Using an artificial neural network to recognize sturgeon blood cells in microscopic images

The article considers the labor intensity of the process of determining the white blood cell count of fish, which is simultaneously being highly significant and necessary in terms of monitoring the health of individuals. The authors present an approach to automating the compilation of the white blood cell count of fish (using sturgeon as an example) using a convolutional neural network model capable of recognizing and identifying cells in a microscopic blood image. The general scheme of hematopoiesis and standards for hematological parameters of sturgeon are considered. The procedure for preparing images for training a markup-based artificial neural network model is described. Software tools for interaction with images and artificial neural network models are described. As a result of the research, 14 microscopic images of fish blood cells based on markup were prepared, a convolutional neural network model was trained, the overall mean average precision (MAP) of which was 0.33. At the same time, the overall accuracy of cell recognition in individual images was 0.92, and the rate of red blood cell recognition was 0.94. The research results can serve as a basis for further study, development and application of convolutional neural networks for automating white blood cell count compilation based on high-precision recognition of fish blood cells in microscopic images.

1. Alieva E.M., Gadzhimuradov G.Sh., Abdullaeva Z.K., Mirzaalieva H.A. Biochemical parameters of sterlet blood. Vserossiyskaya nauchno-prakticheskaya konferentsiya ‘Sovremennye tekhnologii i dostizheniya nauki v APK’. November 22-23, 2018. Makhachkala, Russia: Dagestan State Agricultural University named after M.M. Dzhambulatov, 2018:274-280. (In Russ.)

2. Zinchenko A.P., Ukolova A.V., Demichev V.V., Tikhonova A.V. et al. Digital technologies for data analysis in agriculture: a monograph. Moscow, Russia: Nauchniy konsultant, 2022:260. (In Russ.)

3. Pronina G.I., Bykov D.V., Ukolova A.V., Ul’yankin A.E. et al. Identification of fish blood cell populations on the basis of a convolutionary neural network for compiling a leukogram. Izvestiya of Timiryazev Agricultural Academy. 2023;1(4):110-125. (In Russ.) https://doi.org/10.26897/0021-342X-2023-4-110-125

4. Koryagina N.Yu., Pronina G.I. Methodology of physiological and immunological assessment of aquatic organisms: a textbook. St. Petersburg, Russia: Lan, 2022:96. (In Russ.)

5. Kazarnikova A.V. Instruction book for combating fish diseases: a study guide. Moscow, Russia: SBS-AGRO, 1999:234. (In Russ.)

6. Pastushok I.A., Kim M.A., Gusev V.N., Yaremin B.I. et al. System for automatic recognition of leukocytes in a peripheral blood smear based on deep learning technology. Vestnik meditsinskogo instituta “Reaviz”: reabilitatsiya, vrach i zdorov’e. 2018;31(1):117-120. (In Russ.)

7. Sosnin D.Y., Onyanova L.S., Kubarev O.G., Kozonogova E.V. Evaluation of Efficacy of White Blood Cell Identification in Peripheral Blood by Automated Scanning of Stained Blood Smear Images with Variable Magnification. Biomedical Engineering. 2018;1(51):31-36. https://doi.org/10.1007/s10527-018-9776-1