Non-human primate models and systems for gait and neurophysiological analysis

Liang, Feng-Yan; Sheng, Yu; Pang, Siqi; Wang, Xiao; Jie, Jing; Gao, Fei; Song, Zhenhua; Li, Binbin; Liao, Wei-Hsin; Yin, Min

doi:10.3389/fnins.2023.1141567

Cited by 7 publications

(2 citation statements)

References 133 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second application is the gait analysis for 3D movements. Non-human primates are not restricted to moving on the ground, and the 3D gait would reflect their abnormal state after modeling treatment Liang et al (2023 ); Thota and Alberts (2013 ). ADPT decreases the pose drift caused by body occlusion of single-view frames, which would reduce the error of 3D gait reconstruction.…”

Section: Discussionmentioning

confidence: 99%

Anti-drift pose tracker (ADPT): A transformer-based network for robust animal pose estimation cross-species

Tang,

Han,

Sun

et al. 2024

Preprint

View full text Add to dashboard Cite

Deep learning-based methods for animal pose estimation have recently made substantial progress in improving the accuracy and efficiency of quantitative descriptions of animal behavior. However, these methods commonly suffer from tracking drifts, i.e., sudden jumps in the estimated position of a body point due to noise, thus reducing the reliability of behavioral study results. Here, we present a transformer-based animal pose estimation tool, called Anti-Drift Pose Tracker (ADPT), for eliminating tracking drifts in behavior analysis. To verify the anti-drift performance of ADPT, we conduct extensive experiments in multiple cross-species datasets, including long-term recorded mouse and monkey behavioral datasets collected by ourselves, as well as two public Drosophilas and macaques datasets. Our results show that ADPT greatly reduces the rate of tracking drifts, and significantly outperforms the existing deep-learning methods, such as DeepLabCut, SLEAP, and DeepPoseKit. Moreover, ADPT is compatible with multi-animal pose estimation, enabling animal identity recognition and social behavioral study. Specifically, ADPT provided an identification accuracy of 93.16% for 10 unmarked mice, and of 90.36% for free-social unmarked mice which can be further refined to 99.72%. Compared to other multi-stage network-based tools like multi-animal DeepLabCut, SIPEC and Social Behavior Atlas, the end-to-end structure of ADPT supports its lower computational costs and meets the needs of real-time analysis. Together, ADPT is a versatile anti-drift animal behavior analysis tool, which can greatly promote the accuracy, robustness, and reproducibility of animal behavioral studies. The code of ADPT is available at https://github.com/tangguoling/ADPT.

show abstract

Section: Discussionmentioning

confidence: 99%

Anti-drift pose tracker (ADPT): A transformer-based network for robust animal pose estimation cross-species

Tang,

Han,

Sun

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Non-human primates, e.g. baboons, are sufficiently similar to humans in anatomy and habitus, and their usefulness in medical and evolutionary research is widely accepted (Aerts et al, 2023a;Boulinguez-Ambroise et al, 2021;Druelle et al, 2021;Liang et al, 2023;Nardone et al, 2017). Their developmental trajectory is less steep than that of piglets (Ch.…”

Section: Piglets Baboons and Humansmentioning

confidence: 99%

Methodological Advances in Studying Postnatal Locomotor Development

Mielke¹

2023

Preprint

View full text Add to dashboard Cite

We study piglet locomotion, attempting to falsify a difference that is due to birth weight category.This requires a methodological foundation on topics unfamiliar to most Biologists (Fourier Analysis, probabilistic models), which I introduce in dedicated chapters._Part I: Kinematic Analysis_+ I will introduce Fourier Methods with a practical guide and review its occurrence specifically in the field of locomotor biomechanics (Ch. 2).+ The power of Fourier tools is then unleashed onto a large cross-species study that covers most of the ungulate clade (Ch. 3, Mielke et al., 2019)._Part II: Probabilistic Modeling_+ Processing complex kinematic data, I will introduce the basics of probabilistic modeling (Ch. 4) in a "tiny textbook of statistics"...+ ... before turning around the conventional modeling strategy and applying it to piglets (Ch. 5, Mielke et al., 2023)._Part III: Dynamics_+ Kinematics are just half of locomotor research: the study of forces and moments is reviewed and summarized in another overview chapter (Ch. 6).+ To calculate joint moments, one needs to measure inertial properties, yet it turns out that these are not trivial to retrieve from x-ray tomographic images (Ch. 7).The thesis closes with a general discussion to round up and project the presented work to potential future applications (Ch. 8).

show abstract