• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

AGMA-PESS：一种基于深度学习的婴儿姿势估计器和序列选择器软件，用于一般运动评估。

AGMA-PESS: a deep learning-based infant pose estimator and sequence selector software for general movement assessment.

作者信息

Soualmi Ameur, Alata Olivier, Ducottet Christophe, Petitjean-Robert Anne, Plat Aurélie, Patural Hugues, Giraud Antoine

机构信息

Laboratoire Hubert Curien UMR 5516, CNRS, Institut d'Optique Graduate School Université Jean Monnet Saint-Etienne, Saint-Etienne, France.

INSERM, U1059 SAINBIOSE, Université Jean Monnet, Saint-Étienne, France.

出版信息

Front Pediatr. 2024 Dec 18;12:1465632. doi: 10.3389/fped.2024.1465632. eCollection 2024.

DOI:10.3389/fped.2024.1465632
PMID:39744216
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11688355/
Abstract

The General Movement Assessment (GMA) is a validated evaluation of brain maturation essential to shaping early individual developmental trajectories of preterm infants. To ensure a reliable GMA, preterm infants should be recorded for 30 to 60 min before manually selecting at least three sequences with general movements. This time-consuming task of manually selecting short video sequences from lengthy recordings impedes its implementation within the Neonatal Unit. Moreover, an accurate pose estimation tool for preterm infants is paramount to developing the field of GMA automation. We introduce the AGMA Pose Estimator and Sequence Selector (AGMA-PESS) software, based on the state-of-the-art deep learning infant pose estimation network, to automatically select the video sequences for GMA at preterm and writhing ages and estimate the pose of infants in 2D. Its simplicity and efficiency make AGMA-PESS a valuable tool to promote GMA use within the Neonatal Unit, both for clinical practice and research purposes.

摘要

全身运动评估（GMA）是一种经过验证的对大脑成熟度的评估，对于塑造早产儿早期个体发育轨迹至关重要。为确保可靠的GMA，应在手动选择至少三个具有全身运动的序列之前，对早产儿进行30至60分钟的记录。从冗长的记录中手动选择短视频序列这项耗时的任务阻碍了其在新生儿病房的实施。此外，用于早产儿的精确姿势估计工具对于GMA自动化领域的发展至关重要。我们基于最先进的深度学习婴儿姿势估计网络，引入了AGMA姿势估计器和序列选择器（AGMA-PESS）软件，以自动选择早产儿和扭动期婴儿的GMA视频序列，并估计婴儿的二维姿势。其简单性和高效性使AGMA-PESS成为促进新生儿病房在临床实践和研究中使用GMA的有价值工具。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/99655316152b/fped-12-1465632-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/a783e49f4e51/fped-12-1465632-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/fe32590a8fad/fped-12-1465632-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/414502b3bff5/fped-12-1465632-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/11b3dcefe15b/fped-12-1465632-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/99655316152b/fped-12-1465632-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/a783e49f4e51/fped-12-1465632-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/fe32590a8fad/fped-12-1465632-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/414502b3bff5/fped-12-1465632-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/11b3dcefe15b/fped-12-1465632-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cf33/11688355/99655316152b/fped-12-1465632-g005.jpg

相似文献

1
AGMA-PESS: a deep learning-based infant pose estimator and sequence selector software for general movement assessment.AGMA-PESS：一种基于深度学习的婴儿姿势估计器和序列选择器软件，用于一般运动评估。
Front Pediatr. 2024 Dec 18;12:1465632. doi: 10.3389/fped.2024.1465632. eCollection 2024.
2
Mean 3D Dispersion for Automatic General Movement Assessment of Preterm Infants.用于早产儿自动全身运动评估的平均三维离散度
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-5. doi: 10.1109/EMBC40787.2023.10340961.
3
A self-supervised spatio-temporal attention network for video-based 3D infant pose estimation.基于视频的 3D 婴儿姿态估计的自监督时空注意网络。
Med Image Anal. 2024 Aug;96:103208. doi: 10.1016/j.media.2024.103208. Epub 2024 May 18.
4
General movement optimality score and general movements trajectories following early parent-administrated physiotherapy in the neonatal intensive care unit.早期在新生儿重症监护病房中进行家长主导的物理治疗后，一般性运动的最优得分和一般性运动轨迹。
Early Hum Dev. 2021 Dec;163:105488. doi: 10.1016/j.earlhumdev.2021.105488. Epub 2021 Oct 14.
5
Preterm and writhing movements: is it possible to predict fidgety movements in preterm infants?扭动和扭动运动：是否可以预测早产儿的烦躁运动？
J Perinatol. 2021 Oct;41(10):2442-2448. doi: 10.1038/s41372-021-01064-z. Epub 2021 May 13.
6
Semi-supervised body parsing and pose estimation for enhancing infant general movement assessment.用于增强婴儿一般运动评估的半监督身体解析与姿势估计
Med Image Anal. 2023 Jan;83:102654. doi: 10.1016/j.media.2022.102654. Epub 2022 Oct 14.
7
Comparison of marker-less 2D image-based methods for infant pose estimation.基于无标记二维图像的婴儿姿势估计方法比较。
Sci Rep. 2025 Apr 9;15(1):12148. doi: 10.1038/s41598-025-96206-0.
8
Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk.从高危婴儿的自发性运动预测脑瘫的深度学习方法的开发和验证。
JAMA Netw Open. 2022 Jul 1;5(7):e2221325. doi: 10.1001/jamanetworkopen.2022.21325.
9
General Movements in preterm infants undergoing craniosacral therapy: a randomised controlled pilot-trial.接受颅骶疗法的早产儿的一般运动：一项随机对照试验性研究。
BMC Complement Altern Med. 2016 Jan 13;16:12. doi: 10.1186/s12906-016-0984-5.
10
Automated detection of abnormal general movements from pressure and positional information in hospitalized infants.利用住院婴儿的压力和位置信息自动检测异常的全身运动。
Pediatr Res. 2025 Feb;97(2):598-607. doi: 10.1038/s41390-024-03387-x. Epub 2024 Jul 30.

本文引用的文献

1
Mean 3D Dispersion for Automatic General Movement Assessment of Preterm Infants.用于早产儿自动全身运动评估的平均三维离散度
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-5. doi: 10.1109/EMBC40787.2023.10340961.
2
A Pose-Based Feature Fusion and Classification Framework for the Early Prediction of Cerebral Palsy in Infants.基于姿势的特征融合与分类框架在婴儿脑瘫早期预测中的应用。
IEEE Trans Neural Syst Rehabil Eng. 2022;30:8-19. doi: 10.1109/TNSRE.2021.3138185. Epub 2022 Jan 28.
3
Early Intervention for Children Aged 0 to 2 Years With or at High Risk of Cerebral Palsy: International Clinical Practice Guideline Based on Systematic Reviews.
0 至 2 岁或有脑瘫高风险的儿童的早期干预：基于系统评价的国际临床实践指南。
JAMA Pediatr. 2021 Aug 1;175(8):846-858. doi: 10.1001/jamapediatrics.2021.0878.
4
Novel AI driven approach to classify infant motor functions.新型人工智能驱动的婴儿运动功能分类方法。
Sci Rep. 2021 May 10;11(1):9888. doi: 10.1038/s41598-021-89347-5.
5
Writhing Movement Detection in Newborns on the Second and Third Day of Life Using Pose-Based Feature Machine Learning Classification.基于姿势特征的机器学习分类法检测出生后第二和第三天新生儿的扭动运动。
Sensors (Basel). 2020 Oct 22;20(21):5986. doi: 10.3390/s20215986.
6
Computer Vision to Automatically Assess Infant Neuromotor Risk.计算机视觉自动评估婴儿神经运动风险。
IEEE Trans Neural Syst Rehabil Eng. 2020 Nov;28(11):2431-2442. doi: 10.1109/TNSRE.2020.3029121. Epub 2020 Nov 6.
7
Early general movements are associated with developmental outcomes at 4.5-5 years.早期一般性运动与 4.5-5 岁时的发育结果相关。
Early Hum Dev. 2020 Sep;148:105115. doi: 10.1016/j.earlhumdev.2020.105115. Epub 2020 Jun 20.
8
Neural substrate and clinical significance of general movements: an update.全身运动的神经基础及临床意义：最新进展
Dev Med Child Neurol. 2018 Jan;60(1):39-46. doi: 10.1111/dmcn.13540. Epub 2017 Aug 23.
9
The qualitative assessment of general movements in preterm, term and young infants--review of the methodology.早产、足月及幼儿期婴儿一般运动的定性评估——方法学综述
Early Hum Dev. 1997 Nov 24;50(1):47-60. doi: 10.1016/s0378-3782(97)00092-3.