Design and Development of an Implantable System for Behavioral Analysis in Rats Using Machine Vision and Deep Neural Networks for Neuroscience Applications

Zibaii, Mohammad Ismail; Hosseini, Seyedeh Mahshad

Journal of Modern Research Physics

EN FA

Volume 10, Issue 2 (Autumn and Winter 2026) JMRPh 2026, 10(2): 1-17 | Back to browse issues page

Mendeley

Zotero

RefWorks

Zibaii M I, Hosseini S M. Design and Development of an Implantable System for Behavioral Analysis in Rats Using Machine Vision and Deep Neural Networks for Neuroscience Applications. JMRPh 2026; 10 (2) :1-17
URL: http://jmrph.khu.ac.ir/article-1-274-en.html

Design and Development of an Implantable System for Behavioral Analysis in Rats Using Machine Vision and Deep Neural Networks for Neuroscience Applications

Mohammad Ismail Zibaii ^*

, Seyedeh Mahshad Hosseini

Shahid Beheshti University

Abstract: (55 Views)

Accurate and quantitative monitoring of laboratory animals’ behavior, particularly in neuroscience models, is essential for understanding the neural-circuit function and its relation with complex behaviors. In computational ethology, novel systems and algorithms have been developed to make experiments automated, more precise, and less reliant on human observers, which could improve the reproducibility and repeatability of the results. In this research, a system composed of behavior-monitoring cameras and a miniature cranial implant for rats was designed and fabricated to record the animal’s body movement, track eye movements, and measure head orientation. The implant integrates an Inertial Measurement Unit (IMU) to measure head acceleration and angular velocity, as well as an infrared miniature camera for pupillometry; the total weight was about 4.5 g. A custom-developed software tool is designed to capture, process, and visualize the data. Sensor fusion of accelerometer and gyroscope data was used to compute the Euler angles of head motion. Classical computer-vision and deep neural-network algorithms were utilized for image analysis. Thresholding and edge-detection algorithms enabled real-time tracking of the pupil in pigmented rats and the body center, with a processing speed of 25 frames per second, which is suitable for closed-loop neural control. For body-pose estimation and pupil tracking in albino rats, the DeepLabCut networks were used along with data augmentation and transfer learning methods. This approach reduced the pupil detection error to 3.31 pixels after training on 448 labeled images for 30,000 iterations. While deep learning methods provide high accuracy, they impose substantial computational demands; therefore, the suitable algorithm should be chosen based on the experimental objective and available hardware resources. The proposed behavioral monitoring system can be used simultaneously with optogenetics and electrophysiological recordings, which provides a versatile and beneficial tool for advancing research in cognitive neuroscience.

Keywords: Optogenetics, computational ethology, automated video behavior analysis, pupil tracking, neural network

Full-Text [PDF 1296 kb] (27 Downloads)

Type of Study: Applicable | Subject: Special
Received: 2025/10/25 | Accepted: 2025/12/5 | Published: 2026/03/20 | ePublished: 2026/03/20

References

1. [1] J. W. Krakauer, A. A. Ghazanfar, A. Gomez-Marin, M. A. MacIver, and D. Poeppel, "Neuroscience Needs Behavior: Correcting a Reductionist Bias," Neuron, vol. 93, no. 3, pp. 480-490, 2017.

2. [2] S. R. Datta, D. J. Anderson, K. Branson, P. Perona, and A. Leifer, "Computational Neuroethology: A Call to Action," Neuron, vol. 104, no. 1, pp. 11-24, Oct. 2019.

3. [3] A. I. Dell et al., "Automated image-based tracking and its application in ecology," Trends Ecol. Evol., vol. 29, no. 7, pp. 417-428, 2014.

4. [4] Y. Hao, A. M. Thomas, and N. Li, "Fully autonomous mouse behavioral and optogenetic experiments in home-cage," Elife, vol. 10, May 2021.

5. [5] L. Berg, J. Gerdey, and O. A. Masseck, "Optogenetic Manipulation of Neuronal Activity to Modulate Behavior in Freely Moving Mice," JoVE (Journal Vis. Exp., vol. 2020, no. 164, p. e61023, Oct. 2020.

6. [6] D. J. Wallace, D. S. Greenberg, J. Sawinski, S. Rulla, G. Notaro, and J. N. D. Kerr, "Rats maintain an overhead binocular field at the expense of constant fusion," Nature, vol. 498, no. 7452, pp. 65-69, Jun. 2013.

7. [7] H. L. Payne and J. L. Raymond, "Magnetic eye tracking in mice," Elife, vol. 6, Sep. 2017.

8. [8] R. Paylor, "Simultaneous behavioral characterizations: Embracing complexity," Proc. Natl. Acad. Sci. U. S. A., vol. 105, no. 52, pp. 20563-20564, 2008.

9. [9] L. von Ziegler, O. Sturman, and J. Bohacek, "Big behavior: challenges and opportunities in a new era of deep behavior profiling," Neuropsychopharmacology, vol. 46, no. 1, pp. 33-44, 2021.

10. [10] A. F. Meyer, J. Poort, J. O'Keefe, M. Sahani, and J. F. Linden, "A Head-Mounted Camera System Integrates Detailed Behavioral Monitoring with Multichannel Electrophysiology in Freely Moving Mice," Neuron, vol. 100, no. 1, pp. 46-60.e7, Oct. 2018.

11. [11] M. O. Pasquet et al., "Wireless inertial measurement of head kinematics in freely-moving rats," Sci. Rep., vol. 6, no. October, pp. 1-13, 2016.

12. [12] R. Fayat et al., "Inertial measurement of head tilt in rodents: Principles and applications to vestibular research," Sensors, vol. 21, no. 18, pp. 1-22, 2021. [DOI:10.3390/s21186318] [PMID] []

13. [13] W. Abbas and D. M. Rodo, "Computer methods for automatic locomotion and gesture tracking in mice and small animals for neuroscience applications: A survey," Sensors (Switzerland), vol. 19, no. 15, 2019.

14. [14] S. Arvin, R. N. Rasmussen, and K. Yonehara, "EyeLoop: An Open-Source System for High-Speed, Closed-Loop Eye-Tracking," Front. Cell. Neurosci., vol. 15, p. 494, Dec. 2021.

15. [15] M. de Jeu and C. I. De Zeeuw, "Video-oculography in Mice," JoVE (Journal Vis. Exp., no. 65, p. e3971, Jul. 2012. [DOI:10.3791/3971-v] [PMID] []

16. [16] V. Panadeiro, A. Rodriguez, J. Henry, D. Wlodkowic, and M. Andersson, "A review of 28 free animal-tracking software applications: current features and limitations," Lab Anim. (NY)., vol. 50, no. 9, pp. 246-254, 2021.

17. [17] E. Insafutdinov, L. Pishchulin, B. Andres, M. Andriluka, and B. Schiele, "DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model," Lect. Notes Comput. Sci., vol. 9910 LNCS, pp. 34-50, May 2016.

18. [18] A. Mathis et al., "DeepLabCut: markerless pose estimation of user-defined body parts with deep learning," Nat. Neurosci., vol. 21, no. 9, pp. 1281-1289, Sep. 2018.

19. [19] M. W. Mathis and A. Mathis, "Deep learning tools for the measurement of animal behavior in neuroscience.," Curr. Opin. Neurobiol., vol. 60, pp. 1-11, Feb. 2020.

20. [20] A. Mathis, S. Schneider, J. Lauer, and M. W. Mathis, "A Primer on Motion Capture with Deep Learning: Principles, Pitfalls, and Perspectives," Neuron, vol. 108, no. 1, pp. 44-65, 2020.

21. [21] T. D. Pereira et al., "SLEAP: A deep learning system for multi-animal pose tracking," Nat. Methods, vol. 19, no. 4, pp. 486-495, Apr. 2022.

22. [22] J. M. Graving et al., "Deepposekit, a software toolkit for fast and robust animal pose estimation using deep learning," Elife, vol. 8, no. January 2020.

23. [23] T. Nath, A. Mathis, A. C. Chen, A. Patel, M. Bethge, and M. W. Mathis, "Using DeepLabCut for 3D markerless pose estimation across species and behaviors," Nat. Protoc., vol. 14, no. 7, pp. 2152-2176, Jun. 2019. [DOI:10.1038/s41596-019-0176-0] [PMID]

24. [24] O. Sturman et al., "Deep learning-based behavioral analysis reaches human accuracy and is capable of outperforming commercial solutions," Neuropsycho pharmacology, vol. 45, no. 11, pp. 1942-1952, 2020.

25. [25] G. Lopes et al., "Bonsai: An event-based framework for processing and controlling data streams," Front. Neuroinform., vol. 9, no. APR, pp. 1-14, 2015.

26. [26] J. Lauer et al., "Multi-animal pose estimation, identification and tracking with DeepLabCut," Nat. Methods 2022 194, vol. 19, no. 4, pp. 496-504, Apr. 2022. [DOI:10.1038/s41592-022-01443-0] [PMID] []

27. [27] G.-W. Zhang, L. Shen, Z. Li, H. W. Tao, and L. I. Zhang, "Track-Control, an automatic video-based real-time closed-loop behavioral control toolbox," bioRxiv, p. 2019.12.11.873372, Dec. 2019.

28. [28] T. Imai, Y. Takimoto, N. Takeda, A. Uno, H. Inohara, and S. Shimada, "High-Speed Video-Oculography for Measuring Three-Dimensional Rotation Vectors of Eye Movements in Mice. PLOS ONE 11(3), 2016.

29. [29] S. S. Oh and H. L. Narver, "Mouse and rat anesthesia and Analgesia," Current Protocols, vol. 4, no. 2, Feb. 2024.

30. [30] H. Leinonen and H. Tanila, "Vision in laboratory rodents-tools to measure it and implications for behavioral research," Behavioural Brain Research, vol. 352, pp. 172-182, Oct. 2018.

31. [31] S. O. H. Madgwick, A. J. L. Harrison, and R. Vaidyanathan, "Estimation of IMU and MARG orientation using a gradient descent algorithm," IEEE Int. Conf. Rehabil. Robot., pp. 179-185, 2011.

Send email to the article author

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.