| 罗洪艳,李敏,谭立文,郑小林,张绍祥,侯文生.一种数字人脑部切片图像分割新方法[J].中国医学影像技术,2009,25(8):1488~1491 |
| 一种数字人脑部切片图像分割新方法 |
| A new segmentation method for slice images of digital human brain |
| 投稿时间：2009-02-27 修订日期：2009-03-24 |
| DOI： |
| 中文关键词: 切片图像分割 白质 皮质 区域生长 |
| 英文关键词:Slice image segmentation White matter Cerebral cortex Region growing |
| 基金项目:国家自然科学基金(60771025)。 |
|
| 摘要点击次数: 2662 |
| 全文下载次数: 928 |
| 中文摘要: |
| 目的 提出一种人脑切片图像自动分割算法,以克服现有的方法对大量人工参与的依赖。 方法 针对人脑切片图像的特征,提出一种基于区域生长的灰度直方图阈值化分割算法。首先通过区域生长过程对图像进行初始的粗分割,再用直方图阈值化方法进行二次细分割提取目标区域。 结果 采用此方法准确有效地分割出了大脑白质和大脑皮质。 结论 此算法结合切片图像的全局信息和局部信息应用于分割,是一种比较好的分割方法。 |
| 英文摘要: |
| Objective To present a new automatic segmentation algorithm for human slice images,in order to reduce the massive manual intervention in the existing segmentation methods. Methods According to the features of slice images of digital human brain, a segmentation algorithm based on the theory of region growing and threshold in normal gray histogram was proposed. More exactly, the slice images were initially segmented coarsely by means of the region growing. Then the method of threshold in normal gray histogram was adopted to refine the segmentation. Results White matter and cerebral cortex were segmented accurately and effectively with this method. Conclusion This algorithm characterized by the combination of global information and local information of a slice image for automatic segmentation exhibits good performance. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
