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

IF 3.4 Q1 Health Professions Animal models and experimental medicine Pub Date : 2025-01-23 DOI:10.1002/ame2.12530

Yangzhen Wang, Feng Su, Rixu Cong, Mengna Liu, Kaichen Shan, Xiaying Li, Desheng Zhu, Yusheng Wei, Jiejie Dai, Chen Zhang, Yonglu Tian

{"title":"High-throughput markerless pose estimation and home-cage activity analysis of tree shrew using deep learning","authors":"Yangzhen Wang, Feng Su, Rixu Cong, Mengna Liu, Kaichen Shan, Xiaying Li, Desheng Zhu, Yusheng Wei, Jiejie Dai, Chen Zhang, Yonglu Tian","doi":"10.1002/ame2.12530","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>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.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>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.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>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.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>This study provides an efficient tool for quantifying and understand tree shrews' natural behaviors</p>\n </section>\n </div>","PeriodicalId":93869,"journal":{"name":"Animal models and experimental medicine","volume":"8 5","pages":"896-905"},"PeriodicalIF":3.4000,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ame2.12530","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Animal models and experimental medicine","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ame2.12530","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Health Professions","Score":null,"Total":0}

引用次数: 0

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

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于深度学习的树鼩高通量无标记姿态估计和家笼活动分析。

背景：对树鼩丰富的家笼活动进行量化，为了解树鼩的日常生活规律和建立疾病模型提供了可靠的依据。然而，由于缺乏有效的行为方法，对树鼩行为的研究大多局限于简单的措施，导致许多行为信息的丢失。方法：为了解决这一问题，我们提出了一种深度学习（DL）方法来实现无标记姿态估计，并识别树鼩的多种自发行为，包括饮水、进食、休息和呆在黑暗的房子里等。结果：这种高通量方法可以在较长时间内同时监测16只树鼩的家笼活动。此外，我们还展示了一个具有可靠仪器、范例和分析方法的创新系统，用于研究食物抓取行为。每次抓握的中位持续时间为0.20 s。结论：本研究为定量了解树鼩的自然行为提供了有效的工具。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊