Validation of various adaptive threshold methods of segmentation applied to follicular lymphoma digital images stained with 3,3’-Diaminobenzidine&Haematoxylin

Diagnostic Pathology

Marylene Lejeune¹  Lukasz Witkowski²  Ramon Bosch¹  Carlos Lopez¹  Lukasz Roszkowiak²  Anna Korzynska² 

[1] , Molecular Biology and Research Section Hospital de Tortosa Verge de la Cinta, C Esplanetes 14, Tortosa, Spain;, Nalecz Institute of Biocybernetics and Biomedical Engineering, Ks. Trojdena 4 Str., Warsaw, Poland

关键词: Morphometry;    Pathology;    Nuclear quantification;    Immunohistochemistry;    Lymphoma;   

Others  :  807337
DOI  :  10.1186/1746-1596-8-48

 received in 2012-12-07, accepted in 2013-02-28,  发布年份 2013

【 摘 要 】

The comparative study of the results of various segmentation methods for the digital images of the follicular lymphoma cancer tissue section is described in this paper. The sensitivity and specificity and some other parameters of the following adaptive threshold methods of segmentation: the Niblack method, the Sauvola method, the White method, the Bernsen method, the Yasuda method and the Palumbo method, are calculated. Methods are applied to three types of images constructed by extraction of the brown colour information from the artificial images synthesized based on counterpart experimentally captured images. This paper presents usefulness of the microscopic image synthesis method in evaluation as well as comparison of the image processing results. The results of thoughtful analysis of broad range of adaptive threshold methods applied to: (1) the blue channel of RGB, (2) the brown colour extracted by deconvolution and (3) the ’brown component’ extracted from RGB allows to select some pairs: method and type of image for which this method is most efficient considering various criteria e.g. accuracy and precision in area detection or accuracy in number of objects detection and so on. The comparison shows that the White, the Bernsen and the Sauvola methods results are better than the results of the rest of the methods for all types of monochromatic images. All three methods segments the immunopositive nuclei with the mean accuracy of 0.9952, 0.9942 and 0.9944 respectively, when treated totally. However the best results are achieved for monochromatic image in which intensity shows brown colour map constructed by colour deconvolution algorithm. The specificity in the cases of the Bernsen and the White methods is 1 and sensitivities are: 0.74 for White and 0.91 for Bernsen methods while the Sauvola method achieves sensitivity value of 0.74 and the specificity value of 0.99. According to Bland-Altman plot the Sauvola method selected objects are segmented without undercutting the area for true positive objects but with extra false positive objects. The Sauvola and the Bernsen methods gives complementary results what will be exploited when the new method of virtual tissue slides segmentation be develop.

Virtual Slides

The virtual slides for this article can be found here: slide 1: http://diagnosticpathology.slidepath.com/dih/webViewer.php?snapshotId=13617947952577 webcite and slide 2: http://diagnosticpathology.slidepath.com/dih/webViewer.php?snapshotId=13617948230017 webcite.

【 授权许可】

   
2013 Korzynska et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

【 参考文献 】

• [1]Roux L, Tutac A, Lomenie N, Balensi D, Racoceanu D, all: A cognitive virtual microscopic framework for knowlege-based exploration of large microscopic images in breast cancer histopathology. In Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. Minneapolis, MN: IEEE; 2009:3697-3702.
• [2]Grala B, Markiewicz T, Kozlowski W, Osowski S, Slodkowska J, Papierz W: New automated image analysis method for the assessment of Ki-67 labeling index in meningiomas. Folia Histochemica et Cytobiologica 2010, 47(4):587-592.
• [3]Swerdlow S, for Research on Cancer IA: WHO Classification of Tumours of Haematopoietic and Lymphoid Tissues.. : World Health Organization classification of tumours, International Agency for Research on Cancer; 2008. [http://www.ncbi.nlm.nih.gov/nlmcatalog/101477951 webcite]. [ISBN-13: 9789283224310; ISBN-10: 9283224310]
• [4]Rojo M, Bueno G, Slodkowska J: Review of imaging solutions for integrated quantitative immunohistochemistry in the Pathology daily practice. Folia Histochemica et Cytobiologica 2010, 47(3):349-354. [http://czasopisma.viamedica.pl/fhc/article/view/4337 webcite]
• [5]Seidal T, Balaton AJ, Battifora H: Interpretation and Quantification of Immunostains. Am J Surg Pathol 2001, 25(9):1204-1207. [http://journals.lww.com/ajsp/Fulltext/2001/09000/Interpretation_and_Quantification_ of_Immunostains.13.aspx webcite]
• [6]Yaziji H, Barry T: Diagnostic Immunohistochemistry: What can Go Wrong? Adv Anat Pathol 2006, 13(5):238-246. [http://journals.lww.com/anatomicpathology/Fulltext/2006/09000/Diagnostic_ Immunohistochemistry__What_can_Go.3.aspx webcite]
• [7]Du X, Dua S: Segmentation of fluorescence microscopy cell images using unsupervised mining. Open Med Inform J 2010, 4:41-49. [http://europepmc.org/abstract/MED/21116323 webcite]
• [8]Markiewicz T, Wisniewski P, Osowski S, Patera J, Kozlowski W, Koktysz R: Comparative analysis of methods for accurate recognition of cells through nuclei staining of Ki-67 in neuroblastoma and estrogen/progesterone status staining in breast cancer. Anal Quant Cytol Histol 2009, 31:49-62. [http://www.ncbi.nlm.nih.gov/pubmed/19320193 webcite]
• [9]Lopez C, Lejeune M, Salvado MT, Escriva P, Bosch R, Pons L, Alvaro T, Roig J, Cugat X, Baucells J, Jaen J: Automated quantification of nuclear immunohistochemical markers with different complexity. Histochem Cell Biol 2008, 129:379-387. [http://dx.doi.org/10.1007/s00418-007-0368-5 webcite]
• [10]Pietka E, Kawa J, Spinczyk D, Badura P, Wieclawek W, Czajkowska J, Rudzki M: Role of radiologists in CAD life-cycle. Eur J Radiol 2011, 78(2):225-233. [http://www.sciencedirect.com/science/article/pii/S0720048X09005087 webcite]
• [11]Korzynska A, Zychowicz M: A method of estimation of the cell doubling time on basis of the cell culture monitoring data. Biocybern Biomed Eng 2008, 28(4):75-82. [http://ibib.waw.pl/bbe/bbefulltext/BBE_28_4_075_FT.pdf webcite]
• [12]Choi HJ, Choi IH, Cho NH, Choi HK: Color image analysis for quantifying renal tumor angiogenesis. Anal Quant Cytol Histol 2005, 27:43-51. [http://www.ncbi.nlm.nih.gov/pubmed/15794451 webcite]
• [13]Comaniciu D, Meer P: Cell image segmentation for diagnostic pathology. In Advanced Algorithmic Approaches to Medical Image Segmentation. Advances in Computer Vision and Pattern Recognition. London: Springer; 2002:541-558.
• [14]Markiewicz T, Osowski S, Patera J, Kozlowski W: Image processing for accurate cell recognition and count on histologic slides. Anal Quant Cytol Histol / Int Acad Cytology [and] Am Soc Cytol 2006, 28(5):281-291. [http://www.ncbi.nlm.nih.gov/pubmed/17067010 webcite]
• [15]Kayser K, Gortler J, Goldmann T, Vollmer E, Hufnagl P, Kayser G: Image standards in tissue-based diagnosis (Diagnostic Surgical Pathology). Diagn Pathol 2008, 3:17. [http://www.diagnosticpathology.org/content/3/1/17 webcite] BioMed Central Full Text
• [16]Gil J, Wu HS: Applications of image analysis to anatomic pathology: realities and promises. Cancer Investig 2003, 21(6):950-959.
• [17]Gil J, Wu H, Wang BY: Image analysis and morphometry in the diagnosis of breast cancer. Microsc Res Tech 2002, 59(2):109-118.
• [18]Klapper W, Hoster E, Determann O, Oschlies I, Laak J, Berger F, Bernd HW, Cabecadas J, Campo E, Cogliatti S, Hansmann M, Kluin P, Kodet R, Krivolapov Y, Loddenkemper C, Stein H, Muller P, Barth T, MÃller-Hermelink K, Rosenwald A, Ott G, Pileri S, Ralfkiaer E, Rymkiewicz G, Krieken J, Wacker H, Unterhalt M, Hiddemann W, Dreyling M: Ki-67 as a prognostic marker in mantle cell lymphoma-consensus guidelines of the pathology panel of the European MCL Network. J. Hematopathol 2009, 2:103-111.
• [19]Lehmussola A, Ruusuvuori P, Selinummi J, Huttunen H, Yli-Harja O: Computational framework for simulating fluorescence microscope images with cell populations. Med Imaging, IEEE Trans 2007, 26(7):1010-1016.
• [20]Lehmussola A, Ruusuvuori P, Selinummi J, Rajala T, Yli-Harja O: Synthetic images of high-throughput microscopy for validation of image analysis methods. Proc IEEE 2008, 96(8):1348-1360.
• [21]Kayser K, Radziszowski D, Bzdyl P, Sommer R, Kayser G: Towards an automated virtual slide screening: theoretical considerations and practical experiences of automated tissue-based virtual diagnosis to be implemented in the Internet. Diagn Pathol 2006, 1:1-8. BioMed Central Full Text
• [22]Kayser G, Radziszowski D, Bzdyl P, Sommer R, Kayser K: Theory and implementation of an electronic, automated measurement system for images obtained from immunohistochemically stained slides. Anal Quant Cytol Histol 2006, 28:27-38. [http://pubget.com/paper/16566277 webcite]
• [23]Markiewicz T: Using MATLAB software with Tomcat server and Java platform for remote image analysis in pathology. Diagn Pathol 2011, 6:1-7. BioMed Central Full Text
• [24]Bueno G, Gonzalez R, Deniz O, Garcia-Rojo M, Gonzalez-Garcia J, Fernandez-Carrobles M, Vallez N, Salido J: A parallel solution for high resolution histological image analysis. Comput Methods Programs Biomed 2012, 108:388-401. [http://www.sciencedirect.com/science/article/pii/S016926071200082X webcite]
• [25]Korzynska A, Iwanowski M: Segmentation of moving cells in bright field and Epi-Fluorescent microscopic image sequences. In Computer Vision and Graphics, Volume 6374 of Lecture Notes in Computer Science. Edited by Bolc L, Tadeusiewicz R, Chmielewski L, Wojciechowski K. Berlin Heidelberg: Springer; 2010:401-410.
• [26]Korzynska A, Hoppe A, Strojny W, Wertheim D: Investigation of a combined texture and contour method for segmentation of light microscopy cell images. In Proceedings of the Second IASTED International Conference on Biomedical Engineering, Volume 417 Edited by Tilg B. 2004, 234-239. [http://www.actapress.com/Abstract.aspx?paperId=16336 webcite]
• [27]Korzynska A, Iwanowski M: Multistage morphological segmentation of bright-field and fluorescent microscopy images. Opto-Electron Rev 2012, 20(2):174-186.
• [28]Bartels P, Montironi R, Duval da Silva V, Hamilton P, Thompson D, Vaught L, Bartels H: Tissue architecture analysis in prostate cancer and its precursors: an innovative approach to computerized histometry. Eur Urol 1999, 35(5-6):484-491.
• [29]Schulerud H, Kristensen GB, Liestol K, Vlatkovic L, Reith A, Albregtsen F, Danielsen HE: A review of caveats in statistical nuclear image analysis. Anal Cell Pathol 1998, 16(2):63-82. [http://iospress.metapress.com/content/6159KHY5B2WPJN0Y webcite]
• [30]Koprowski R, Wrobel Z: The cell structures segmentation. In Computer Recognition Systems, Volume 30 of Advances in Soft Computing. Edited by Kurzynski M, Puchala E, Wozniak M, Zolnierek A. Berlin Heidelberg: Springer; 2005:569-576.
• [31]Korzynska A, Neuman U, Lopez C, Lejeun M, Bosch R: The method of immunohistochemical images standardization. In Image Processing and Communications Challenges 2, Volume 84 of Advances in Intelligent and Soft Computing. Edited by Choras R. Berlin Heidelberg: Springer; 2010:213-221.
• [32]Tadrous P: Digital stain separation for histological images. J Microsc 2010, 240(2):164-172.
• [33]Ruifrok A, Johnston D: Quantification of histochemical staining by color deconvolution. Anal Quant Cytol Histol 2001, 23(4):291-299. [http://europepmc.org/abstract/MED/11531144 webcite]
• [34]Di Cataldo S, Ficarra E, Acquaviva A, Macii E: Automated segmentation of tissue images for computerized IHC analysis. Comput Methods Programs Biomed 2010, 100:1-15. [http://www.sciencedirect.com/science/article/pii/S0169260710000337 webcite]
• [35]Di Cataldo S, Ficarra E, Acquaviva A, Macii E: Achieving the way for automated segmentation of nuclei in cancer tissue images through morphology-based approach: A quantitative evaluation. Comput Med Imaging Graph 2010, 34(6):453-461. [http://www.sciencedirect.com/science/article/pii/S089561110900158X webcite]
• [36]Kuse M, Sharma T, Gupta S: A classification scheme for lymphocyte segmentation in H&E stained histology images. In Recognizing Patterns in Signals, Speech, Images and Videos, Volume 6388 of Lecture Notes in Computer Science. Edited by Unay D, Cataltepe Z, Aksoy S.. Berlin Heidelberg: Springer; 2010:235-243.
• [37]White JM, Rohrer GD: Image thresholding for optical character recognition and other applications requiring character image extraction. IBM J Res Dev 1983, 27(4):400-411.
• [38]Bernsen J: Dynamic thresholding of gray-level images. ICPR’86: International Conference on Pattern Recognition 1986. [http://libra.msra.cn/Publication/2042781/dynamic-thresholding-of-gray-level-images webcite]
• [39]Yasuda Y, Dubois M, Huang T: Data compression for check processing machines. Proc IEEE 1980, 68(7):874-885.
• [40]Neuman U, Korzynska A, Lopez C, Lejeune M: Segmentation of stained lymphoma tissue section images. In Inform Technol Biomed, Volume 69 of Advances in Intelligent and Soft Computing. Edited by Pietka E, Kawa J. Berlin Heidelberg: Springer; 2010:101-113.
• [41]Pham DL, Xu C, Prince JL: A survey of current methods in medical image segmentation. Annu Rev Biomed Eng 2000, 2:315-337. [http://www.annualreviews.org/doi/abs/10.1146/annurev.bioeng.2.1.315 webcite] [PMID: 11701515]
• [42]Fu K, Mui J: A survey on image segmentation. Patt Recognit 1981, 13:3-16. [http://www.sciencedirect.com/science/article/pii/0031320381900285 webcite]
• [43]Sezgin M, Sankur B: Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 2004, 13:146-168.
• [44]Niblack W: An Introduction to Image Processing. Englewood Cliffs: Prentice-Hall International; 1986. [http://books.google.pl/books?id=XOxRAAAAMAAJ webcite]
• [45]Sauvola J, Pietikainen M: Adaptive document image binarization. Patt Recognit 2000, 33(2):225-236. [http://www.sciencedirect.com/science/article/pii/S0031320399000552 webcite]
• [46]Siva P, Hulls C: Dynamic segmentation of small image windows for visual servoing. In Mechatronics and Automation, 2005 IEEE International Conference, Volume 2. Niagara Falls, Canada: IEEE Service Center; 2005:643-648.
• [47]Palumbo PW, Swaminathan P, Srihari SN: Document image binarization: evaluation of algorithms. Proc SPIE Appl Digit Image Process IX 1986, 697(278):278-285.
• [48]Alvaro T, Lejeune M, Salvado MT, Lopez C, Jaen J, Bosch R, Pons LE: Immunohistochemical patterns of reactive microenvironment are associated with clinicobiologic behavior in follicular lymphoma patients. J Clin Oncolog 2006, 24(34):5350-5357. [http://jco.ascopubs.org/content/24/34/5350.abstract webcite]
• [49]Nieniewski M: Morfologia matematyczna w przetwarzaniu obrazow. Problemy Wspolczesnej Nauki: Informatyka, Akademicka Ofic. Wydawnicza PLJ; 1998. [http://books.google.pl/books?id=vAk webcite∖_twAACAAJ]
• [50]Iwanowski M: Metody morfologiczne w przetwarzaniu obrazow cyfrowych. : Akademicka Oficyna Wydawnicza EXIT; 2009. [https://sites.google.com/site/metodymorfologiczne/ webcite]