DATA DISCRIMINATION IN PATHOMORPHOLOGY. WAYS OF COPING

Authors

DOI:

https://doi.org/10.11603/mie.1996-1960.2022.3.13359

Keywords:

data discrimination, big data, data compression, virtual pathology slides, visual discrimination model, neural convolutional networks, 4S algorithm

Abstract

Background. The issues of modern data analytics are considered, among which the risk of discrimination is the most acute. There are still no major studies on this topic in pathomorphology. Our work aims to identify the causes and consequences of discrimination in data mining and explore potential solutions to this problem. The purpose of the work was to identify the main reasons for the appearance of data discrimination in pathomorphology and conceptual substantiation of ways to overcome incomplete or biased data.

Materials and methods. Results. There are a large number of available compression schemes that help to solve various artifact problems (for example, blocking and color distortion, which is especially important for pathology, hot spot selection), but do not solve them all. Does not have a definitive solution to the effect of compressing the initial scan. To date, there is too little research on this topic.

Conclusions. A significant amount of work needs to be done before the complex relationships between the quality of the original sample, the quality of the scanned image, the quantitative characteristics of the applied compression and the impact on diagnostic interpretation and other related diagnostic procedures (structural classification, prognosis etc.). The proposed 4S algorithm (systematization, structuring stability of states), associated with the use of technology for creating stable morphological, histological, or other structures. The experience of its use provides a basis for cautious optimism.

References

Favaretto, M., De Clercq, E., Elger, B. S. (2019). Big Data and discrimination: perils, promises and solutions. A systematic review. J Big Data, 6(12). DOI:10.1186/s40537-019-0177-4. DOI: https://doi.org/10.1186/s40537-019-0177-4

Homeyer, A., Hammad, S., Schwen, L. O., Dahmen, U., Hofener, H. et al. (2018). Focused scores enable reliable discrimination of small differences in steatosis. Diagn Pathol, 3(76). DOI:10.1186/s13000-018-0753-5. DOI: https://doi.org/10.1186/s13000-018-0753-5

Johnson, J. P., Krupinski, E. A., Yan, M., Roehrig, H. et al. (2011). Using a visual discrimination model for the detection of compression artifacts in virtual pathology images. IEEE Trans Med Imaging, 30(2), 306-314. DOI:10.1109/TMI.2010.2077308-2. DOI: https://doi.org/10.1109/TMI.2010.2077308

Khosravi, P., Kazemi, E., Imielinski, M., Elemento, O., Hajirasouliha, I. (2018). Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images. EBioMedicine, 27, 317-328. DOI:10.1016/j. ebiom.2017.12.026. DOI: https://doi.org/10.1016/j.ebiom.2017.12.026

O'Connor, J. P. B., Rose, C. J., Waterton, J. C. et al. (2015). Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome. Clin Cancer Res, 21, 49-57. DOI: https://doi.org/10.1158/1078-0432.CCR-14-0990

Nong, P., Williamson, A., Anthony, D., Platt, J., Kardia Sh. (2022). Discrimination, trust, and withholding information from providers: Implications for missing data and inequity. SSM - Population Health. 18(101092), 1-7. DOI: https://doi.org/10.1016/j.ssmph.2022.101092

Plancoulaine, B., Laurinaviciene, A., Herlin, P. (2015). A methodology for comprehensive breast cancer Ki67 labeling index with intra-tumor heterogeneity appraisal based on hexagonal tiling of digital image analysis data. Virchows Arch, 467, 711-722. DOI: https://doi.org/10.1007/s00428-015-1865-x

Weinstein, R. S., Descour, M. R., Liang, C., Barker, G., Scott, K. M. et al. (2004). An array microscope for ultrarapid virtual slide processing and telepathology. Design, fabrication, and validation study. Human Pathol, 35, 1303-1314. DOI: https://doi.org/10.1016/j.humpath.2004.09.002

Mintser O. P., Babintseva L. Yu. (2022). Novi tendentsiyi rozvytku system predstavlennya ta upravlinnya danymy. analitychnyy pohlyad. [New trends in the development of data presentation and management systems. Analytical view]. Medychna informatyka ta inzheneriia. [Medical informatics and engineering], 1-2 (57-58), 5-13. DOI: 10.11603/ mie.1996-1960.2022.1-2.13104. [In Ukrainian].

Yagi, Y., Gilberson, J. R. (2005). Digital imaging in pathology: The case for standardization. J Telemed Telecare, 11, 109-116. DOI: https://doi.org/10.1258/1357633053688705

Published

2023-05-26

How to Cite

Mintser, O., & Sinyenko, N. O. (2023). DATA DISCRIMINATION IN PATHOMORPHOLOGY. WAYS OF COPING. Medical Informatics and Engineering, (3), 7–10. https://doi.org/10.11603/mie.1996-1960.2022.3.13359

Issue

Section

Articles