Automatic Cell Counting With YOLOv5: A Fluorescence Microscopy Approach

  1. Sebastián López Flórez 1
  2. Alfonso González-Briones 1
  3. Guillermo Hernández 1
  4. Carlos Ramos 2
  5. Fernando de la Prieta 1
  1. 1 Universidad de Salamanca
    info

    Universidad de Salamanca

    Salamanca, España

    ROR https://ror.org/02f40zc51

  2. 2 Institute of Engineering - Polytechnic of Porto
Journal:
IJIMAI

ISSN: 1989-1660

Year of publication: 2023

Volume: 8

Issue: 3

Pages: 64-71

Type: Article

DOI: 10.9781/IJIMAI.2023.08.001 DIALNET GOOGLE SCHOLAR lock_openDialnet editor

More publications in: IJIMAI

Abstract

Counting cells in a Neubauer chamber on microbiological culture plates is a laborious task that depends on technical experience. As a result, efforts have been made to advance computer vision-based approaches, increasing efficiency and reliability through quantitative analysis of microorganisms and calculation of their characteristics, biomass concentration, and biological activity. However, variability that still persists in these processes poses a challenge that is yet to be overcome. In this work, we propose a solution adopting a YOLOv5 network model for automatic cell recognition and counting in a case study for laboratory cell detection using images from a CytoSMART Exact FL microscope. In this context, a dataset of 21 expert-labeled cell images was created, along with an extra Sperm DetectionV dataset of 1024 images for transfer learning. The dataset was trained using the pretrained YOLOv5 algorithm with the Sperm DetectionV database. A laboratory test was also performed to confirm result’s viability. Compared to YOLOv4, the current YOLOv5 model had accuracy, precision, recall, and F1 scores of 92%, 84%, 91%, and 87%, respectively. The YOLOv5 algorithm was also used for cell counting and compared to the current segmentation-based U-Net and OpenCV model that has been implemented. In conclusion, the proposed model successfully recognizes and counts the different types of cells present in the laboratory.

Bibliographic References

  • [1] M. Anderson, P. Hinds, S. Hurditt, P. Miller, D. McGrowder, R. AlexanderLindo, “The microbial content of unexpired pasteurized milk from selected supermarkets in a developing country,” Asian Pacific journal of tropical biomedicine, vol. 1, no. 3, pp. 205–211, 2011.
  • [2] T. E. Gray, D. G. Thomassen, M. J. Mass, J. C. Barrett, “Quantitation of cell proliferation, colony formation, and carcinogen induced cytotoxicity of rat tracheal epithelial cells grown in culture on 3t3 feeder layers,” In Vitro, pp. 559–570, 1983.
  • [3] Y. Li, G. Hetet, A.-M. Maurer, Y. Chait, D. Dhermy, J. Briere, “Spontaneous megakaryocyte colony formation in myeloproliferative disorders is not neutralizable by antibodies against il3, il6 and gm-csf,” British journal of haematology, vol. 87, no. 3, pp. 471–476, 1994.
  • [4] W. Xie, J. A. Noble, A. Zisserman, “Microscopy cell counting and detection with fully convolutional regression networks,” Computer methods in biomechanics and biomedical engineering: Imaging & Visualization, vol. 6, no. 3, pp. 283–292, 2018.
  • [5] T. Falk, D. Mai, R. Bensch, Ö. Çiçek, A. Abdulkadir, Y. Marrakchi, A. Böhm, J. Deubner, Z. Jäckel, K. Seiwald, et al., “U-net: deep learning for cell counting, detection, and morphometry,” Nature methods, vol. 16, no. 1, pp. 67–70, 2019.
  • [6] V. Gallego Albiach, L. M. Pérez Igualada, “Estimación de la densidad celular mediante el uso de cámaras de recuento,” 2021.
  • [7] C. Wilson, R. Lukowicz, S. Merchant, H. Valquier- Flynn, J. Caballero, J. Sandoval, M. Okuom, C. Huber, T. D. Brooks, E. Wilson, et al., “Quantitative and qualitative assessment methods for biofilm growth: a mini-review,” Research & reviews. Journal of engineering and technology, vol. 6, no. 4, 2017.
  • [8] G. M. Knight, E. Dyakova, S. Mookerjee, F. Davies, E. T. Brannigan, J. A. Otter, A. H. Holmes, “Fast and expensive (pcr) or cheap and slow (culture)? a mathematical modelling study to explore screening for carbapenem resistance in uk hospitals,” BMC medicine, vol. 16, no. 1, pp. 1–11, 2018.
  • [9] B. Song, B. Zhuge, H. Fang, J. Zhuge, “Analysis of the chromosome ploidy of candida glycerinogenes,” Wei Sheng wu xue bao= Acta Microbiologica Sinica, vol. 51, no. 3, pp. 326–331, 2011.
  • [10] S. I. Kim, H. J. Kim, H.-J. Lee, K. Lee, D. Hong, H. Lim, K. Cho, N. Jung, Y. W. Yi, “Application of a non- hazardous vital dye for cell counting with automated cell counters,” Analytical biochemistry, vol. 492, pp. 8– 12, 2016.
  • [11] D. Wang, M. Hwang, W.-C. Jiang, K. Ding, H. C. Chang, K.-S. Hwang, “A deep learning method for counting white blood cells in bone marrow images,” BMC bioinformatics, vol. 22, no. 5, pp. 1–14, 2021.
  • [12] X. Zhu, S. Lyu, X. Wang, Q. Zhao, “Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 2778–2788.
  • [13] S.-J. Lee, P.-Y. Chen, J.-W. Lin, “Complete blood cell detection and counting based on deep neural networks,” Applied Sciences, vol. 12, no. 16, p. 8140, 2022.
  • [14] Y. Egi, M. Hajyzadeh, E. Eyceyurt, “Drone-computer communication based tomato generative organ counting model using yolo v5 and deepsort,” Agriculture, vol. 12, no. 9, p. 1290, 2022.
  • [15] S. Xiang, S. Wang, M. Xu, W. Wang, W. Liu, “Yolo pod: a fast and accurate multi-task model for dense soybean pod counting,” Plant Methods, vol. 19, no. 1, p. 8, 2023.
  • [16] R. K. Purwar, S. Verma, “Analytical study of yolo and its various versions in crowd counting,” in Intelligent Data Communication Technologies and Internet of Things: Proceedings of ICICI 2021, Springer, 2022, pp. 975–989.
  • [17] S. He, K. T. Minn, L. Solnica-Krezel, M. A. Anastasio, H. Li, “Deeplysupervised density regression for automatic cell counting in microscopy images,” Medical Image Analysis, vol. 68, p. 101892, 2021.
  • [18] D. Zhang, P. Zhang, L. Wang, “Cell counting algorithm based on yolov3 and image density estimation,” in 2019 IEEE 4th international conference on signal and image processing (ICSIP), 2019, pp. 920–924, IEEE.
  • [19] S. L. Flórez, A. González-Briones, G. Hernández, F. de la Prieta, “Automated counting via multicolumn network and cytosmart exact fl microscope,” in Ambient Intelligence—Software and Applications—13th International Symposium on Ambient Intelligence, 2023, pp. 207–218, Springer.
  • [20] S. Chakraborty, C. Das, K. Ghoshal, M. Bhattacharyya, A. Karmakar, S. Chattopadhyay, “Low frequency impedimetric cell counting: analytical modeling and measurements,” IRBM, vol. 41, no. 1, pp. 23–30, 2020.
  • [21] A. Aijaz, D. Trawinski, S. McKirgan, B. Parekkadan, “Non-invasive cell counting of adherent, suspended and encapsulated mammalian cells using optical density,” BioTechniques, vol. 68, no. 1, pp. 35–40, 2020.
  • [22] M. M. Alam, M. T. Islam, “Machine learning approach of automatic identification and counting of blood cells,” Healthcare technology letters, vol. 6, no. 4, pp. 103– 108, 2019.
  • [23] J. Matas, O. Chum, M. Urban, T. Pajdla, “Robust wide-baseline stereo from maximally stable extremal regions,” Image and vision computing, vol. 22, no. 10, pp. 761–767, 2004.
  • [24] C. Arteta, V. Lempitsky, J. A. Noble, A. Zisserman, “Learning to detect cells using non-overlapping extremal regions,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I 15, 2012, pp. 348–356, Springer.
  • [25] V. Acharya, P. Kumar, “Identification and red blood cell automated counting from blood smear images using computer-aided system,” Medical & biological engineering & computing, vol. 56, pp. 483–489, 2018.
  • [26] M. L. Clarke, R. L. Burton, A. N. Hill, M. Litorja, M. H. Nahm, J. Hwang, “Low-cost, high-throughput, automated counting of bacterial colonies,” Cytometry Part A, vol. 77, no. 8, pp. 790–797, 2010.
  • [27] A. Vembadi, A. Menachery, M. A. Qasaimeh, “Cell cytometry: Review and perspective on biotechnological advances,” Frontiers in bioengineering and biotechnology, vol. 7, p. 147, 2019.
  • [28] M. M. Alam, M. T. Islam, “Machine learning approach of automatic identification and counting of blood cells,” Healthcare technology letters, vol. 6, no. 4, pp. 103– 108, 2019.
  • [29] P. J. Schüffler, T. J. Fuchs, C. S. Ong, P. J. Wild, N. J. Rupp, J. M. Buhmann, “Tmarker: A free software toolkit for histopathological cell counting and staining estimation,” Journal of pathology informatics, vol. 4, no. 2, p. 2, 2013.
  • [30] R. J. Santen, “Automated estimation of diploid and tetraploid nuclei with an electronic particle counter,” Experimental Cell Research, vol. 40, no. 2, pp. 413–420, 1965, doi: 10.1016/0014-4827(65)90274-0.
  • [31] Y. Payasi, S. Patidar, “Diagnosis and counting of tuberculosis bacilli using digital image processing,” in 2017 international conference on information, communication, instrumentation and control (ICICIC), 2017, pp. 1–5, IEEE.
  • [32] M. L. Clarke, R. L. Burton, A. N. Hill, M. Litorja, M. H. Nahm, J. Hwang, “Low-cost, high-throughput, automated counting of bacterial colonies,” Cytometry Part A, vol. 77, no. 8, pp. 790–797, 2010.
  • [33] P. Kaur, V. Sharma, N. Garg, “Platelet count using image processing,” in 2016 3rd International conference on computing for sustainable global development (INDIACom), 2016, pp. 2574–2577, IEEE.
  • [34] V. Acharya, P. Kumar, “Identification and red blood cell automated counting from blood smear images using computer-aided system,” Medical & biological engineering & computing, vol. 56, pp. 483–489, 2018.
  • [35] C. Arteta, V. Lempitsky, J. A. Noble, A. Zisserman, “Detecting overlapping instances in microscopy images using extremal region trees,” Medical image analysis, vol. 27, pp. 3–16, 2016.
  • [36] W. Xie, J. A. Noble, A. Zisserman, “Microscopy cell counting and detection with fully convolutional regression networks,” Computer methods in biomechanics and biomedical engineering: Imaging & Visualization, vol. 6, no. 3, pp. 283–292, 2018.
  • [37] M. A. Kumaar, D. Samiayya, V. Rajinikanth, D. Raj Vincent PM, S. Kadry, “Brain tumor classification using a pre-trained auxiliary classifying style-based generative adversarial network,” 2023.
  • [38] S.-H. Chen, C.-W. Wang, I. Tai, K.-P. Weng, Y.-H. Chen, K.-S. Hsieh, et al., “Modified yolov4-densenet algorithm for detection of ventricular septal defects in ultrasound images,” 2021.
  • [39] P. Kaur, V. Sharma, N. Garg, “Platelet count using image processing,” in 2016 3rd International conference on computing for sustainable global development (INDIACom), 2016, pp. 2574–2577, IEEE.
  • [40] M. Yuzkat, H. O. Ilhan, N. Aydin, “Detection of sperm cells by singlestage and two-stage deep object detectors,” Biomedical Signal Processing and Control, vol. 83, p. 104630, 2023.
  • [41] W. Han, L. Cao, S. Xu, “A method of the coverage ratio of street trees based on deep learning.,” International Journal of Interactive Multimedia & Artificial Intelligence, vol. 7, no. 5, 2022.
  • [42] J. G. A. Barbedo, “Automatic object counting in neubauer chambers,” Scientific. net, 2013, doi: 10.14209/sbrt.2013.224.
  • [43] M. J. Sanderson, I. Smith, I. Parker, M. D. Bootman, “Fluorescence microscopy,” Cold Spring Harb. Protoc., vol. 2014, p. db.top071795, Oct. 2014.
  • [44] X. Xu, Y. Feng, C. Han, Z. Yao, Y. Liu, C. Luo, J. Sheng, “Autophagic response of intestinal epithelial cells exposed to polystyrene nanoplastics,” Environmental Toxicology, vol. 38, no. 1, pp. 205–215, 2023.
  • [45] king mongkuts university of technology thonburi, “sperm detectionv4 dataset.” https://universe.roboflow.com/king-mongkuts-university-oftechnology-thonburi-ybmh7/sperm-detectionv4, feb 2023. [Online]. Available: https://universe.roboflow.com/king-mongkuts-university-oftechnology-thonburi-ybmh7/sperm-detectionv4, visited on 2023-03-07.
  • [46] Z. Wang, L. Jin, S. Wang, H. Xu, “Apple stem/calyx real-time recognition using yolo-v5 algorithm for fruit automatic loading system,” Postharvest Biology and Technology, vol. 185, p. 111808, 2022.
  • [47] X. Dong, S. Yan, C. Duan, “A lightweight vehicles detection network model based on yolov5,” Engineering Applications of Artificial Intelligence, vol. 113, p. 104914, 2022.
  • [48] N. Al-Qubaydhi, A. Alenezi, T. Alanazi, A. Senyor, N. Alanezi, B. Alotaibi, M. Alotaibi, A. Razaque, A. A. Abdelhamid, A. Alotaibi, “Detection of unauthorized unmanned aerial vehicles using yolov5 and transfer learning,” Electronics, vol. 11, no. 17, p. 2669, 2022.
  • [49] S. L. Flórez, A. González-Briones, G. Hernández, F. de la Prieta, “Automated counting via multicolumn network and cytosmart exact fl microscope,” in International Symposium on Ambient Intelligence, 2022, pp. 207–218, Springer.
Data source: Dialnet