篇名 | Segmentation Technology of Medical Images Based on Regional Growth |
---|---|
卷期 | 31:3 |
作者 | Qiang Guo 、 Gao-Yang Li 、 Yong Wang |
頁次 | 115-125 |
關鍵字 | blood vessel segmentation 、 gradation transformation 、 medical image 、 region growth 、 seed point selection 、 EI 、 MEDLINE 、 Scopus |
出刊日期 | 202006 |
DOI | 10.3966/199115992020063103009 |
This paper mainly studies the enhancement and segmentation of blood vessels in medical image processing. Firstly, the blood vessel images are preprocessed. In this paper, the gray-scale transformation method is used to enhance the image; then the principle of region growth and its advantages and disadvantages are analyzed. It is found that there are two key points in segmenting the blood vessel image by the method of region growth: one is the selection of seed points. Since manual selection of seed points is time-consuming and labor-intensive, this paper chooses to fix the seed points in the middle of the image. The second is the determination of the threshold T. In this paper, through the experiments of multiple groups, the appropriate threshold is finally determined. Experiments show that the proposed vascular segmentation algorithm can segment regional blood vessels with high efficiency and high quality and reduce human intervention, and has good robustness.