Al-Dulaimi Khamael, Tomeo-Reyes Inmaculada, Banks Jasmine, Chandran Vinod
School of Electrical Engineering and Computer Science, Queensland University of Technology, QLD, Australia; Al-Nahrain University, Computer Science Department, Iraq.
School of Electrical Engineering and Telecommunications, University of New South Wales, NSW, Australia.
Comput Biol Med. 2020 Jan;116:103568. doi: 10.1016/j.compbiomed.2019.103568. Epub 2019 Nov 30.
The segmentation of white blood cells and their nuclei is still difficult and challenging for many reasons, including the differences in their colour, shape, background and staining techniques, the overlapping of cells, and changing cell topologies. This paper shows how these challenges can be addressed by using level set forces via edge-based geometric active contours. In this work, three level set forces-based (curvature, normal direction, and vector field) are comprehensively studied in the context of the problem of segmenting white blood cell nuclei based on geometric flows. Cell images are first pre-processed, using contrast stretching and morphological opening and closing in order to standardise the image colour intensity, to create an initial estimate of the cell foreground and to remove the narrow links between lobes and cell bulges. Next, segmentation is conducted to prune out the white blood cell nucleus region from the cell wall and cytoplasm by combining the theory of curve evolution using curvature, normal direction, and vector field-based level set forces and edge-based geometric active contours. The overall performance of the proposed segmentation method is compared and benchmarked against existing techniques for nucleus shape detection, using the same databases. The three level set forces studied here (curvature, normal direction, and vector field) via edge-based geometric active contours achieve F-index values of 92.09%, 91.13%, and 90.76%, respectively, and the proposed segmentation method results in better performance than all other techniques for all indices, including Jaccard distance, boundary displacement error, and Rand index.
白细胞及其细胞核的分割仍然困难且具有挑战性，原因有很多，包括它们在颜色、形状、背景和染色技术方面的差异、细胞重叠以及细胞拓扑结构的变化。本文展示了如何通过基于边缘的几何活动轮廓使用水平集力来应对这些挑战。在这项工作中，在基于几何流分割白细胞细胞核的问题背景下，对三种基于水平集力（曲率、法线方向和向量场）进行了全面研究。首先对细胞图像进行预处理，使用对比度拉伸以及形态学开运算和闭运算，以标准化图像颜色强度，创建细胞前景的初始估计，并去除叶与细胞凸起之间的狭窄连接。接下来，通过结合使用基于曲率、法线方向和向量场的水平集力以及基于边缘的几何活动轮廓的曲线演化理论，进行分割以从细胞壁和细胞质中修剪出白细胞细胞核区域。使用相同的数据库将所提出的分割方法的整体性能与现有的细胞核形状检测技术进行比较和基准测试。通过基于边缘的几何活动轮廓在此研究的三种水平集力（曲率、法线方向和向量场）分别实现了92.09%、91.13%和90.76%的F指数值，并且所提出的分割方法在包括杰卡德距离、边界位移误差和兰德指数在内的所有指标上都比所有其他技术表现更好。
