Using statistical parametric contour and threshold segmentation technology applied in X-ray bone images

• Published in: 2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) pp. 1 - 5
• Main Authors: Kuang-Yi Chou, Chien-Sheng Lin, Chin-Hsiang Chien, Jen-Shiun Chiang, Chih-Hsien Hsia
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2016
• Subjects: Bones; Histograms; Image processing; Image segmentation; Medical diagnostic imaging; Medical image analysis; Wrist; X-ray imaging
• DOI: 10.1109/ISPACS.2016.7824769

The medical image segmentation technology is quite a challenging and complicated research. Generally, an X-ray image is often giving significant information of hard tissue pathology within most assessments. Compared with medical images of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), the advantages of X-ray imaging are inexpensive, and it is widely attempted in most of the medical examinations. The X-ray imaging has been intensively applied on clinical bone diagnostics nowadays. However, the X-ray imaging still has several drawbacks on clarifying its images when radiation intensities exposed unevenly on the examined subject. For example, on a hand X-ray image, if the image has received unequal X-ray strengths, the final image would be inexplicable to separate soft tissues. In this work, we use the technique of a statistical parametric contour with threshold X-ray image segmentation technology to overcome those drawbacks of the X-ray images. By using this approach, we can successfully separate bone from muscle tissues of hand.