A Novel Evolution Strategy of Level Set Method for the Segmentation of Overlapping Cervical Cells
Source abstract
Abstract
Development of an accurate and automated algorithm to completely segment cervical cells in Pap images is still one of the most challenging tasks. The main reasons are the presence of overlapping cells and the lack of guiding mechanism for the convergence of ill-defined contours to the actual cytoplasm boundaries. In this paper, we propose a novel method to address these problems based on level set method (LSM). Firstly, we proposed a morphological scaling-based topology filter (MSTF) and derived a new mathematical toolbox about vector calculus for evolution of level set function (LSF). Secondly, we combine MSTF and the mathematical toolbox into a multifunctional filtering algorithm 2D codimension two-object level set method (DCTLSM) to split touching cells. The DCTLSM can morphologically scale up and down the contour while keeping part of the contour points fixed. Thirdly, we design a contour scanning strategy as the evolution method of LSF to segment overlapping cells. In this strategy, a cutting line can be detected by morphologically scaling the union LSF of the pairs of cells. Then, we used this cutting line to construct a velocity field with an effective guiding mechanism for attracting and repelling LSF. The performance of the proposed algorithm was evaluated quantitatively and qualitatively on the ISBI-2014 dataset. The experimental results demonstrated that the proposed method is capable of fully segmenting cervical cells with superior segmentation accuracy compared with recent peer works.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Image Segmentation Techniques · Advanced Image and Video Retrieval Techniques · Digital Imaging for Blood Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
University of Chinese Academy of Sciences, Beijing 100049, China
Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Science, Shenyang 110016, China
The Key Laboratory of Image Understanding and Computer Vision, Shenyang 110016, China
Space Star Technology Company, Ltd., Beijing 100086, China
References (73)
Show source-provided references
1. Global cancer statistics
2. Cancer incidence and mortality worldwide: Sources, methods and major patterns in globocan 2012
3. Global estimates of cancer prevalence for 27 sites in the adult population in 200810.1002/ijc.27711 ↗
4. A new procedure for staining vaginal smears10.1126/science.95.2469.438 ↗
5. American Cancer Society (2015). Cancer Prevention & Early Detection Facts & Figures 2015–2016, American Cancer Society.
6. Accurate segmentation of nuclei in pathological images via sparse reconstruction and deep convolutional networks10.1016/j.neucom.2016.08.103 ↗
7. A method for quantitative analysis of clump thickness in cervical cytology slides10.1016/j.micron.2015.09.002 ↗
8. Win, K.P., Kitjaidure, Y., Hamamoto, K., and Myo Aung, T. (2020). Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images. Appl. Sci., 10.10.3390/app10051800 ↗
9. Segmentation of cytoplasm and nuclei of abnormal cells in cervical cytology using global and local graph cuts10.1016/j.compmedimag.2014.02.001 ↗
10. A review of automated techniques for cervical cell image analysis and classification10.1007/978-94-007-4270-3_1 ↗
11. Béliz-Osorio, N., Crespo, J.M., García-Rojo, A.M., and Azpiazu, J. (2011). Cytology Imaging Segmentation Using the Locally Constrained Watershed Transform. Proceedings of the 10th International Symposium on Mathematical Morphology and Its Applications to Image and Signal Processing (ISMM 2011), Verbania-Intra, Italy, 6–8 July 2011, Springer-Verlag.10.1007/978-3-642-21569-8_37 ↗
12. Unsupervised cell nucleus segmentation with active contours10.1016/S0165-1684(98)00145-5 ↗
13. Segmenting clustered nuclei using H-minima transform-based marker extraction and contour parameterization10.1109/TBME.2010.2060336 ↗
14. Plissiti, M.E., Nikou, C., and Charchanti, A. (2010, January 3–5). Watershed-based segmentation of cell nuclei boundaries in Pap smear images. Proceedings of the IEEE International Conference on Information Technology & Applications in Biomedicine, Corfu, Greece.10.1109/ITAB.2010.5687745 ↗
15. Unsupervised segmentation of overlapped nuclei using Bayesian classification10.1109/TBME.2010.2060486 ↗
16. Automated cell nucleus segmentation using improved snake
17. Automated detection of cell nuclei in pap smear images using morphological reconstruction and clustering10.1109/TITB.2010.2087030 ↗
18. Plissiti, M., Charchanti, A., Krikoni, O., and Fotiadis, D. (2006, January 26–28). Automated segmentation of cell nuclei in Pap smear images. Proceedings of the IEEE International Special Topic Conference on Information Technology in Biomedicine, Ioannina, Greece.
19. Detection and segmentation of cervical cell cytoplast and nucleus10.1002/ima.20198 ↗
20. Edge Enhancement Nucleus and Cytoplast Contour Detector of Cervical Smear Images10.1109/TSMCB.2007.912940 ↗
21. Improving level set method for fast auroral oval segmentation10.1109/TIP.2014.2321506 ↗
22. Accurate segmentation of cervical cytoplasm and nuclei based on multiscale convolutional network and graph partitioning10.1109/TBME.2015.2430895 ↗
23. Ushizima, D., Bianchi, A., and Carneiro, C. (2015). Segmentation of Subcellular Compartments Combining Superpixel Representation with Voronoi Diagrams, Ernest Orlando Lawrence Berkeley Nat. Lab.. Tech. Rep. LBNL-6892E.
24. Automation-assisted cervical cancer screening in manual liquid-based cytology with hematoxylin and eosin staining10.1002/cyto.a.22407 ↗
25. Ramalho, G.L., Ferreira, D.S., Bianchi, A.G., Carneiro, C.M., Medeiros, F.N., and Ushizima, D.M. (2015, January 16–19). Cell reconstruction under Voronoi and enclosing ellipses from 3D microscopy. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), Brooklyn Bridge, NY, USA.
26. Lee, H., and Kim, J. (July, January 26). Segmentation of overlapping cervical cells in microscopic images with superpixel partitioning and cell-wise contour refinement. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, USA.10.1109/CVPRW.2016.172 ↗
27. Curvelet initialized level set cell segmentation for touching cells in low contrast images10.1016/j.compmedimag.2016.01.002 ↗
28. Tareef, A., Song, Y., Cai, W., Feng, D.D., and Chen, M. (2014, January 10–12). Automated three-stage nucleus and cytoplasm segmentation of overlapping cells. Proceedings of the 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), Singapore.10.1109/ICARCV.2014.7064418 ↗
29. Tareef, A., Song, Y., Lee, M.Z., Feng, D.D., and Cai, W. (2015, January 23–25). Morphological Filtering and Hierarchical Deformation for Partially Overlapping Cell Segmentation. Proceedings of the 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Adelaide, Australia.10.1109/DICTA.2015.7371285 ↗
30. A variational approach for overlapping cell segmentation
31. Nosrati, M., and Hamarneh, G. (2015). Segmentation of overlapping cervical cells: A variational method with star-shape prior. Proc. ISBI, 186–189.10.1109/ISBI.2015.7163846 ↗
32. Lu, Z., Carneiro, G., and Bradley, A.P. (2013). Automated nucleus and cytoplasm segmentation of overlapping cervical cells. Medical Image Computing and Computer-Assisted Intervention, Springer.10.1007/978-3-642-40811-3_57 ↗
33. An improved joint optimization of multiple level set functions for the segmentation of overlapping cervical cells
34. Fronts propagating with curvature dependent speed: Algorithms based on Hamilton–Jacobi formulations10.1016/0021-9991(88)90002-2 ↗
35. Snakes: Active contour models10.1007/BF00133570 ↗
36. A Geometric Model for Active Contours in Image Processing10.1007/BF01385685 ↗
37. Shape Modeling with Front Propagation: A Level Set Approach10.1109/34.368173 ↗
38. Optimal approximations by piecewise smooth functions and associated variational problems10.1002/cpa.3160420503 ↗
39. A Variational Level Set Approach to Multiphase Motion10.1006/jcph.1996.0167 ↗
40. Chan, T., and Vese, L. (1999). An Active Contour Model without Edges. International Conference on Scale-Space Theories in Computer Vision, Springer-Verlag.10.1007/3-540-48236-9_13 ↗
41. Geodesic active contours10.1023/A:1007979827043 ↗
42. Chen, Y., Thiruvenkadam, H., Tagare, H., Huang, F., and Wilson, D. (2001, January 1). On the Incorporation of Shape Priors int Geometric Active Contours. Proceedings of the IEEE Workshop in Variational and Level Set Methods, Vancouver, BC, Canada.
43. Distance regularized level set evolution and its application to image segmentation10.1109/TIP.2010.2069690 ↗
44. Canny, J. (1986). A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI, 679–698.10.1109/TPAMI.1986.4767851 ↗
45. Spiral Crystal Growth10.1016/S0167-2789(99)00216-X ↗
46. Motion of curves in three spatial dimensions using a level set approach10.1006/jcph.2001.6758 ↗
47. A relay level set method for automatic image segmentation10.1109/TSMCB.2010.2065800 ↗
48. A Unified Tensor Level Set for Image Segmentation10.1109/TSMCB.2009.2031090 ↗
49. A shape-initialized and intensity-adaptive level set method for auroral oval segmentation10.1016/j.ins.2014.03.014 ↗
50. Optimizing the cervix cytological examination based on deep learning and dynamic shape modeling10.1016/j.neucom.2017.01.093 ↗
51. Huang, Y., Zhu, H., Wang, P., and Dong, D. (2019, January 6–9). Segmentation of Overlapping Cervical Smear Cells Based on U-Net and Improved Level Set. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy.10.1109/SMC.2019.8914625 ↗
52. Learning Shape-Driven Segmentation Based on Neural Network and Sparse Reconstruction toward Automated Cell Analysis of Cervical Smears
53. Automatic segmentation of overlapping cervical smear cells based on local distinctive features and guided shape deformation10.1016/j.neucom.2016.09.070 ↗
54. Accurate Cervical Cell Segmentation from Overlapping Clumps in Pap Smear Images10.1109/TMI.2016.2606380 ↗
55. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
56. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net. Convolutional Networks for Biomedical Image Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
57. Mask R-CNN10.1109/TPAMI.2018.2844175 ↗
58. Kirillov, A., Girshick, R.B., He, K., and Dollár, P. (2018). Panoptic Feature Pyramid Networks. arXiv.10.1109/CVPR.2019.00656 ↗
59. Accurate segmentation of overlapping cells in cervical cytology with deep convolutional neural networks10.1016/j.neucom.2019.06.086 ↗
60. Cytoplasm and nucleus segmentation in cervical smear images using radiating GVF snake10.1016/j.patcog.2011.09.018 ↗
61. Kale, A., and Aksoy, S. (2010, January 23–26). Segmentation of cervical cell images. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.587 ↗
62. A linear time algorithm for computing exact euclidean distance transforms of binary images in arbitrary dimensions10.1109/TPAMI.2003.1177156 ↗
63. Osher, S., and Fedkiw, R. (2003). Level Set Methods and Dynamic Implicit Surfaces, Springer.10.1007/b98879 ↗
64. Topographic distance and watershed lines10.1016/0165-1684(94)90060-4 ↗
65. Vedaldi, A., and Soatto, S. (2008). Quick shift and kernel methods for mode seeking. Comput. Vis., 705–718.10.1007/978-3-540-88693-8_52 ↗
66. A general approach to connected-component labeling for arbitrary image representations10.1145/128749.128750 ↗
67. Matas, J., Chum, O., Urban, M., and Pajdla, T. (2002, January 2–5). Robust wide baseline stereo from maximally stable extremal regions. Proceedings of the British Machine Vision Conference 2002, Cardiff, UK.10.5244/C.16.36 ↗
68. A Level Set Formulation for the Solution of the Dirichlet Problem for Hamilton–Jacobi Equations10.1137/0524066 ↗
69. Efficient Algorithms for Globally Optimal Trajectories10.1109/9.412624 ↗
70. Guangqi, L. (2020, September 01). Mathmatical-Toolbox-for-DCTLSM. Available online: https://github.com/liuchee/Mathmatical-Toolbox-for-DCTLSM.
71. (2020, September 06). Overlapping Cervical Cytology Image Segmentation Challenge-ISBI. Available online: https://cs.adelaide.edu.au/~carneiro/isbi14_challenge/index.html.
72. A one-pass extended depth of field algorithm based on the over-complete discrete wavelet transform
73. Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells10.1109/JBHI.2016.2519686 ↗