A segmentation algorithm of the cortex bone and trabecular bone in Proximal humerus based on CT images

State evaluation of proximal humeral trabecular bone can be used as one of the determining methods of osteoporosis state. By using computer image analysis technology, an objective and effective computer aided diagnosis system can be designed. Based on the reasonable threshold, the binarization of humerus CT image is done, and then the image pretreatment is finished by using the method of mathematical morphology. Finally the cortex bone and trabecular bone in proximal humeral is extracted successfully by using Gabor wavelet transform. The experimental results show that the algorithm is with good stability.