For citation:
Ganigin S. Y., Davydov A. N., Nechaev A. S., Kiyashchenko V. V. Development and analysis of an algorithm for detecting multiple instances of an object in microscopic images using numerical methods. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, 2025, vol. 25, iss. 1, pp. 116-127. DOI: 10.18500/1816-9791-2025-25-1-116-127, EDN: UVLBDK
Development and analysis of an algorithm for detecting multiple instances of an object in microscopic images using numerical methods
This paper presents a method for object detection in microscopy images, focusing on particle detection. The main objective of the research is to develop an algorithm capable of efficiently detecting multiple instances of objects in various scenarios, while maintaining specificity for structures of interest. The algorithm is based on using extremal regions as candidates for detection, followed by evaluating these regions with trained parameters. A key element of the algorithm is its built-in non-overlapping constraint, which enables effective handling of particle clustering. Experimental results on various microscopy datasets confirm the method's robustness to changes in image intensity, particle density, and size. The proposed algorithm serves as a valuable tool in the development of object detection methods for microscopy images and can be applied in both scientific and medical research.
- Puchkov E. Image Analysis in Microbiology: A Review. Journal of Computer and Communications, 2016, vol. 4, iss. 15, pp. 8–32. https://doi.org/10.4236/jcc.2016.415002
- Spahn C., Gomez-de-Mariscal E., Laine R. F., Pereira P. M., Chamier L., Conduit M., Pinho M. G., Jacquemet G., Holden S., Heilemann M., Henriques R. DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches. Communications Biology, 2022, iss. 5, art. 688. https://doi.org/10.1038/s42003-022-03634-z
- Su P.-T., Liao C.-T., Roan J.-R., Wang S.-H., Chiou A., Syu W.-J. Bacterial colony from two-dimensional division to three-dimensional development. PloS ONE, 2023, vol. 7, iss. 11, art. e48098. https://doi.org/10.1371/journal.pone.0048098
- Zamyatin D. A., Porotnikov A. V., Shchapova Yu. V., Votyakov S. L. JPD-analysis of microscopic images in the study of structural and chemical heterogeneity of natural zircon grains. Mineraly: stroenie, svoystva, metody issledovaniya [Mineraly: Structure, Properties, Research Methods], 2014, iss. 6, pp. 26–27 (in Russian). EDN: YMSLCU
- Polishchuk S. V., Smekhun Ya. A. Electron microscopic images analysis using spectral characteristics. Mezhdunarodnyy nauchno-issledovatel’skiy zhurnal [International Scientific Research Journal], 2014, iss. 4–1 (23), pp. 65–67 (in Russian). EDN: SCQPCB
- Belyaeva L. A., Shurygina O. V., Yukhimets S. N., Petrova A. A., Mironov S. Yu., Ratenkova N. V., Kulakova O. V., Bovtunova S. S. Automated and manual semen analysis: The comparative characteristics. Morphological Newsletter, 2022, vol. 30, iss. 4, pp. 9–15 (in Russian). https://doi.org/10.20340/mv-mn.2022.30(4).704, EDN: JGHSAW
- Wei X., Liu Yo., Song Q., Zou J., Wen Zh., Li J., Jie D. Microscopic hyperspectral imaging and an improved detection model based detection of Mycogone perniciosa chlamydospore in soil. European Journal of Agronomy, 2024, vol. 152, art. 127007. https://doi.org/10.1016/j.eja.2023.127007
- Khan S., Sajjad M., Abbas N., Escorcia-Gutierrez J., Gamarra M., Khan M. Efficient leukocytes detection and classification in microscopic blood images using convolutional neural network coupled with a dual attention network. Computers in Biology and Medicine, 2024, vol. 174, art. 108146. https://doi.org/10.1016/j.compbiomed.2024.108146
- Han Zh., Huang H., Lu D., Fan Q., Ma Ch., Chen X., Gu Q., Chen Q. One-stage and lightweight CNN detection approach with attention: Application to WBC detection of microscopic images. Computers in Biology and Medicine, 2023, vol. 154, art. 106606. https://doi.org/10.1016/j.compbiomed.2023.106606
- Wang Ts. I., Voronov V. I. Analysis of the results of computed tomography of the brain using a convolutional neural network. DSPA: Voprosy primeneniya tsifrovoy obrabotki signalov [DSPA: Issues of Digital Signal Processing Application], 2020, vol. 10, iss. 1, pp. 32–40 (in Russian). EDN: OFBSSY
- Sun M., Wang W., Zhu X., Liu J. Reparameterizing and dynamically quantizing image features for image generation. Pattern Recognition, 2024, vol. 146, art. 109962. https://doi.org/10.1016/j.patcog.2023.109962
- Pawlowski J., Majchrowska S., Zhu X., Golan T. Generation of microbial colonies dataset with deep learning style transfer. Scientific Reports, 2022, vol. 12, art. 5212. https://doi.org/10.1038/s41598-022-09264-z
- Panic B., Borovinsek M., Vesenjak M., Oman S., Nagode M. A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields. Materials and Design, 2024, vol. 239, art. 112750. https://doi.org/10.1016/j.matdes.2024.112750
- Franti P., Mariescu-Istodor R. Soft precision and recall. Pattern Recognition Letters, 2023, vol. 167, pp. 115–121. https://doi.org/10.1016/j.patrec.2023.02.005
- 125 reads