Cognitive Algorithms and digitized Tissue – based Diagnosis

  • Jürgen Görtler IBM Global Markets, Systems, Frankfurt, Germany
  • Klaus Kayser Charite, Berlin, Germany
  • Stephan Borkenfeld IAT, Heidelberg, Germany
  • Rita Carvalho Central Lisbon Hospital Center, Department of Pathology, Lisbon, Portugal
  • Gian Kayser Institute of Surgical Pathology, Medical Center – University of Freiburg, Faculty of Medicine, University of Freiburg, Germany

Abstract

Aims: To analyze the nature and impact of cognitive algorithms and programming on digitized tissue – based diagnosis.


Definitions: Digitized tissue – based diagnosis includes all computerized tissue investigations that contribute to the most appropriate description and forecast of the actual patient’s disease [1]. Cognitive algorithms are programs that encompass machine learning, reasoning, and human – computer interaction [2].


Theoretical considerations: Digitized blood data, objective clinical findings, microscopic, gross, radiological images and gene alterations are analyzed by specialized image analysis methods, and transferred in numbers and vectors. These are analyzed by statistical procedures. They include higher order statistics such as multivariate analysis, neural networks and ‘black box’ strategies, for example ‘deep learning’ or ‘Watson’ approaches. These algorithms can be applied at different cognitive ‘levels’, to reach a digital decision for different procedures which should assist the patient’s health condition. These levels can be grouped in self learning, self promoting, self targeting, and self exploring algorithms. Each of them requires a memory and neighbourhood condition. Self targeting and exploring algorithms are circumscribed mechanisms with singularities and repair procedures. They develop self recognition.  


Consecutives: Medical doctors including pathologists are commonly not trained to understand the basic principles and workflow of applied or potential future procedures. At present, basic medical data only serve for simple cognitive algorithms. Most of the investigations focus on ‘deep learning’ procedures. The applied learning and decision algorithms might be modified and themselves be used for ‘next order cognitive algorithms’. Such systems will develop their own strategies, and become independent from potential human interactions. The basic strategy of such IT systems is described herein.


Perspectives: Medical doctors including pathologists should be aware about the abilities to enhance their work by supporting tools. In some case the users may not be able to fully understand these tools. Furthermore, these tools will probably become self learning, and, therefore, seem to propose the daily workflow probably without any medical control or even interaction.

References

1. Kayser K, Hoshang SA, Metze K, Goldmann T, Vollmer E, Radziszowski D, Kosjerina Z, Mireskandari M, Kayser G. Texture- and object-related automated information analysis in histological still images of various organs. Anal Quant Cytol Histol. 2008; 30(6):323-35.
2. Kayser K, Molnar B, Weinstein R. Virtual Microscopy - Fundamentals, Applications, Perspectives of Electronic Tissue-based Diagnosis. Berlin: VSV Interdisciplinary Medical Publishing; 2006.
3. Kayser K, Gabius HJ. 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):443-55.
4. Kayser K, Kayser G, Metze K. The concept of structural entropy in tissue based diagnosis. AQCH. 2007; 29(5):296-308.
5. Kayser K, Radziszowski D, Bzdyl P, Sommer R, Kayser G. Digitized pathology: theory and experiences in automated tissue-based virtual diagnosis. Rom J Morphol Embryol. 2006; 47(1):21-8.
6. Gabius HJ, Kayser K. Introduction to glycopathology : the concept, the tools and the perspectives. Diagn Pathol. 2014; 9:4.
7. Hetzmann Z, Mostafa MG, Dalquen P. Computational Pathology and Telepathology : SY05-1 Telecytology Only An Advantage For Countries With Underserved Setting. Pathology. 2014; 46:S7.
8. Kayser G, Kayser K. Quantitative pathology in virtual microscopy: history, applications, perspectives. Acta Histochem. 2013; 115(6):527-32.
9. Pekmezci M, Reuss DE, Hirbe AC, Dahiya S, Gutmann DH, von Deimling A, Horvai AE, Perry A. Morphologic and immunohistochemical features of malignant peripheral nerve sheath tumors and cellular schwannomas. Mod Pathol. 2015; 28(2):187-200.
10. Slavik T, Asselah F, Fakhruddin N, El Khodary A, Torjman F, Anis E, Quinn M, Khankan A, Kerr KM. Diagnosis and Predictive Molecular Analysis of Non-Small-Cell Lung Cancer in the Africa-Middle East Region: Challenges and Strategies for Improvement. Clin Lung Cancer. 2014; 15(6):398-404.
11. Kayser K, Borkenfeld S, Carvalho R, Djenouni A, Kayser G. How to analyze Structure and Function in Tissue – based Diagnosis?. Diagnostic Pathology. 2016; 2-106.
12. Bartels PH, Montironi R. Quantitative histopathology: the evolution of a scientific field. Anal Quant Cytol Histol. 2009; 31(1):1-4.
13. Cooper WA, Yu B, Yip PY, Ng CC, Lum T, Farzin M, Trent RJ, Mercorella B, Clarkson A, Kohonen-Corish MR, Horvath LG, Kench JG, McCaughan B, Gill AJ, O'Toole SA. EGFR mutant-specific immunohistochemistry has high specificity and sensitivity for detecting targeted activating EGFR mutations in lung adenocarcinoma. J Clin Pathol.2013; 66(9):744-8.
14. Kayser K. Quantification of virtual slides: Approaches to analysis of content-based image information. J Pathol Inform. 2011; 2:2.
15. Schlenk RF, Döhner K, Kneba M, Götze K, Hartmann F, del Valle F, Kirchen H, Koller E, Fischer JT, Bullinger L, Habdank M, Späth D, Groner S, Krebs B, Kayser S, Corbacioglu A, Anhalt A, Benner A, Fröhling S, Döhner H. Gene mutations and response to treatment with all-trans retinoic acid in elderly patients with acute myeloid leukemia. Results from the AMLSG Trial AML HD98B. Haematologica. 2009; 94(1):54-60.
16. Kayser K, Görtler J, Giesel F, Kayser G. How to implement grid technology in tissue-based diagnosis: diagnostic surgical pathology. Expert Opin Med Diagn. 2008; 2(3):323-337.
17. Kayser K, Borkenfeld S, Carvalho R, Kayser G. Structure, Function, and Predictive Diagnosis Algorithms. Diagnostic Pathology. 2016; 8:153.
18. van Leeuwen J, Ibrahim A, Anca Bucur A. Integration Of Externalized Decision Models In The Definition Of Workflows For Digital Pathology. Diagnostic Pathology. 2017; 8:179.
19. Liu YT, Lin YY, Wu SL, Chuang CH, Lin CT. Brain Dynamics in Predicting Driving Fatigue Using a Recurrent Self-Evolving Fuzzy Neural Network. IEEE Trans Neural Netw Learn Syst. 2016; 27(2):347-60.
20. Urwyler P, Rampa L, Stucki R, Büchler M, Müri R, Mosimann UP, Nef T. Recognition of activities of daily living in healthy subjects using two ad-hoc classifiers. Biomed Eng Online. 2015; 14:54.
21. Wu T, Li B, Zhu SC. Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation. IEEE Trans Pattern Anal Mach Intell. 2016; 38:9.
22. Edelman G, Tononi G. A Universe of Consciousness: How Matter Becomes Imagination. New York: Basic Books New York; 2000.
23. Rothganger F. The dawn of the real thinking machine. IEEE Spectrum. 2017; 44-49.
24. Koch C, Tonini G. Can we quantify machine consciousness?. IEEE Spectrum. 2017; 62-69.
25. Kayser K, Stute H, Bubenzer J, Paul J. Combined morphometrical and syntactic structure analysis as tools for histomorphological insight into human lung carcinoma growth. Anal Cell Pathol. 1990; 2(3):167-78.
26. Kayser K, Schlegel W. Pattern recognition in histo-pathology: basic considerations. Methods. Inf Med. 1982; 21(1):15-22.
27. Kayser K, Hoffgen H. Pattern recognition in histopathology by orders of textures. Med Inform (Lond). 1984; 9(1):55-9.
28. Kayser K, Görtler J, Borkenfeld S, Kayser G. Interactive and automated application of virtual microscopy. Diagn Pathol. 2011; 6:S10.
29. Kayser K, Borkenfeld S, Goldmann T, Kayser G. To be at the right place at the right time. Diagn Pathol. 2011; 6:2-9.
30. Okuno H, Yagi T. A visually guided collision warning system with a neuromorphic architecture. Neural Netw. 2008; 21(10):1431-8.
31. Sharma K, Rupprecht C, Caroli A, Aparicio MC, Remuzzi A, Baust M, Navab N. Automatic Segmentation of Kidneys using Deep Learning for Total Kidney Volume Quantification in Autosomal Dominant Polycystic Kidney Disease. Sci Rep. 2017; 7(1):2049.
32. Rudd EM, Jain LP, Scheirer WJ, Boult TE. The Extreme Value Machine. IEEE Trans Pattern Anal Mach Intell. 2017; Available from:epub ahead of print.
33. Huang T, Javaherian H, Liu D. Nonlinear torque and air-to-fuel ratio control of spark ignition engines using neuro-sliding mode techniques. Int J Neural Syst. 21(3):213-24.
34. Inglese P, McKenzie JS, Mroz A, Kinross J, Veselkov K, Holmes E, Takats Z, Nicholson JK, Glen RC. Deep learning and 3D-DESI imaging reveal the hidden metabolic heterogeneity of cancer. Chem Sci. 2017; 8(5):3500-3511.
35. Zhang XY, Yin F, Zhang YM, Liu CL, Bengio Y. Drawing and Recognizing Chinese Characters with Recurrent Neural Network. IEEE Trans Pattern Anal Mach Intell. 2017; epub ahead of print.
36. Yuan Y, Chao M, Lo YC. Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks with Jaccard Distance. IEEE Trans Med Imaging. 2017; [epub ahead of print].
37. Lakhani P, Sundaram B. Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks. Radiology. 2017; [epub ahead of print].
38. Kraus OZ, Grys BT, Ba J, Chong Y, Frey BJ, Boone C, Andrews BJ. Automated analysis of high-content microscopy data with deep learning. Mol Syst Biol. 2017; 13(4): 924.
39. Kong Y, Ding Z, Li J, Fu Y. Deeply Learned View-Invariant Features for Cross-View Action Recognition. IEEE Trans Image Process. 2017; epub ahead of print.
40. Ciompi F, Chung K, van Riel SJ, Setio AAA, Gerke PK, Jacobs C, Scholten ET, Schaefer-Prokop C, Wille MMW, Marchianò A, Pastorino U, Prokop M, van Ginneken B. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci Rep. 2016; 7:46479.
41. Chien JT, Bao YT. Tensor-Factorized Neural Networks. IEEE Trans Neural Netw Learn Syst. 2017; [Epub ahead of print].
42. Pasquier M, Quek C, Toh M. Fuzzylot: a novel self-organising fuzzy-neural rule-based pilot system for automated vehicles. Neural Netw. 2001; 14(8):1099-112.
43. O'Donnell K, Badrick E, Kumari M, Steptoe A. Psychological coping styles and cortisol over the day in healthy older adults. Psychoneuroendocrinology. 2008; 33(5):601-11.
44. Lafont S, Laumon B, Helmer C, Dartigues JF, Fabrigoule C. Driving cessation and self-reported car crashes in older drivers: the impact of cognitive impairment and dementia in a population-based study. J Geriatr Psychiatry Neurol. 2008; 21(3):171-82.
45. Gundersen HJ, Bendtsen TF, Korbo L, Marcussen N, Møller A, Nielsen K, Nyengaard JR, Pakkenberg B, Sørensen FB, Vesterby A. Some new, simple and efficient stereological methods and their use in pathological research and diagnosis. Apmis. 1988; 96(5):379-94.
46. Gundersen HJ. Stereology -- or how figures for spatial shape and content are obtained by observation of structures in sections. Microsc Acta. 1980; 83(5):409-26.
47. Elias H, Bokelmann D, Vogtle R. Principles of stereology and morphometry presented with large intestinal carcinogenesis as example. Verh Anat Ges. 1976; 70(Pt 2):911-6.
48. Cruz-Orive LM, Weibel ER. Sampling designs for stereology. J Microsc. 1981; 122(Pt 3):235-57.
49. Thrun S, Montemerlo M. FastSLAM : a scalable method for the simultaneous localization and mapping problem in robotics. New York: Springer; 2007.
50. Thrun S, Burgard W, Fox D. Probabilistic Robotics (Intelligent Robotics and Autonomous Agents). Cambridge/London: MIT Pressed; 2005.
51. Sedlacek J. Einführung in die Graphentheorie. Leipzig: B. G. Teubner; 1972.
52. Sumner JA, Griffith JW, Mineka S. Examining the mechanisms of overgeneral autobiographical memory: capture and rumination, and impaired executive control. Memory. 2011; 19(2):169-83.
53. Voronoi G. Nouvelles applications des parametres continus a la theorie des formes quadratiques, deuxieme memoire: recherches sur les paralleloedres primitifs. J Reine Angew Math. 1902; 134:188-287.
54. Plancher G, Tirard A, Gyselinck V, Nicolas S, Piolino P. Using virtual reality to characterize episodic memory profiles in amnestic mild cognitive impairment and Alzheimer's disease: influence of active and passive encoding. Neuropsychologia. 2012; 50(5):592-602.
55. Liu J, Gong M, Miao Q, Wang X, Li H. Structure Learning for Deep Neural Networks Based on Multiobjective Optimization. IEEE Trans Neural Netw Learn Syst. Date of publication [2017]. Available from: [epub ahead of print].
56. Le MN, Ong YS, Menzel S, Jin Y, Sendhoff B. Evolution by adapting surrogates. Evol Comput. 2013; 21(2):313-40.
57. Moore GP, Talarico S, Kempinska A, Lawrence SE, Weisz DE. An innovative on-call system for paediatric residency programs: The alternate night float. Paediatr Child Health. 2015; 20(2):77-81.
58. McNabb J, Gray R. Staying Connected on the Road: A Comparison of Different Types of Smart Phone Use in a Driving Simulator. PLoS One. 2016; 11(2):e0148555.
59. Available from: https://www.oculus.com/rift/.
60. Kayser K, Gabius HJ. 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):1-106.
61. Yuan J, Wu Y. Mining visual collocation patterns via self-supervised subspace learning. IEEE Trans Syst Man Cybern B Cybern. 2012; 42(2):334-46.
62. Samek W, Binder A, Montavon G, Lapuschkin S, Müller K-R. Evaluating the visualization of what a deep neural network has learned. IEEE Trans Neural Netw Learn Syst. 2016; 99: 1–14.
63. Montavon G, Lapuschkin S, Binder A, Samek W, Müller K-R. Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recognition. 2017; 65:211 - 222.
64. Available from: https://su.org/faculty-speakers/neil-jacobstein/.
Published
2017-07-28
How to Cite
GÖRTLER, Jürgen et al. Cognitive Algorithms and digitized Tissue – based Diagnosis. Diagnostic Pathology, [S.l.], v. 3, n. 1, july 2017. ISSN 2364-4893. Available at: <http://www.diagnosticpathology.eu/content/index.php/dpath/article/view/248>. Date accessed: 21 oct. 2017. doi: https://doi.org/10.17629/www.diagnosticpathology.eu-2017-3:248.
Section
Research

Most read articles by the same author(s)