Automated method of fracture detection in CT brain images

This paper presents a novel approach to automatically detect the fracture of skull in CT images. The approach consists of 5 steps: 1) skull segmentation, 2) skull extraction, 3) edge detection, 4) noise removal and, 5) image classification. Experiments show that the recognition rate is 99% for 100 images that are randomly chosen from a medical image database contributed by Hospital Putrajaya, Malaysia. This approach is simple and fast, but yet gives reliable results and high recognition rate. Due to this fact, it can provide a very strong basis of content-based medical image retrieval for medical training or diagnosis.