High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning

Abstract Background Quantifying the rich home‐cage activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models. However, due to the lack of effective behavioral methods, most efforts on tree shrew behavior are limited to simple measures, res...

Full description

Saved in:
Bibliographic Details
Main Authors: Yangzhen Wang, Feng Su, Rixu Cong, Mengna Liu, Kaichen Shan, Xiaying Li, Desheng Zhu, Yusheng Wei, Jiejie Dai, Chen Zhang, Yonglu Tian
Format: Article
Language:English
Published: Wiley 2025-05-01
Series:Animal Models and Experimental Medicine
Subjects:
Online Access:https://doi.org/10.1002/ame2.12530
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717950182850560
author Yangzhen Wang
Feng Su
Rixu Cong
Mengna Liu
Kaichen Shan
Xiaying Li
Desheng Zhu
Yusheng Wei
Jiejie Dai
Chen Zhang
Yonglu Tian
author_facet Yangzhen Wang
Feng Su
Rixu Cong
Mengna Liu
Kaichen Shan
Xiaying Li
Desheng Zhu
Yusheng Wei
Jiejie Dai
Chen Zhang
Yonglu Tian
author_sort Yangzhen Wang
collection DOAJ
description Abstract Background Quantifying the rich home‐cage activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models. However, due to the lack of effective behavioral methods, most efforts on tree shrew behavior are limited to simple measures, resulting in the loss of much behavioral information. Methods To address this issue, we present a deep learning (DL) approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews, including drinking, eating, resting, and staying in the dark house, etc. Results This high‐throughput approach can monitor the home‐cage activities of 16 tree shrews simultaneously over an extended period. Additionally, we demonstrated an innovative system with reliable apparatus, paradigms, and analysis methods for investigating food grasping behavior. The median duration for each bout of grasping was 0.20 s. Conclusion This study provides an efficient tool for quantifying and understand tree shrews' natural behaviors
format Article
id doaj-art-a89477b3b5ac49448363660438b953a6
institution DOAJ
issn 2576-2095
language English
publishDate 2025-05-01
publisher Wiley
record_format Article
series Animal Models and Experimental Medicine
spelling doaj-art-a89477b3b5ac49448363660438b953a62025-08-20T03:12:31ZengWileyAnimal Models and Experimental Medicine2576-20952025-05-018589690510.1002/ame2.12530High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learningYangzhen Wang0Feng Su1Rixu Cong2Mengna Liu3Kaichen Shan4Xiaying Li5Desheng Zhu6Yusheng Wei7Jiejie Dai8Chen Zhang9Yonglu Tian10Department of Automation Tsinghua University Beijing ChinaCollege of Future Technology Peking University Beijing ChinaMinistry of Education, Key Laboratory of Cell Proliferation and Differentiation College of Life Sciences, Peking University Beijing ChinaSchool of Basic Medical Sciences Beijing Key Laboratory of Neural Regeneration and Repair, Advanced Innovation Center for Human Brain Protection, Capital Medical University Beijing ChinaDepartment of Automation Tsinghua University Beijing ChinaLaboratory Animal Center School of Life Sciences, Peking University Beijing ChinaLaboratory Animal Center School of Life Sciences, Peking University Beijing ChinaLaboratory Animal Center School of Life Sciences, Peking University Beijing ChinaInstitute of Medical Biology Chinese Academy of Medical Sciences and Peking Union Medical College Kunming ChinaSchool of Basic Medical Sciences Beijing Key Laboratory of Neural Regeneration and Repair, Advanced Innovation Center for Human Brain Protection, Capital Medical University Beijing ChinaSchool of Psychological and Cognitive Sciences IDG/McGovern Institute for Brain Research, Peking University Beijing ChinaAbstract Background Quantifying the rich home‐cage activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models. However, due to the lack of effective behavioral methods, most efforts on tree shrew behavior are limited to simple measures, resulting in the loss of much behavioral information. Methods To address this issue, we present a deep learning (DL) approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews, including drinking, eating, resting, and staying in the dark house, etc. Results This high‐throughput approach can monitor the home‐cage activities of 16 tree shrews simultaneously over an extended period. Additionally, we demonstrated an innovative system with reliable apparatus, paradigms, and analysis methods for investigating food grasping behavior. The median duration for each bout of grasping was 0.20 s. Conclusion This study provides an efficient tool for quantifying and understand tree shrews' natural behaviorshttps://doi.org/10.1002/ame2.12530deep learningfood graspinghome‐cage activitypose estimationtree shrew
spellingShingle Yangzhen Wang
Feng Su
Rixu Cong
Mengna Liu
Kaichen Shan
Xiaying Li
Desheng Zhu
Yusheng Wei
Jiejie Dai
Chen Zhang
Yonglu Tian
High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
Animal Models and Experimental Medicine
deep learning
food grasping
home‐cage activity
pose estimation
tree shrew
title High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
title_full High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
title_fullStr High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
title_full_unstemmed High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
title_short High‐throughput markerless pose estimation and home‐cage activity analysis of tree shrew using deep learning
title_sort high throughput markerless pose estimation and home cage activity analysis of tree shrew using deep learning
topic deep learning
food grasping
home‐cage activity
pose estimation
tree shrew
url https://doi.org/10.1002/ame2.12530
work_keys_str_mv AT yangzhenwang highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT fengsu highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT rixucong highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT mengnaliu highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT kaichenshan highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT xiayingli highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT deshengzhu highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT yushengwei highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT jiejiedai highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT chenzhang highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning
AT yonglutian highthroughputmarkerlessposeestimationandhomecageactivityanalysisoftreeshrewusingdeeplearning