Carpal Bone Segmentation using Intensity Profile Information and multi-seed based Region Growing

초록

In the early twenty-first century, minimally invasive surgery is the mainstay of various kinds of surgical fields. Surgeons gave percutaneous surgical treatment of the screw directly using a fluoroscopic view in the past. The latest date, they began to operate the fractured carpal bone surgery using Computerized Tomography (CT). Carpal bones composed of wrist joint consist of eight small bones which have hexahedron and sponge shape. Because of these shape, it is difficult to grasp the shape of carpal bones using only CT image data. Although several image segmentation studies have been conducted with carpal bone CT image data, more studies about carpal bone using CT data are still required. Due to the intensity variation of bone structure the carpal bone segmentation process is very challenging task. To do this challenging work more efficiently, we propose modified multi-seed region growing segmentation method, which has preprocessing step to enhance contrast between bone structure and soft tissue with intensity profile. A prior knowledge of intensity characteristics (for example, the minimum intensity level of bone) is exploited to improve poor contrast variation around low contrast regions such as middle of carpal. This enhancement procedure also modifies the intensity distribution of the image. This preprocessing procedure is very preliminary but it gives us far better results comparing to non-preprocessing procedure. In addition, using multi-seed points, multi-bone objects of the carpal bone are extracted simultaneously.