Shitong Wang, Min Wang
Computer Department, Southern Yangtse University, Wuxi, China.
IEEE Trans Inf Technol Biomed. 2006 Jan;10(1):5-10. doi: 10.1109/titb.2005.855545.
White blood cell detection is one of the most basic and key steps in the automatic recognition system of white blood cells in microscopic blood images. Its accuracy and stability greatly affect the operating speed and recognition accuracy of the whole system. But there are only a few methods available for cell detection or segmentation due to the complexity of the microscopic images. This paper focuses on this issue. Based on the detailed analysis of the existing two methods--threshold segmentation followed by mathematical morphology (TSMM), and the fuzzy logic method--a new detection algorithm (NDA) based on fuzzy cellular neural networks is proposed. NDA combines the advantages of TSMM and the fuzzy logic method, and overcomes their drawbacks. With NDA, we can detect almost all white blood cells, and the contour of each detected cell is nearly complete. Its adaptability is strong and the running speed is expected to be comparatively high due to the easy hardware implementation of FCN. Experimental results show good performance.
白细胞检测是显微血液图像中白细胞自动识别系统最基本和关键的步骤之一。其准确性和稳定性极大地影响整个系统的运行速度和识别精度。但由于显微图像的复杂性，用于细胞检测或分割的方法很少。本文聚焦于该问题。在详细分析现有两种方法——先阈值分割再进行数学形态学处理（TSMM）和模糊逻辑方法的基础上，提出了一种基于模糊细胞神经网络的新检测算法（NDA）。NDA结合了TSMM和模糊逻辑方法的优点，克服了它们的缺点。使用NDA，我们几乎可以检测到所有白细胞，并且每个检测到的细胞轮廓几乎完整。其适应性强，由于模糊细胞神经网络易于硬件实现，预计运行速度较高。实验结果显示出良好的性能。
