Transform, such that granule lines within the fractured regions are detected. The lines are given in the form of points, (x, y), which includes the starting and ending points. Based on the given line points, 13 features are extracted from each line as a summary of line information. These features are used for fracture and non-fracture classification of the detected lines. The classification is carried out by the Artificial Neural Network (ANN). The Standard Scheme is capable of achieving an average accuracy of 71.57%, whereas the ADPO scheme achieved an average accuracy of 72.89%. The ADPO scheme is opted for over the Standard scheme, however it can be further improved with contour fracture detection.