基于多光谱采集技术的骨髓涂片细胞分割方法

通过光学显微镜估计不同类型、不同成熟阶段的血细胞的相对数目对血液病的诊断具有十分重要的意义。由于骨髓中有核血细胞类数多,特征复杂,给自动分析造成极大困难。论文采用了一种新颖的多光谱成像技术,所采集的图像可以提供更多反映物质特性的光谱信息。在此基础上,探索性地将支持向量机用于骨髓细胞图像的分割。实验证明这种以多光谱技术为基础的分割方法推广性好,准确率非常高,并且明显降低了对采集设备情况和涂片质量的依赖性。

Segmentation of Blood and Bone Marrow Smears Based on Multispectral Imaging Techniques

Counting of different classes of white blood cells in bone marrow smears can give pathologists valuable information regarding various cancers.But it is difficult to manually locate ,identify ,and count these classes of cells by automatic techniques.Multispectral imaging techniques providing additional useful spectral information in common pathological samples are used for image acquisition.On this base,a novel segmentation algorithm using support vector machine is presented for segmentation.Experiments show that the segmentation is robust,precise,insensitive to smear staining and illumination condition.