Automatic Cell Nuclei Segmentation Using Superpixel and Clustering Methods in Histopathological Images

It is seen that there is an increase in cancer and cancer-related deaths day by day. Early diagnosis is vital for the early treatment of the cancerous area. Computer-aided programs allow for the early diagnosis of unhealthy cells that specialist pathologists diagnose due to efforts. In this study, clustering and superpixel segmentation techniques were used to detect cell nuclei in high-resolution histopathology images automatically. As a result of the study, the successful performances of the segmentation algorithms were analyzed and evaluated. It is seen that better success is obtained in the Watershed and FCM algorithms in highresolution histopathological images used. Quickshift and SLIC methods gave better results in terms of precision. It is seen that there are k-Means and FCM algorithms that provide the best performance in F measure (F-M), and the correct negative rate (TNR) is more successful in Quickshift, kMeans, and SLIC methods.

PDF

___

[1] Anonim,2017. Erken Teşhis Hayat Kurtarır [Online] https://www.saglik.gov.tr/Eklenti/8635,kanseristatistikleridocx.docx?0
[2] A. Albayrak and G. Bilgin, 2017. Superpixel approach in high resolution histopathological image segmentation. In 2017 25th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
[3] J. Xu, L. Xiang, Q. Liu, H. Gilmore, J. Wu, J. Tang, and A. Madabhushi,2015. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE transactions on medical imaging, 35(1), 119-130.
[4] B. H. Aksebzeci, and Ö. Kayaalti, 2017. Computer-aided classification of breast cancer histopathological images. In 2017 Medical Technologies National Congress (TIPTEKNO) (pp. 1-4). IEEE.
[5] A. Albayrak, and G. Bilgin, (2018). Segmentation of cellular structures with encoder-decoder-based deep learning algorithm in histopathological images. In 2018 Medical Technologies National Congress (TIPTEKNO) (pp. 1-4). IEEE.
[6] A.Albayrak, A. Ünlü, N. Çalık, G. Bilgin İ. Türkmen A. Çakı., ... and L. D. Ata, (2017). Segmentation of precursor lesions in cervical cancer using convolutional neural networks. In 2017 25th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
[7] S. Turan, and G. Bilgin, (2019). Semantic nuclei segmentation with deep learning on breast pathology images. In 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) (pp. 1-4). IEEE.
[8] B. Li, W. J. Niessen, S. Klein, M. de Groot, M.A. Ikram, M. W.Vernooij, and E. E. Bron,(2019). A hybrid deep learning framework for integrated segmentation and registration: Evaluation on longitudinal white matter tract changes. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 645-653). Springer, Cham.
[9] O. Ronneberger, P. Fischer, and T. Brox (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computerassisted intervention (pp. 234-241). Springer, Cham.
[10] M. E. Bagdigen, and G. Bilgin, (2019). Detection and Grading of Breast Cancer via Spatial Features in Histopathological Images. In 2019 Medical Technologies Congress (TIPTEKNO) (pp. 1-4). IEEE.
[11] A. Feng-Ping, and L. Zhi-Wen, (2019). Medical image segmentation algorithm based on feedback mechanism convolutional neural network. Biomedical Signal Processing and Control, 53, 101589.
[12] K. Xia, H. Yin, P. Qian, Y. Jiang, and S. Wang, (2019). Liver semantic segmentation algorithm based on improved deep adversarial networks in a combination of weighted loss function on abdominal CT images. IEEE Access, 7, 96349-96358.
[13] Y. Feng, H. Zhao, X. Li, X. Zhang, and H. Li, (2017). A multi-scale 3D Otsu thresholding algorithm for medical image segmentation. Digital Signal Processing, 60, 186-199.
[14] T. H. Farag, W. A. Hassan, H. A. Ayad, A.S AlBahussain, U. A. Badawi, and M. K. Alsmadi, (2017). Extended absolute fuzzy connectedness segmentation algorithm utilizing region and boundary based information. Arabian Journal for Science and Engineering, 42(8), 3573-3583.
[15] I. F. Salazar-Reque, S. G. Huamán, G. Kemper, J. Telles, and D. Diaz, (2019). An algorithm for plant disease visual symptom detection in digital images based on superpixels. Int. J. Adv. Sci. Eng. Inf. Technol, 9(1), 194-203.
[16] W. Qin, J. Wu , F.Han, Y. Yuan, W. Zhao, B. Ibragimov, ... and L. Xing, (2018). Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation. Physics in Medicine & Biology, 63(9), 095017.
[17] O. F. Kar, A. Güngör, S. Ilbey, and H. E. Güven, (2018, May). An efficient parallel algorithm for single-pixel and fpa imaging. In Computational Imaging III (Vol. 10669, p. 106690J). International Society for Optics and Photonics.
[18] H. Yu, M. Jiang, H. Chen, J. Feng, Y. Wang, and Y. Lu, (2017). Super-pixel algorithm and group sparsity regularization method for compressed sensing MR image reconstruction. Optik, 140, 392-404.
[19] S. Kaur, R. K. Bansal, M. Mittal, L. M Goyal, I. Kaur, and A. Verma, (2019). Mixed pixel decomposition based on extended fuzzy clustering for single spectral value remote sensing images. Journal of the Indian Society of Remote Sensing, 47(3), 427-437.
[20] T. Kanungo, Mount, DM, Netanyahu, NS, Piatko, CD, Silverman, R., and Wu, AY (2002). An effective k-mean clustering algorithm: Analysis and application. IEEE processes on model analysis and machine intelligence, 24 (7), 881-892.
[21] A. Likas, N. Vlassis, and J. J. Verbeek, (2003). The global k-means clustering algorithm. Pattern recognition, 36(2), 451-461.
[22] B. K. Tripathy, A. Basu, and S. Govel, (2014). Image segmentation using spatial intuitionistic fuzzy C means clustering. In 2014 IEEE International Conference on Computational Intelligence and Computing Research (pp. 1-5). IEEE.
[23] S. Zhang, Z. Ma, G. Zhang, T. Lei, R. Zhang, and Y. Cui (2020). Semantic Image Segmentation with Deep Convolutional Neural Networks and Quick Shift. Symmetry, 12(3), 427.
[24] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Süsstrunk, (2012). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE transactions on pattern analysis and machine intelligence, 34(11), 2274-2282.
[25] S. Zhang, Z. Ma, G. Zhang, T. Lei, R. Zhang, and Y. Cui, (2020). Semantic Image Segmentation with Deep Convolutional Neural Networks and Quick Shift. Symmetry, 12(3), 427.
[26] F. M. Osman, and M. H. Yap, (2020). Adjusted Quick Shift Phase Preserving Dynamic Range Compression method for breast lesions segmentation. Informatics in Medicine Unlocked, 100344.
[27] A. Levinshtein, A. Stere, K. N. Kutulakos, D. J. Fleet, S. J. Dickinson, and K. Siddiqi, (2009). Turbopixels: Fast superpixels using geometric flows. IEEE transactions on pattern analysis and machine intelligence, 31(12), 2290-2297.
[28] P. F. Felzenszwalb, and D.P. Huttenlocher, (2004). Efficient graphbased image segmentation. International journal of computer vision, 59(2), 167-181.
[29] L. Yao, and S. Muhammad, (2019). A novel technique for analysing histogram equalized medical images using superpixels. Computer Assisted Surgery, 24(sup1), 53-61.
[30] [30] V. Machairas, E. Decencière, and T. Walter, (2014). Waterpixels: Superpixels based on the watershed transformation. In 2014 IEEE International Conference on Image Processing (ICIP) (pp. 4343-4347)
[31] [31] J. Schönberger, A. Siqueira, A. Mueller, E. Gouillart, G. Lee, M. Harfouche, J. Warner, J.N. Iglesias, L. Grüter, M. Corvellec, R. Fezzani, F. Boulogne, E. Panfilov, and S. Walt, (2014) https://scikitimage.org/ [Online]
[32] [32] Benson, CC, V. Deepa, Lajish, VL, and K. Rajamani, (2016). Brain tumor segmentation from MR brain images using advanced fuzzy c-averaged clustering and watershed algorithm. In the 2016 International Conference on Informatics, Communication and Informatics Advances (ICACCI) (p.187-192).
[33] J. B. Roerdink and A. Meijster,(2000). The watershed transform: Definitions, algorithms and parallelization strategies. Fundamenta Informatica, 41(1, 2), 187-228
[34] A.Albayrak, and G. Bilgin, (2019). Automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms. Medical & biological engineering & computing, 57(3), 653-665.
[35] W. Wang, D. Xiang, Y. Ban, J. Zhang, and J. Wan, (2017). Superpixel segmentation of polarimetric SAR images based on integrated distance measure and entropy rate method. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(9), 4045-4058.
[36] M. Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa, (2011). Entropy rate superpixel segmentation. In CVPR 2011 (pp. 2097- 2104). IEEE.
[37] A. S. Glas, J. G. Lijmer, M. H. Prins, G. J. Bonsel, and P. M. Bossuyt, (2003). The diagnostic odds ratio: a single indicator of test performance. Journal of clinical epidemiology, 56(11), 1129-1135.