淋巴瘤病理图像中R-S细胞的自动提取

Automatic Abstraction R-S Cells in Pathological Images of Lymphoma

介绍一种淋巴瘤病理图像中R-S细胞自动提取的方法.针对淋巴瘤病理图像中组织灰度分布的特点,采用循环分解和类别方差思想的混合自动分割算法分割病理图像;提出一个基于目标形态、灰度纹理和空间相关性等特征的识别模型,提取R-S细胞.实验结果表明,该方法速度快,能准确地识别提取淋巴瘤病理图像中的R-S细胞,有助于病理医生研究诊断.

Amethod of automatically abstracting R-S cells in pathological images of lymphoma is intro- duced. According to the characteristics of tissular gray distribution in pathological images, a hybrid method based on the algorithm of recursive threshold ing to segment pathological images is adopted and a recognition model based on mathematicalmorphology gray texture and spatial relativities to abstract R-S cells are provid- ed. The experiment results show that the efficiency of this method is satisfying, the method can precisely ab- stractR-S cells in pathological images of lymphoma and help pathological doctors to research and diagnose.