AN ANALYSIS OF DIGITAL IMAGES USING NEURAL NETWORKS TO DETECT HEMATOLOGIC DISEASES
https://doi.org/10.35266/1999-7604-2023-3-43-51
Abstract
The article discusses the application of the transfer learning method for the ensemble of artificial convolutional neural networks with preliminary digital image segmentation for blood cells in order to classify them later. The results obtained during neural networks classification demonstrate the efficiency of such technologies used for improving the accuracy of artificial neural networks when solving the problems of medical images segmentation for leukocytes in order to diagnose hematologic diseases.
About the Authors
Maksim A. Panin
Surgut State University, Surgut
Russian Federation
Russian Federation
Master’s Degree Student
Elishan Sh. Mamedov
Surgut State University, Surgut
Russian Federation
Russian Federation
Master’s Degree Student
Dmitry V. Tarakanov
Surgut State University, Surgut
Russian Federation
Russian Federation
Candidate of Sciences (Engineering), Docent
References
1. Burkhonov R. A., Klimenko S. V. Using methods of deep learning for medical image analysis. In: Proceedings of the International Conference CPT1617, May 08‒15, 2016; May 07‒14, 2017, Larnaca, Cyprus; June 28‒29, 2016, TzarGrad, Russia. Moscow; Protvino: ICPT; 2017. p. 163–165. (In Russian).
2. Penikov A. A., Belov Yu. S. Overview of convolutional neural network architectures for solving the problem of semantic segmentation of medical images. In: Proceedings of the All-Russian National Scientific Conference “Fundamentalnye i prikladnye issledovaniia”, January 11, 2022, Saint Petersburg. St. Petersburg: Humanitarian National Research Institute NATsRAZVITIE; 2022. p. 18–21. (In Russian).
3. Gu Z., Cheng J., Fu H. et al. CE-Net: Context encoder network for 2D medical image segmentation. IEEE Transactions on Medical Imaging. 2019;38(10):2281–2292.
4. Pogruzhenie v svertochnye neironnye seti: peredacha obucheniia (transfer learning). URL: https://habr.com/ ru/post/467967/ (accessed: 14.09.2023). (In Russian).
5. Keras Applications. URL: https://keras.io/api/applications/ (accessed: 14.09.2023).
6. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. ArXiv. 2015. URL: https://arxiv.org/pdf/1409.1556.pdf (accessed: 14.09.2023).
7. Kurkova A. A., Grigoryeva A. I. Differential diagnostics of acute lymphoblastic and myeloblastic leukimia. Smolensk Medical Almanac. 2018;(1):191–196. (In Russian).
8. C_NMC_2019 dataset: ALL challenge dataset of ISBI 2019 (C-NMC 2019). URL: https://wiki.cancer-imagingarchive.net/pages/viewpage.action?pageId= 52758223#52758223a9c2c0a8b429412880eaa123286ca6f7 (accessed: 14.09.2023).
9. A single-cell morphological dataset of leukocytes from AML patients and non-malignant controls (AML-Cytomorphology_LMU). URL: https://wiki. cancerimagingarchive.net/pages/viewpage.action?pa geId=61080958#610809587633e163895b484eafe5794e2017c585 (accessed: 14.09.2023).
Review
For citations:
Panin M.A., Mamedov E.Sh., Tarakanov D.V. AN ANALYSIS OF DIGITAL IMAGES USING NEURAL NETWORKS TO DETECT HEMATOLOGIC DISEASES. Proceedings in Cybernetics. 2023;22(3):43-51. (In Russ.) https://doi.org/10.35266/1999-7604-2023-3-43-51
Views:
73
Email this article 