FARUK SERİN, Metin ERTURKLER, Mehmet GÜL

A Novel Probabilistic Nuclei Segmentation Algorithm for H&E Stained Histopathological Tissue Images

In this study, we propose a novel, fast and accurate segmentation algorithm to segment nuclei in H&E stained histopathological tissue images. The proposed algorithm does not require pre-processing, post-processing, and any manual parameter or threshold. The algorithm utilizes probabilistic and statistical properties of the pixels’ color value in the images with RGB color space, and determines whether pixels are a part of any nuclei or not by using an automatically calculated threshold value. The algorithm provides time efficiency and reduced overall cost in the segmentation. Two more algorithms are also proposed to distinguish nuclei cluster from the other clusters obtained by K-means, and eliminate false positives in nuclei cluster, which are not nuclei. In order to compare and evaluate the performance of the proposed segmentation algorithm in terms of time and cost efficiency, K-Means is preferred because of its common usage. Expert evaluation is declared as ground truth for determining the accuracy of the results. The experiments are performed on 60 healthy and 60 damaged kidney, and 60 healthy and 60 damaged liver tissue images. The evaluations show that the proposed algorithm can effectively segment nuclei. The comparison results also demonstrate that the deviation between proposed algorithm and the expert is 2%, while the deviation between K-Means and expert is 5%.

H&E ile Boyanmış Histopatolojik Doku İmgeleri için Yeni Bir Olasılıksal Hücre Çekirdeği Bölütleme Algoritması

Bu çalışmada, H&E boyalı histopatolojik doku imgelerindeki hücre çekirdeklerini bölütlemek için yeni, hızlı ve doğru bir bölütleme algoritması önerilmiştir. Önerilen algoritma ön işlem, son işlem, herhangi bir manuel parametre veya eşik değeri gerektirmez. Algoritma, RGB renk uzayında olan imgelerdeki piksellerin renk değerinin olasılıksal ve istatistiksel özelliklerini kullanır ve piksellerin herhangi bir çekirdeğin bir parçası olup olmadığını otomatik olarak hesaplanan eşik değeri kullanarak belirler. Algoritma, zaman verimliliği sağlar ve bölütleme genel maliyetini düşürür. Ayrıca, K-ortalama sonucu elde edilen kümeler içerisinden hücre çekirdeklerini içeren kümenin belirlenmesi ve hücre çekirdekleri kümesi içerisinde bulunan ancak hücre çekirdeği olmayan yanlış pozitiflerin elimine edilmesi için iki algoritma daha önerilmiştir. Önerilen bölütleme algoritmasının zaman ve maliyet verimliliği açısından performansını karşılaştırmak ve değerlendirmek için, yaygın kullanımı nedeniyle K-ortalama bölütleme algoritması tercih edilmiştir. Sonuçların doğruluğunu belirlenmesi için uzman değerlendirmesi baz alınmıştır. Deneyler 60 sağlıklı ve 60 hasarlı böbrek ile 60 sağlıklı ve 60 hasarlı karaciğer görüntüsü üzerinde gerçekleştirilmiştir. Değerlendirmeler, önerilen algoritmanın çekirdekleri etkili bir şekilde bölütleyebildiğini göstermektedir. Karşılaştırma sonuçları ayrıca önerilen algoritma ile uzman arasındaki sapmanın %2 olduğunu, K-Ortalama ve uzman arasındaki sapmanın ise %5 olduğunu göstermektedir.

PDF

___

[1] Mills, S.E., “Histology for Pathologists”, Wolters Kluwer Health/Lippincott Williams & Wilkins, Philadelphia, (2012).

[2] Suvarna, K.S., Layton, C. and Bancroft, J.D., “Bancroft’s Theory and Practice of Histological Techniques”, Elsevier Health Sciences UK, (2012).

[3] He, L., Long, L.R., Antani, S. and Thoma, G., “Computer assisted diagnosis in histopathology”, Seq. Genome Anal. Methods Appl., 271–287, (2010).

[4] Fox, H., “Is H&E morphology coming to an end?” J. Clin. Pathol., 53: 38–40, (2000).

[5] Murphy, D.B. and Davidson, M.W., “Fundamentals of Light Microscopy and Electronic Imaging”, WileyBlackwell, Hoboken, N.J., (2012)

[6] Thomas, G.D., Dixon, M.F., Smeeton, N.C. and Williams, N.S., “Observer variation in the histological grading of rectal carcinoma”, J. Clin. Pathol., 36: 385–91, (1983).

[7] Metter, G.E., Nathwani, B.N., Burke, J.S., Winberg, C.D., Mann, R.B., Barcos, M., Kjeldsberg, C.R., Whitcomb, C.C., Dixon, D.O. and Miller, T.P., “Morphological subclassification of follicular lymphoma: variability of diagnoses among hematopathologists, a collaborative study between the Repository Center and Pathology Panel for Lymphoma Clinical Studies”, J. Clin. Oncol., 3: 25– 38, (1985).

[8] Dick, F., VanLier, S., Banks, P., Frizzera, G., Witrak, G., Gibson, R., Everett, G., Schuman, L., Isacson, P., O’Conor, G., Cantor, K., Blattner, W. and Blair, A., “Use of the Working Formulation for Non-Hodgkin’s Lymphoma in Epidemiologic Studies: Agreement Between Reported Diagnoses and a Panel of Experienced Pathologists”, J. Natl. Cancer Inst., 78: 1137–44, (1987).

[9] Chan, W.C., Armitage, J.O., Gascoyne, R., Connors, J., Close, P., Jacobs, P., Norton, A., Lister, T.A., Pedrinis, E., Cavalli, F. and others, “A clinical evaluation of the International Lymphoma Study Group classification of non-Hodgkin’s lymphoma”, Blood, 89: 3909–3918, (1997).

[10] Serin, F., Ertürkler, M. and Gül, M., “K-nearest unrepeatable cell graph model of histopathological tissue image”, 2015 23nd Signal Processing and Communications Applications Conference (SIU), 2585–8, (2015).

[11] Serin, F., Erturkler, M. and Gul, M., “A novel overlapped nuclei splitting algorithm for histopathological images”, Comput. Methods Programs Biomed., 151: 57–70, (2017).

[12] Gunduz, C., Yener, B. and Gultekin, S.H., “The cell graphs of cancer”, Bioinformatics, 20: i145–51, (2004).

[13] Ng, H.P., Ong, S.H., Foong, K.W.C., Goh, P.S. and Nowinski, W.L., “Medical image segmentation using Kmeans clustering and improved watershed algorithm”, 2006 IEEE Southwest Symposium on Image Analysis and Interpretation, 61–65, (2006).

[14] Petushi, S., Garcia, F.U., Haber, M.M., Katsinis, C. and Tozeren, A., “Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer”, BMC Med. Imaging, 6: 14, (2006).

[15] Bilgin, C., Demir, C., Nagi, C. and Yener, B., “CellGraph Mining for Breast Tissue Modeling and Classification”, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 5311–4, (2007).

[16] Gurcan, M.N., Boucheron, L.E., Can, A., Madabhushi, A., Rajpoot, N.M. and Yener, B., “Histopathological image analysis: A review”, Biomed. Eng. IEEE Rev. In, 2: 147–171, (2009).

[17] Kothari, S., Chaudry, Q. and Wang, M.D., “Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques”, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE, 795–8, (2009).

[18] Bilgin, C.C., Bullough, P., Plopper, G.E. and Yener, B., “ECM-aware cell-graph mining for bone tissue modeling and classification”, Data Min. Knowl. Discov., 20: 416– 438, (2010).

[19] Malu, G., Balakrishnan, K. and Bodhey, N.K., “Area and volume calculation of necrotic tissue regions of heart using interpolation”, 2011 International Conference on Emerging Trends in Electrical and Computer Technology (ICETECT), 728–30, (2011).

[20] Baykara, M., Erturkler, M., Gul, M. and Harputluoglu, M., “Karaciğer Dokusundaki Nekroz Alanın Doku Tabanlı Bölütleme Kullanılarak Belirlenmesi ve Nicemlenmesi”, Akıllı Sistemlerde Yenilikler ve Uygulamaları Sempozyumu (ASYU), Trabzon/Turkey, (2012).

[21] Ozseven, T., Erturkler, M., Nurmuhammed, M., Gul, M. and Harputluoglu, M., “Quantifying the necrotic areas on liver tissues using support vector machine (SVM) algorithm and Gabor filters”, 2012 International Symposium on Innovations in Intelligent Systems and Applications (INISTA), 1–5, (2012).

[22] Serin, F., Erturkler, M., Gul, M. and Yigitcan, B., “NonAlkolik Yağlı Karaciğer Hastalığında Karaciğerdeki Yağ Vakuolleri Oranının Hesaplanması”, Akıllı Sistemlerde Yenilikler ve Uygulamaları Sempozyumu (ASYU), 306– 10, (2012).

[23] Serin, F., Erturkler, M., Gul, M. and Yigitcan, B., “Investigating the effects of melatonin and resveratrol agents on non-alcoholic fatty liver disease”, Glob. J. Technol., 3, (2013).

[24] Skodras, A., Giannarou, S., Fenwick, M., Franks, S., Stark, J. and Hardy, K., “Object recognition in the ovary: Quantification of oocytes from microscopic images”, 2009 16th International Conference on Digital Signal Processing, 1–6, (2009).

[25] Chang, W.-Y., Huang, A., Yang, C.-Y., Lee, C.-H., Chen, Y.-C., Wu, T.-Y. and Chen, G.-S., “Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study”, PLOS ONE, 8: e76212, (2013).

[26] Veta, M., Pluim, J.P.W., van Diest, P.J. and Viergever, M.A., “Breast Cancer Histopathology Image Analysis: A Review”, IEEE Trans. Biomed. Eng., 61: 1400–11, (2014).

[27] Wang, S., Burtt, K., Turkbey, B., Choyke, P., Summers, R.M., Wang, S., Burtt, K., Turkbey, B., Choyke, P. and Summers, R.M., “Computer Aided-Diagnosis of Prostate Cancer on Multiparametric MRI: A Technical Review of Current Research, Computer Aided-Diagnosis of Prostate Cancer on Multiparametric MRI: A Technical Review of Current Research”, BioMed Res. Int. BioMed Res. Int., 2014, 2014: e789561, (2014).

[28] Firmino, M., Morais, A.H., Mendoça, R.M., Dantas, M., Hekis, H. and Valentim, R., “Computer-aided detection system for lung cancer in computed tomography scans: Review and future prospects”, Biomed Eng Online, 13: 1–16, (2014).

[29] Otsu, N., “A threshold selection method from gray-level histograms”, Automatica, 11: 23–27, (1975).

[30] Adams, R. and Bischof, L., “Seeded region growing”, Pattern Anal. Mach. Intell. IEEE Trans. On, 16: 641– 647, (1994).

[31] Patil, D.D. and Deore, S.G., “Medical image segmentation: a review”, Int. J. Comput. Sci. Mob. Comput., 2: 22–27, (2013).

[32] Zhang, C., Xiao, X., Li, X., Chen, Y.-J., Zhen, W., Chang, J., Zheng, C. and Liu, Z., “White Blood Cell Segmentation by Color-Space-Based K-Means Clustering”, Sensors, 14: 16128–47, (2014).

[33] Zhang, D.-Q. and Chen, S.-C., “A novel kernelized fuzzy c-means algorithm with application in medical image segmentation”, Artif. Intell. Med., 32: 37–50, (2004).

[34] Chuang, K.-S., Tzeng, H.-L., Chen, S., Wu, J. and Chen, T.-J., “Fuzzy c-means clustering with spatial information for image segmentation”, Comput. Med. Imaging Graph., 30: 9–15, (2006).

[35] Kong, H., Belkacem-Boussaid, K. and Gurcan, M., “Cell nuclei segmentation for histopathological image analysis”, SPIE Medical Imaging, International Society for Optics and Photonics, 79622R–79622R, (2011).

[36] Zhang, X., Xing, F., Su, H., Yang, L. and Zhang, S., “High-throughput histopathological image analysis via robust cell segmentation and hashing”, Med. Image Anal., 26: 306–15, (2015).

[37] Xu, Y., Zhu, J.-Y., Chang, E.I.-C., Lai, M. and Tu, Z., “Weakly supervised histopathology cancer image segmentation and classification”, Med. Image Anal., 18: 591–604, (2014).

[38] Wienert, S., Heim, D., Saeger, K., Stenzinger, A., Beil, M., Hufnagl, P., Dietel, M., Denkert, C. and Klauschen, F., “Detection and segmentation of cell nuclei in virtual microscopy images: a minimum-model approach”, Sci. Rep., 2: 503, (2012).

[39] Al-Kofahi, Y., Lassoued, W., Lee, W. and Roysam, B., “Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images”, IEEE Trans. Biomed. Eng., 57: 841–52, (2010).

[40] Kecheril, S.S., Venkataraman, D., Suganthi, J. and Sujathan, K., “Automated lung cancer detection by the analysis of glandular cells in sputum cytology images using scale space features”, Signal Image Video Process., 9: 851–63, (2013).

[41] Kothari, S., Phan, J.H., Stokes, T.H. and Wang, M.D., “Pathology imaging informatics for quantitative analysis of whole-slide images”, J. Am. Med. Inform. Assoc., 20: 1099–108, (2013).

[42] Ray, S. and Turi, R.H., “Determination of number of clusters in k-means clustering and application in colour image segmentation”, Proceedings of the 4th international conference on advances in pattern recognition and digital techniques, Calcutta, India, 137– 143, (1999).

[43] https://www.mathworks.com/help/images/color-basedsegmentation-using-k-means-clustering.html, “ColorBased Segmentation Using K-Means Clustering - MATLAB & Simulink Example”, (2017).

[44] He, L., Chao, Y. and Suzuki, K., “A Run-Based TwoScan Labeling Algorithm”, IEEE Trans. Image Process., 17: 749–56, (2008).