Multiple classification system for fracture detection in human bone x-ray images

Abstract

X-Ray is one the oldest and frequently used devices, that makes images of any bone in the body, including the hand, wrist, arm, elbow, shoulder, foot, ankle, leg (shin), knee, thigh, hip, pelvis or spine. A typical bone ailment is the fracture, which occurs when bone cannot withstand outside force like direct blows, twisting injuries and falls. Automatic detection of fractures in bone x-ray images is considered important, as humans are prone to miss-diagnosis. The main focus of this paper is to automatically detect fractures in long bones and in particular, leg bone (often referred as Tibia), from plain diagnostic X-rays using a multiple classification system. Two types of features (texture and shape) with three types of classifiers (Back Propagation Neural Network, K-Nearest Neighbour, Support Vector Machine) are used during the design of multiple classifiers. A total of 12 ensemble models are proposed. Experiments proved that ensemble models significantly improve the quality of fracture identification.