Digital Image Content and Context Information in Tissue-based Diagnosis

  • Klaus Kayser Charite - Berlin
  • Stephan Borkenfeld IAT Heidelberg
  • Gian Kayser Institut für Klinische Pathologie Universitätsklinikum Freiburg

Abstract

Background and definitions: Image content information (ICI) comprises the information that an external observer can extract solely from the image itself, i.e., without additional notifications (labels, classification, etc.). Image analysis is the procedure to extract meaningful information from the image. It is an important issue in digital pathology and the prerequisite to implement algorithms of diagnosis assistance. Meaningful information (IMI) comprises the information which the observer can understand or which is transformed into an information related reaction. It corresponds to regions of interest (ROI). Pixel and gray value create all information of a digitized image. The spatial distribution of pixel gray values is called texture. Objects are externally defined pixel clusters; their spatial distribution forms a structure.
Living organisms are limited spatially circumscribed systems which are included in external environment and possess an unstable inner volume. Development and limited stability of these open thermodynamic systems are guaranteed by their environment and additional not overlapping inner equivalent systems, which build the so - called hierarchically order of structures. Interaction between objects might alter appearance, development, appearance of new or disappearance of existing objects. The interactions are commonly called functions. They are equivalent to communication and based upon different ‘carriers’ such as electromagnetic signals, macromolecules, salt concentrations, etc.
Detection and description of structures depend upon the observer time. The application of visible macromolecules which bind to boundaries of structures might detect and forecast changes of the boundaries, i.e. structures. The intensity of the visibility and its distribution reflect to the thermodynamic affinity.  Detailed analysis of gray value intensities might allow an insight in thermodynamic properties of structures.
Context is defined as information which can be derived from and added to object and structure related information, and, vice versa, might be applied to predefine the observer information capability which is needed to understand the ‘meaning’ of an image, or to select the most capable observer.
Perspectives: The described algorithm is an appropriate tool to combine computerized image content information with its computerized ‘observer’ system. It will be able to measure, acquire, understand and to transfer image content information in an adequate reaction, i.e. diagnosis.


 Tuberculosis


Fibrosis

References

1. Kayser, K., et al., History and structures of telecommunication in pathology, focusing on open access platforms. Diagn Pathol. 6: p. 110.
2. Kayser, K., Quantification of virtual slides: Approaches to analysis of content-based image information. J Pathol Inform. 2: p. 2.
3. Kayser, K., et al., Grid computing in image analysis. Diagn Pathol. 6 Suppl 1: p. S12.
4. Achille, A. and S. Soatto, Information Dropout: Learning Optimal Representations Through Noisy Computation. IEEE Trans Pattern Anal Mach Intell, 2018.
5. Aggarwal, H.K., M.P. Mani, and M. Jacob, MoDL: Model Based Deep Learning Architecture for Inverse Problems. IEEE Trans Med Imaging, 2018.
6. Kayser, K., et al., Texture and object related image analysis in microscopic images. Diagnostic Pathology, 2015. 1(14).
7. Kayser, K., et al., To be at the right place at the right time. Diagn Pathol. 6: p. 2-9.
8. Al-Kofahi, Y., et al., A deep learning-based algorithm for 2-D cell segmentation in microscopy images. BMC Bioinformatics, 2018. 19(1): p. 365.
9. Bellenberg, S., et al., Automated Microscopic Analysis of Metal Sulfide Colonization by Acidophilic Microorganisms. Appl Environ Microbiol, 2018. 84(20).
10. Nelson, A.J. and S.T. Hess, Molecular imaging with neural training of identification algorithm (neural network localization identification). Microsc Res Tech, 2018.
11. Kayser, G., et al., Towards an automated morphological classification of histological images of common lung carcinomas. Elec J Pathol Histol, 2002. 8: p. 022-03.
12. Kayser, K., et al., Correlation of expression of binding sites for synthetic blood group A-, B- and H-trisaccharides and for sarcolectin with survival of patients with bronchial carcinoma. Eur J Cancer, 1994. 30A(5): p. 653-7.
13. Kayser, K., et al., Cell type-dependent alterations of binding of synthetic blood group antigen-related oligosaccharides in lung cancer. Glycoconj J, 1994. 11(4): p. 339-44.
14. Kayser, K. and H.J. Gabius, The application of thermodynamic principles to histochemical and morphometric tissue research: principles and practical outline with focus on the glycosciences. Cell Tissue Res, 1999. 296(3): p. 443-55.
15. Kayser, K., et al., Alterations in human lung parenchyma after cytostatic therapy. Apmis, 1991. 99(2): p. 121-8.
16. Kayser, K., S. Borkenfeld, and G. Kayser, How to introduce virtual microscopy (VM) in routine diagnostic pathology: constraints, ideas, and solutions. Anal Cell Pathol (Amst). 35(1): p. 3-10.
17. Kayser, K., et al., Interactive and automated application of virtual microscopy. Diagn Pathol. 6 Suppl 1: p. S10.
18. Kayser, K. and H. Hoffgen, Pattern recognition in histopathology by orders of textures. Med Inform (Lond), 1984. 9(1): p. 55-9.
19. Kayser, K., et al., Phenotype and genotype associations of lung carcinoma with atypical adenomatoid hyperplasia, squamous cell dysplasia, and chromosome alterations in non-neoplastic bronchial mucosa. Rom J Morphol Embryol, 2005. 46(1): p. 5-10.
20. Gabius, H.J., et al., Reverse lectin histochemistry: design and application of glycoligands for detection of cell and tissue lectins. Histol Histopathol, 1993. 8(2): p. 369-83.
21. Kayser, K., et al., Preneoplasia-associated expression of calcyclin and of binding sites for synthetic blood group A/H trisaccharide--exposing neoglycoconjugates in human lung. Cancer Biochem Biophys, 1997. 15(4): p. 235-43.
22. Kayser, K., et al., Analysis of soft tissue tumors by an attributed minimum spanning tree. Anal Quant Cytol Histol, 1991. 13(5): p. 329-34.
23. Kayser, K., et al., Alteration of human lung parenchyma associated with primary biliary cirrhosis. Zentralbl Pathol, 1993. 139(4-5): p. 377-80.
24. Kayser, K., et al., Application of computer-assisted morphometry to the analysis of prenatal development of human lung. Anat Histol Embryol, 1997. 26(2): p. 135-9.
25. Kayser, K., et al., Biotinylated epidermal growth factor: a useful tool for the histochemical analysis of specific binding sites. Histochem J, 1990. 22(8): p. 426-32.
26. Krylow, G. Advances in Synergetics. in First Workshop on Mind, Brain and Neurocomputers. 1994. Minks, Belarus: Belarusian State University Press.
27. Cheng, H.C., et al., Deep-learning-assisted Volume Visualization. IEEE Trans Vis Comput Graph, 2018.
28. Funke, J., et al., Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction. IEEE Trans Pattern Anal Mach Intell, 2018.
29. Fuyong, X., et al., Deep Learning in Microscopy Image Analysis: A Survey. IEEE Trans Neural Netw Learn Syst, 2018. 29(10): p. 4550-4568.
30. Kayser, G., et al., Numerical and structural centrosome aberrations are an early and stable event in the adenoma-carcinoma sequence of colorectal carcinomas. Virchows Arch, 2005. 447(1): p. 61-5.
31. Kayser, K., et al., How to measure image quality in tissue-based diagnosis (diagnostic surgical pathology). Diagn Pathol, 2008. 3 Suppl 1: p. S11.
32. Kayser, K., et al., Texture- and object-related automated information analysis in histological still images of various organs. Anal Quant Cytol Histol, 2008. 30(6): p. 323-35.
33. Kayser, K., G. Kayser, and K. Metze, The concept of structural entropy in tissue-based diagnosis. Anal Quant Cytol Histol, 2007. 29(5): p. 296-308.
34. Kayser, K., et al., Expression of endogenous lectins (galectins, receptors for ABH-epitopes) and the MIB-1 antigen in esophageal carcinomas and their syntactic structure analysis in relation to post-surgical tumor stage and lymph node involvement. Anticancer Res, 2001. 21(2B): p. 1439-44.
35. Kayser, K., et al., Combined analysis of tumor growth pattern and expression of endogenous lectins as a prognostic tool in primary testicular cancer and its lung metastases. Histol Histopathol, 2003. 18(3): p. 771-9.
36. Kayser, K. and O. Hagemeyer, Stage related morphometry of sarcoid granulomas and inflammatory cell types in broncho-alveolar lavage. Anal Cell Pathol, 1991. 3(6): p. 335-42.
37. Pincus, S.M., Approximate entropy as a measure of system complexity. Proc Natl Acad Sci U S A, 1991. 88(6): p. 2297-2301.
38. Shannon, C., A mathematical theory of communication. The Bell System Technical Journal 1948. 27(3): p. 379-423.
39. Eigen, M., Selforganization of matter and the evolution of biological macromolecules. Naturwissenschaften, 1971. 58: p. 465-523.
40. Gibbs, J., Elementary Principles in statistical Mechanics developed with especial reference to the rational. Foundation of Thermodynamics 1902, New York: Yale University Press.
41. Tsallis, C., Entropic nonextensivity: a possible measure of complexity. Chaos, Solitons and Fractals 2002. 13(371-391).
42. Beretta, G.P., Steepest entropy ascent model for far-nonequilibrium thermodynamics: unified implementation of the maximum entropy production principle. Phys Rev E Stat Nonlin Soft Matter Phys. 90(4): p. 042113.
43. Gunduz, G. and U. Gunduz, The mathematical analysis of the structure of some songs Physica A, 2005. 357: p. 565-592.
44. Kayser, K. and H.J. Gabius, Graph theory and the entropy concept in histochemistry. Theoretical considerations, application in histopathology and the combination with receptor-specific approaches. Prog Histochem Cytochem, 1997. 32(2): p. 1-106.
45. Rocha, L.B., et al., Shannon's entropy and fractal dimension provide an objective account of bone tissue organization during calvarial bone regeneration. Microsc Res Tech, 2008. 71(8): p. 619-25.
46. Bento, E.P., et al., Third law of thermodynamics as a key test of generalized entropies. Phys Rev E Stat Nonlin Soft Matter Phys, 2015. 91(2): p. 022105.
47. Lima, J.A., R. Silva, and A.R. Plastino, Nonextensive thermostatistics and the H theorem. Phys Rev Lett, 2001. 86(14): p. 2938-41.
48. Mayoral, E. and A. Robledo, Tsallis' q index and Mori's q phase transitions at the edge of chaos. Phys Rev E Stat Nonlin Soft Matter Phys, 2005. 72(2 Pt 2): p. 026209.
49. Tsekouras, G.A. and C. Tsallis, Generalized entropy arising from a distribution of q indices. Phys Rev E Stat Nonlin Soft Matter Phys, 2005. 71(4 Pt 2): p. 046144.
50. Chavanis, P.H., Generalized thermodynamics and Fokker-Planck equations: applications to stellar dynamics and two-dimensional turbulence. Phys Rev E Stat Nonlin Soft Matter Phys, 2003. 68(3 Pt 2): p. 036108.
51. Crupi, V., et al., Generalized Information Theory Meets Human Cognition: Introducing a Unified Framework to Model Uncertainty and Information Search. Cogn Sci, 2018.
52. Hasegawa, H.H., T. Nakamura, and D.J. Driebe, Generalized second law for a simple chaotic system. Chaos, 2017. 27(10): p. 104606.
53. De Grroot, S.R., Thermodynamik irreversibler Prozesse. 1960, Mannheim: Bibliographisches Institut.
54. Kayser, K., et al., AI (artificial intelligence) in histopathology--from image analysis to automated diagnosis. Folia Histochem Cytobiol, 2009. 47(3): p. 355-61.
55. Ahar, A., A. Barri, and P. Schelkens, From Sparse Coding Significance to Perceptual Quality: A New Approach for Image Quality Assessment. IEEE Trans Image Process, 2018. 27(2): p. 879-893.
56. Bhateja, V., et al., Multispectral medical image fusion scheme based on hybrid contourlet and shearlet transform domains. Rev Sci Instrum, 2018. 89(8): p. 084301.
57. Mehre, S.A., et al., Content-Based Image Retrieval System for Pulmonary Nodules Using Optimal Feature Sets and Class Membership-Based Retrieval. J Digit Imaging, 2018.
58. Kumar, R.K., et al., Virtual microscopy for learning and assessment in pathology. J Pathol, 2004. 204(5): p. 613-8.
59. Nakane, K., et al., Homology-based method for detecting regions of interest in colonic digital images. Diagn Pathol, 2015. 10: p. 36.
60. Theart, R.P., et al., Improved region of interest selection and colocalization analysis in three-dimensional fluorescence microscopy samples using virtual reality. PLoS One, 2018. 13(8): p. e0201965.
61. Kayser, K., et al., Neighborhood analysis of low magnification structures (glands) in healthy, adenomatous, and carcinomatous colon mucosa. Pathol Res Pract, 1986. 181(2): p. 153-8.
62. Kayser, K., et al., Combined morphometrical and syntactic structure analysis as tools for histomorphological insight into human lung carcinoma growth. Anal Cell Pathol, 1990. 2(3): p. 167-78.
63. Corredor, G., E. Romero, and M. Iregui, An adaptable navigation strategy for Virtual Microscopy from mobile platforms. J Biomed Inform.
64. Wright, A.I., H.I. Grabsch, and D.E. Treanor, RandomSpot: A web-based tool for systematic random sampling of virtual slides. J Pathol Inform. 6: p. 8.
65. Kayser, K., Introduction of virtual microscopy in routine surgical pathology--a hypothesis and personal view from Europe. Diagn Pathol. 7: p. 48.
66. John E. Hopcroft, J.D.U., • Einführung in die Automatentheorie, Formale Sprachen und Komplexitätstheorie Vol. 3. Auflage. 1996, Bonn Addison-Wesley.
67. Kayser, K., et al., Image standards in tissue-based diagnosis (diagnostic surgical pathology). Diagn Pathol, 2008. 3: p. 17.
68. Kayser, K., et al., From telepathology to virtual pathology institution: the new world of digital pathology. Rom J Morphol Embryol, 1999. 45: p. 3-9.
69. Park, S., et al., The history of pathology informatics: A global perspective. J Pathol Inform. 4: p. 7.
70. Kayser, K., travels on Conferences. 2016, Berlin: schaefermueller publishing GmbH.
71. Gortler, J., et al., Grid technology in tissue-based diagnosis: fundamentals and potential developments. Diagn Pathol, 2006. 1: p. 23.
Published
2018-12-21
How to Cite
KAYSER, Klaus; BORKENFELD, Stephan; KAYSER, Gian. Digital Image Content and Context Information in Tissue-based Diagnosis. Diagnostic Pathology, [S.l.], v. 4, n. 1, dec. 2018. ISSN 2364-4893. Available at: <http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/269>. Date accessed: 25 mar. 2019. doi: https://doi.org/10.17629/www.diagnosticpathology.eu-2018-4:269.
Section
Theory