| Summary: | 碩士 === 朝陽科技大學 === 資訊管理系碩士班 === 99 === Prostate cancer is one of the leading causes of cancer death in men in recent years, so diagnosis and treatment of prostate cancer are very important. After the total perineal prostatomy, physicians have to review the whole mount prostate Biopsy to make the prognosis and treatment plan.
However, It is a heavy loading to pathologists. They have to spend a lot of time to examine a large number of biopsies one by one and mark the location of the tumor and make the diagnosis. Such a high repetitive work will cause a large disturbance for pathologists. Besides, there are different definitions for the same biopsy by different pathologists. Thus, the automatic diagnosis system for the whole prostate biopsy is thus needed. The key issue for this system is whether the area of the prostate gland can be well segmented automatically.
In this paper, we propose an image segmentation method based on morphology method. It segmented normal prostate gland and break regions from whole prostate biopsy automatically and leave the areas of the prostate cancer. These areas can be adopted as the input of the automatic diagnosis system and help pathologists to make the diagnosis more accuracy.
|
|---|
