Digital pathology in Russia: experience and perspectives
A.I. Remez, A.S. Zhuravlev, A.O. Fattakhov, V.A. Pavlova
UNIM, Moscow
Digital pathology is a new stage in development of pathological anatomy, which appeared at the junction of classical microscopy and high technologies, allowing creation of digital histological preparations (Whole Slide Image) and transferring them via the Internet for consultations. Due to a lack of intuitive user interfaces for working with digital pathoanatomical images, UNIM has developed its own software product based on a SAAS platform (software as a service). It is the platform for remote analysis of the digitized histological preparations. The platform has already been implemented in some laboratories in Russia, the United States, and Europe. Machine learning techniques (ML) are widely used in this direction. ML is a class of algorithms that can customize their internal parameters for solving specific problems (learning process): solving local problems (for example, counting biomarkers expression) and creating replacement physician systems at a morphological stage of diagnosis (machine vision). This review article describes general principles of digital pathology, available in Russia modern resources, as well as possible directions for development of this technology using a training of neural networks.
For citation: Remez A.I., Zhuravlev A.S., Fattakhov A.O., Pavlova V.A. Digital pathology in Russia: experience and perspectives //
RMJ. Medical Review. 2018. № 6. P. 19–21.
References
1. Состояние и основные задачи развития патологоанатомической службы Российской Федерации: отраслевое статистическое исследование за 2016 год / под ред. Г. А. Франка. Минздрав России. М., 2017. 97 с. [Sostojanie i osnovnye zadachi razvitija patologo-anatomicheskoj sluzhby Rossijskoj Federacii: otraslevoe statisticheskoe issledovanie za 2016 god / pod red. G. A. Franka. Minzdrav Rossii. M., 2017. 97 s. (in Russian)].
2. Robboy S. J., Weintraub S., Horvath A. E. et al. Pathologist Workforce in the United States: I. Development of a Predictive Model to Examine Factors Influencing Supply // Archives of Pathology and Laboratory Medicine. 2013. Vol. 137 (12). P. 1723–1732.
3. Состояние и основные задачи развития патологоанатомической службы Российской Федерации: отраслевое статистическое исследование за 2014 год / под ред. Г. А. Франка, Е. П. Какориной и И. Г. Никитина. Минздрав России. М., 2015. 236 с.[Sostojanie i osnovnye zadachi razvitija patologo-anatomicheskoj sluzhby Rossijskoj Federacii: otraslevoe statisticheskoe issledovanie za 2014 god / pod red. G. A. Franka, E. P. Kakorinoj i I. G. Nikitina, Minzdrav Rossii. M., 2015. 236 s. (in Russian)].
4. Sarewitz S. J. Subspecialization in Community Pathology Practice // Arch. Pathol. Lab. Med. 2014. Vol.138. P. 871–872.
5. Groppi D. E., Alexis C. E., Sugrue C. F., Bevis C. C. Consolidation of the North Shore–LIJ Health System Anatomic Pathology Services: The Challenge of Subspecialization, Operations, Quality Management, Staffing, and Education // American Journal of Clinical Pathology. 2013. Vol.140 (1). P. 20–30.
6. Raab S. S., Grzybicki D. M. Quality in Cancer Diagnosis // CA: A Cancer Journal for Clinicians, 60. P. 139–165. doi:10.3322/caac.20068.
7. Zhao C., Wu T., Ding X., Parwani A. International Telepathology Consultation: Three Years of Experience between the University of Pittsburgh Medical Center (UPMC) and KingMed Diagnostics in China // J. Pathol. Inform. 2015. Vol. 6. P. 63. doi: 10.4103/2153–3539.170650.
8. Arbiser Z. K., Folpe A. L., Sharon W. Weiss Consultative (Expert) Second Opinions in Soft Tissue Pathology: Analysis of Problem-Prone Diagnostic Situations [Электронный ресурс] // American Journal of Clinical Pathology. 2001. Vol. 116 (4). P. 473–476. URL: https://doi.org/10.1309/425H-NW4W-XC9A-005H (дата обращения: 13.12.2017).
9. Thway K., Wang J., Mubako T., Fisher C. Histopathological Diagnostic Discrepancies in Soft Tissue Tumours Referred to a Specialist Centre: Reassessment in the Era of Ancillary Molecular Diagnosis // Sarcoma. 2014. 2014:686902. doi:10.1155/2014/686902.
10. Pantanowitz L. Digital images and the future of digital pathology // J. Pathol. Inform. 2010. Vol. 1. P. 15. doi: 10.4103/2153–3539.68332.
11. Pantanowitz L., Valenstein P. N., Evans A. J. et al. Review of the current state of whole slide imaging in pathology // J. Pathol. Inform. 2011. Vol. 2. P. 36. doi: 10.4103/2153–3539.83746.
12. Rosslyn V. Digital Imaging and Communications in Medicine (DICOM) Supplement 145: Whole Slide Microscopic Image IOD and SOP Classes [Электронный ресурс]. URL: ftp://medical.nema.org/medical/dicom/final/sup145_ft.pdf (дата обращения: 30.12.2017).
13. Guo H., Birsa J., Farahani N. et al. Digital pathology and anatomic pathology laboratory information system integration to support digital pathology sign-ou t// Journal of Pathology Informatics. 2016. Vol. 7. P. 23. doi: 10.4103/2153–3539.181767.
14. Pantanowitz L., Szymas J., Yagi Y., Wilbur D. Whole slide imaging for educational purposes // J. Pathol. Inform. 2012. Vol. 3. P. 46. doi: 10.4103/2153–3539.104908.
15. Chlipala E., Elin J., Eichhorn O. et al. Archival and retrieval in digital pathology systems [Электронный ресурс]. URL: https://digitalpathologyassociation.org/_data/files/Archival_and_Retrieval_in_Digital_Pathology_Systems.pdf (дата обращения: 10.12.2017).
16. Hou L., Samaras D., Kurc T. M. et al. Patch-based convolutional neural network for whole slide tissue image classification [Электронный ресурс] // Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2016. Jun-Ju 2016. P. 2424–2433. URL: http://arXiv.org/abs/1504.07947v5 (дата обращения: 01.12.2017).
17. Louis D. N., Feldman M., Carter A. B. et al. Computational Pathology: A Path Ahead [Электронный ресурс] // Archives of Pathology and Laboratory Medicine. 2016. Vol. 140 (1). P. 41–50. URL: https://doi.org/10.5858/arpa.2015–0093-SA (дата обращения: 14.12.2017).
This work is licensed under a Creative Commons «Attribution» 4.0 License.
Previous article
Next article
