Alférez S, Merino A, Mujica L E, Ruiz M, Bigorra L, Rodellar J
Universitat Politècnica de Catalunya, Barcelona, Spain.
Int J Lab Hematol. 2014 Aug;36(4):472-80. doi: 10.1111/ijlh.12175. Epub 2013 Dec 11.
There are automated systems for digital peripheral blood (PB) cell analysis, but they operate most effectively in nonpathological blood samples. The objective of this work was to design a methodology to improve the automatic classification of abnormal lymphoid cells.
We analyzed 340 digital images of individual lymphoid cells from PB films obtained in the CellaVision DM96:150 chronic lymphocytic leukemia (CLL) cells, 100 hairy cell leukemia (HCL) cells, and 90 normal lymphocytes (N). We implemented the Watershed Transformation to segment the nucleus, the cytoplasm, and the peripheral cell region. We extracted 44 features and then the clustering Fuzzy C-Means (FCM) was applied in two steps for the lymphocyte classification.
The images were automatically clustered in three groups, one of them with 98% of the HCL cells. The set of the remaining cells was clustered again using FCM and texture features. The two new groups contained 83.3% of the N cells and 71.3% of the CLL cells, respectively.
The approach has been able to automatically classify with high precision three types of lymphoid cells. The addition of more descriptors and other classification techniques will allow extending the classification to other classes of atypical lymphoid cells.
存在用于数字外周血细胞（PB）分析的自动化系统，但它们在非病理性血样中运行最为有效。本研究的目的是设计一种方法来改进异常淋巴细胞的自动分类。
我们分析了来自CellaVision DM96系统获得的PB涂片的340张单个淋巴细胞的数字图像：150个慢性淋巴细胞白血病（CLL）细胞、100个毛细胞白血病（HCL）细胞和90个正常淋巴细胞（N）。我们实施分水岭变换来分割细胞核、细胞质和细胞周边区域。我们提取了44个特征，然后将聚类模糊C均值（FCM）分两步应用于淋巴细胞分类。
图像自动聚类为三组，其中一组包含98%的HCL细胞。使用FCM和纹理特征对其余细胞集再次进行聚类。两个新组分别包含83.3%的N细胞和71.3%的CLL细胞。
该方法能够高精度地自动分类三种类型的淋巴细胞。添加更多描述符和其他分类技术将允许将分类扩展到其他非典型淋巴细胞类别。
