DOI
10.34229/KCA2522-9664.26.1.14
UDC 004.93.1
А.S. Dovbysh
Sumy State University, Sumy, Ukraine, 
a.dovbysh@cs.sumdu.edu.ua
A.M. Romaniuk
Sumy State University, Sumy, Ukraine, a.romanjik@med.sumdu.edu.ua
I.V. Shelehov
Sumy State University, Sumy, Ukraine, i.shelehov@cs.sumdu.edu.ua
R.A. Moskalenko
Sumy State University, Sumy, Ukraine, r.moskalenko@med.sumdu.edu.ua
T.R. Savchenko
Sumy State University, Sumy, Ukraine,
taras.savchenk0@student.sumdu.edu.ua
A.P. Denysenko
Sumy State University, Sumy, Ukraine,
a.denysenko@med.sumdu.edu.ua
DECISION SUPPORT SYSTEM FOR DIAGNOSING EARLY STAGES OF PROSTATE
CANCER BY PATHOMORPHOLOGY SIGNS
Abstract. The research method was developed within the framework of an information-extreme intelligent data analysis technology, which is based on maximizing the information capacity of the system during machine learning. The method was constructed in line with a functional approach to modeling the cognitive processes of natural intelligence. As a result of information-extreme machine learning using whole-slide histological images, it became possible to distinguish adenoma from early-stage cancer in prostate tissues. The sizes of the affected glands and the inter-center distance between them were used as additional recognition meta-features, which made it possible to construct highly reliable decision rules in the course of the machine-learning process.
Keywords: information-extreme machine learning, information criterion, prostate cancer, adenoma, diagnosis, full-slide histological image.
full text
REFERENCES
- 1. Navid F., Parwani A.V., Pantanowitz L. Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine International. 2015. Vol. 7. P. 23–33. 4321. https://doi.org/10.2147/PLMI.S59826.
- 2. Salvi M., Manini C., LЛpez J.I. et al. Deep learning approach for accurate prostate cancer identification and stratification using combined immunostaining of cytokeratin, p63, and racemase. Computerized Medical Imaging and Graphics. 2023. Vol. 109. Article number 102288. https://doi.org/10.1016/j.compmedimag.2023.102288.
- 3. Parker C., Castro E., Fizazi K. et al. Prostate cancer: ESMO clinical practice guidelines for diagnosis, treatment and follow-up. Annals of Oncology. 2020. Vol. 31, N 9. P. 1119–1134. https://doi.org/10.1016/j.annonc.2020.06.011
- 4. Pesapane F.; Acquasanta M., Meo R.D. et al. Comparison of sensitivity and specificity of biparametric versus multiparametric prostate MRI in the detection of prostate cancer in 431 men with elevated prostate-specific antigen levels. Diagnostics. 2021. Vol. 11, N 7. Article number 1223. https://doi.org/10.3390/diagnostics11071223.
- 5. WebPathology Visual Survey of surgical pathology. Prostate. 2023. URL: https://www.webpathology.com/category.asp?category=1.
- 6. Kwak J.T., Hewitt S.M. Nuclear architecture analysis of prostate cancer via convolutional neural networks. IEEE Access. 2017. Vol. 5. P. 18526–18533. https://doi.org/10.1109/ACCESS.2017.2747838.
- 7. Arvaniti E., Fricker K.S., Moret M. et al. Automated Gleason grading of prostate cancer tissue microarrays via deep learning. Sci. Rep. 2018. Vol. 8, N 1. Article number 12054. https://doi.org/10.1038/s41598-018-30535-1.
- 8. Toth R., Schiffmann H., Hube-Magg C. et al. Random forest-based modelling to detect biomarkers for prostate cancer progression. Clinical Epigenetics. 2019. Vol. 11. Article number 148. https://doi.org/10.1186/s13148-019-0736-8.
- 9. Lin C.-F., Wang S.-D. Fuzzy support vector machines. IEEE Transactions on Neural Networks. 2002. Vol. 13, N 2. P. 464–471. https://doi.org/10.1109/72.991432.
- 10. Del Toro O.J., Atzori M., Otїlora S. et al. Convolutional neural networks for an automatic classification of prostate tissue slides with high-grade Gleason score. Proc. SPIE. 2017. Vol. 10140. Article number 101400O. https://doi.org/1117/12.2255710.
- 11. Rabinovich A., Agarwal S., Laris C.A. et al. Unsupervised color decomposition of histologically stained tissue samples. Proc. 17th Annu. Conf. Neural Inf. Process. Syst. NIPS 2003 (8–13 Dec., 2003, Vancouver, BC, Canada). Journal Advance in Neural Inf. Process. Syst. 2004. URL: http://papers.nips.cc/paper/2497-unsupervised-color-decomposition-of-histologically-stained-tissue-samples.pdf.
- 12. Nishio М., Matsuo Н., Kurata Y., Sugiyama О., Fujimoto K. Label distribution learning for automatic cancer grading of histopathological images of prostate cancer. Cancers. 2023. Vol.15, N 5. Article number 1535. https://doi.org/10.3390/cancers15051535.
- 13. Dovbysh А.S, Piatachenko V.Y, Myronenko M.I., Suprunenko M.K, Simonovskiy J.V. Hierarchical information-extreme machine learning of hand prosthesis control system based on decursive data structure. Journal of Engineering Sciences. 2924. Vol. 11, N 2. P. E1–E8. https://doi.org/10.21272/jes.2024.11(2).e1.
- 14. Dovbysh A.S., Shelehov I.V., Romaniuk A.V., Moskalenko R.A, Savchenko T.R. Desision-making support system for diagnosis of breast oncopathologies by histological images. Cybernetics and System Analysis. 2023. Vol 59, N 3. P. 493–502. https://doi.org/10.1007/s10559-023-00584-0.
- 15. Dovbysh A., Shelehov I., Romaniuk A., Moskalenko R., Savchenko T. Decision-making support system for diagnosis of oncopathologies by histological images. Journal of Pathology Informatics. 2023. Vol. 14. Article number 100193. https://doi.org/10.1016/j.jpi.2023.100193.
