Abstract
Transcriptomics and metabolomics, two biological research fields that need large numbers of zebrafish embryos, require the removal of unfertilised or nonviable zebrafish embryos. Biologists routinely conduct the tedious, error-prone, and time-consuming manual sorting of embryos. We suggest a novel approach that combines deep learning and microfluidics for automated sorting to overcome this difficulty. To determine the developmental stage and viability of zebrafish eggs, we trained an optimized YOLOv5 model with 95.8% accuracy and a processing speed of 10.6 ms per frame, classifying them as dead, unfertilised, or alive. The eggs are contained in traps on a microfluidic chip using micro-pumps. After that, the deep learning system can identify and automatically sort the eggs according to their viability by positioning this chip on an XYZ motorized stage. The sorting experiment was conducted in two modes: without feedback and with feedback while using the dead egg position. The first one had a sorting success rate of 90% as opposed to 97.9% for the feedback mode with 3 seconds required for each dead egg. This automated approach provides a precise and efficient way to handle a large number of zebrafish embryos while also greatly reducing the workload associated with manual sorting. The success rates attained demonstrate the usefulness and effectiveness of our suggested methodology, opening new avenues for biological research involving accurate embryo selection.
Similar content being viewed by others
Data Availability
The datasets supporting in this study are available from the corresponding author upon reasonable request.
Code availability
The codes used for zebrafish embryo detection and sorting in this study are publicly available at the GitHub repository: https://github.com/AliouneDiouf/zebappdetect.git
References
Mohand Ousaid A, Haliyo S, Régnier S, Hayward V (2020) High fidelity force feedback facilitates manual injection in biological samples. IEEE Robot Autom Lett 5(2):1758–1763. https://doi.org/10.1109/LRA.2020.2969940
Woynarovich E, Horváth L et al (1980) The Artificial Propagation of Warm-water Finfishes: a Manual for Extension. vol 201
Meyers JR (2018) Zebrafish: development of a vertebrate model organism. Curr Protocols Essential Lab Tech 16(1):19
Otterstrom JJ, Lubin A, Payne E, Paran Y (2022) Technologies bringing young zebrafish from a niche field to the limelight. SLAS technology
LaBelle CA, Massaro A, Cortés-Llanos B, Sims CE, Allbritton NL (2021) Image-based live cell sorting. Trends Biotechnol 39(6):613–623
Sadak F, Saadat M, Hajıyavand AM (2020) A vision-guided methodology for the automation of biological cell injection. In: 2020 2nd International conference on electrical, control and instrumentation engineering (ICECIE), pp 1–9. IEEE
Schutera M, Dickmeis T, Mione M, Peravali R, Marcato D, Reischl M, Mikut R, Pylatiuk C (2016) Automated phenotype pattern recognition of zebrafish for high-throughput screening. Bioengineered 7(4):261–265
Graf SF (2011) Automated microinjection with integrated cell sorting, immobilization and collection. PhD thesis, ETH Zurich
Breitwieser H, Dickmeis T, Vogt M, Ferg M, Pylatiuk C (2018) Fully automated pipetting sorting system for different morphological phenotypes of zebrafish embryos. SLAS TECHNOLOGY: Translating Life Sci Innov 23(2):128–133
Shang S, Long L, Lin S, Cong F (2019) Automatic zebrafish egg phenotype recognition from bright-field microscopic images using deep convolutional neural network. Appl Sci 9(16):3362
Ishaq O, Sadanandan SK, Wählby C (2017) Deep fish: deep learning-based classification of zebrafish deformation for high-throughput screening. SLAS Discovery: Adv Life Sci R &D 22(1):102–107
Čapek D, Safroshkin M, Morales-Navarrete H, Toulany N, Arutyunov G, Kurzbach A, Bihler J, Hagauer J, Kick S, Jones F et al (2023) Embryonet: using deep learning to link embryonic phenotypes to signaling pathways. Nat Methods 1–9
Cordero-Maldonado ML, Perathoner S, Kolk K-J, Boland R, Heins-Marroquin U, Spaink HP, Meijer AH, Crawford AD, Sonneville J (2019) Deep learning image recognition enables efficient genome editing in zebrafish by automated injections. PLoS One 14(1):0202377
Jones RA, Renshaw MJ, Barry DJ, Smith JC (2023) Automated staging of zebrafish embryos using machine learning. Wellcome Open Res 7(275):275
Zhu F, Akagi J, Hall CJ, Crosier KE, Crosier PS, Delaage P, Wlodkowic D (2013) A high-throughput lab-on-a-chip interface for zebrafish embryo tests in drug discovery and ecotoxicology. In: Micro/Nano materials, devices, and systems, vol 8923, p 892345. International Society for Optics and Photonics
Lefevre A, Gauthier V, Gauthier M, Bolopion A (2022) Closed-Loop Control of Particles Based on Dielectrophoretic Actuation. IEEE/ASME Trans Mechatron 1:1–10
Choudhury D, Noort D, Iliescu C, Zheng B, Poon K-L, Korzh S, Korzh V, Yu H (2012) Fish and chips: a microfluidic perfusion platform for monitoring zebrafish development. Lab Chip 12(5):892–900
Li Y, Yang F, Chen Z, Shi L, Zhang B, Pan J, Li X, Sun D, Yang H (2014) Zebrafish on a chip: a novel platform for real-time monitoring of drug-induced developmental toxicity. PLoS One 9(4):94792
Chen Z, Liu X, Tang X, Li Y, Liu D, Li Y, Huang Q, Arai T (2022) On-chip automatic trapping and rotating for zebrafish embryo injection. IEEE Robot Autom Lett 7(4):10850–10856
Tang X, Liu X, Li P, Liu F, Kojima M, Huang Q, Arai T (2020) On-chip cell–cell interaction monitoring at single-cell level by efficient immobilization of multiple cells in adjustable quantities. Anal Chem 92(17):11607–11616
Diouf A, Sadak F, Fassi I, Boudaoud M, Legnani G, Haliyo S (2023) Automatic sorting of zebrafish embryos using deep learning. In: 2023 International conference on manipulation, automation and robotics at small scales (MARSS), pp 1–6. IEEE
Westerfield M (2007) The zebrafish book; a guide for the laboratory use of zebrafish (danio rerio). (No Title)
Jocher G (2020) ultralytics/yolov5: V3.1 - Bug Fixes and Performance Improvements. https://doi.org/10.5281/zenodo.4154370
Acknowledgements
The authors thank Edouard Manzoni and Marco Amaral, technicians for the Animal Facility and Engineering Aquatic Models Platform of Sorbonne University for providing us fresh zebrafish eggs.
Funding
This study was funded by the Université franco-italienne (UFI) / Universitá Italo Francese (UIF).
Author information
Authors and Affiliations
Contributions
All authors have made substantial contributions regarding the conception and design of the study. Acquisition of images and analysis (AD, SH), labelling images (AD,AM,DZ), development of the deep learning model (AD, FS), Robotic phase sorting (AD, EG, MB), mechanical design and manufacturing of the microfluidic chip (AD, IF, GL). (AD,FS) wrote the main manuscript text and final approval of the version submitted (all authors).
Corresponding author
Ethics declarations
Competing interest
The authors declare that they have no conflict of interest.
Ethics approval and consent to participate
N/A
Consent for publication
N/A
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Diouf, A., Sadak, F., Gerena, E. et al. Robotic sorting of zebrafish embryos. J Micro-Bio Robot 20, 3 (2024). https://doi.org/10.1007/s12213-024-00167-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12213-024-00167-y