为了更加简单、高效并准确地识别定位经苏木精-伊红（HE）染色切片图像中的细胞核，本文提出了一种基于距离的细胞核标记方法，这种方法为在细胞核丛聚图像中提取细胞核单体提供了一种新的处理思路。与目前主流的基于凹度分析的方法不同，本文所述方法避免了对图像中细胞核丛聚和细胞核单体的分类预处理，可以对含有细胞核丛聚的完整图像进行直接处理。该方法使用了一种被称为距离评估矩阵序列（MSDRE）的矩阵集对丛聚细胞核中的点到区域边界的距离进行快速估算，结合凸区域的中心点距边界最远这一客观事实，它可以快速准确地定位、标记出图像中所有的细胞核单体。在实验中，本标记方法获得了 95.26% 的标记准确率和每 1 000 个目标物平均耗时 1.54 s 的标记效率，较目前的主流方法具有更好的识别准确率和执行效率。本文所述方法在保持标记准确率不降低的前提下，大幅提高了识别标记的效率，提升了 HE 染色切片图像分析系统的实时性，有利于相关成果的实施和应用
References
[1]
18. Liu X, Wang Y, Tang Z. A clump splitting based method to localize speech balloons in comics//International Conference on Document Analysis and Recognition, 2015: 901-905.
[2]
20. Cosatto E, Miller M, Graf H P, et al. Grading nuclear pleomorphism on histological micrographs//19th International Conference On Pattern Recognition, 2008, 1-6: 672.
[3]
4. Beucher S, Lantu Joul C. Use of watershed in contour detection. International workshop on image processing, real-time edge and motion detection, 1979: 391-396.
[4]
14. Bai X Z, Sun C M, Zhou F G. Splitting touching cells based on concave points and ellipse fitting. Pattern Recognit, 2009, 42(11): 2434-2446.
[5]
15. Yeo T E, Jin X C, Ong S H, et al. Clump splitting through concavity analysis. Pattern Recognit Lett, 1994, 15(10): 1013-1018.
[6]
1. Kirubarajan T, Bar-Shalom Y. Combined segmentation and tracking of overlapping objects with feedback//2001 IEEE Workshop on Multi-Object Tracking, Washington, 2001: 77-84.
[7]
2. Wang W X. Binary image segmentation aggregates based on polygonal approximation and classification of concavities, 1998, 31(10): 1503-1524.
[8]
3. Ong S H, Jayasooriah R, Yeow H H, et al. Decomposition of digital clumps into convex parts by contour tracing and labelling. Pattern Recognit Lett, 1992, 13(11): 789-795.
[9]
5. Liu Lifeng, Sclaroff S. Shape-Guided split and merge of image regions. Visual Form 2001, Heidelberg: Springer, 2001: 367-377.
[10]
6. Ip H S, Yu R P K. Recursive splitting of active contours in multiple clump segmentation. Electron Lett, 1996, 32(17): 1564-1566.
[11]
7. Wang Hui, Zhang Hong, Ray N. Clump splitting via bottleneck detection and shape classification. Pattern Recognit, 2012, 45(7): 2780-2787.
[12]
8. Farhan M, Yli-Harja O, Niemisto A. A novel method for splitting clumps of convex objects incorporating image intensity and using rectangular window-based concavity point-pair search. Pattern Recognit, 2013, 46(3): 741-751.
[13]
9. Latorre A, Alonso-Nanclares L, Muelas S, et al. Segmentation of neuronal nuclei based on clump splitting and a two-step binarization of images. Expert Syst Appl, 2013, 40(16): 6521-6530.
[14]
10. Samsi S, Trefois C, Antony P M, et al. Automated nuclei clump splitting by combining local concavity orientation and graph partitioning//2014 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2014: 412-415.
[15]
11. Ulle A R, Nagabushan T N, Basavaraj V. Clump splitting in histopathological images based on concave points//2015 International Conference on Cognitive Computing and Information Processing (CCIP), 2015: 1-6.
[16]
12. Kumar S, Ong S H, Ranganath S, et al. A rule-based approach for robust clump splitting. Pattern Recognit, 2006, 39(6): 1088-1098.
[17]
13. Janssens T, Antanas L, Derde S, et al. Charisma: an integrated approach to automatic H&E-stained skeletal muscle cell segmentation using supervised learning and novel robust clump splitting. Med Image Anal, 2013, 17(8): 1206-1219.
[18]
16. Wen Q, Chang H, Parvin B. A Delaunay triangulation approach for segmenting clumps of nuclei//2009 IEEE International Symposium on Biomedical Imaging: From Nano To Macro, 2009, 1-2: 9-12.
[19]
17. Dorfer M, Mattes J. Recursive water flow: a shape decomposition approach for cell clump splitting// 12th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2016: 811-815.
[20]
19. Macenko M, Niethammer M, Marron J S, et al. A method for normalizing histology slides for quantitative analysis//2009 IEEE International Symposium on Biomedical Imaging: From Nano To Macro, 2009, 1-2: 1107.
