An improved OTSU's method for CT image boundary contour extraction

Computed tomography (CT) technology is a classic medical diagnostic tool. The extraction of ts image information has great clinical significance. With the study of CT image boundary contour extraction, an improved OTSU's method which combines adaptive threshold segmentation with edge detection is invented. This method can calculate the optimal threshold automatically, simply and quickly. And the extracted outline is clear and accurate. The proposed method has been coded in MATLAB and tested by sets of clinical CT images. And the results show that the method has strong robustness and can be applied to most CT images. Thus, the improved OTSU method has great potential to be widely used in medical diagnosis and clinical modeling.