DeepLabCut将自动化帕金森症的行为分析
Nabeel Rangoonwala1, Khoi Le1, Vaibhavi Peshattiwar1
1Neurology, University of Toledo, Toledo, Ohio, USA.
概括
人工智能和机器学习显著减少了分析帕金森病老鼠行为所需的时间和劳动力,提供了准确和高效的评分. 这种AI/ML方法通过在行为研究中提供一致,公正的结果来帮助研究人员.
科学领域:
- 神经科学是一个神经科学.
- 行为科学 行为科学
- 人工智能的人工智能
背景情况:
- 帕金森症行为评估传统上依赖于人类评估者,引入偏见和可变性.
- 这需要大样本大小和广泛的视频分析,耗费研究人员宝贵的时间.
- 人工智能/ML的进步为行为研究提供了高效,公正和一致的数据分析.
研究的目的:
- 为了证明AI/ML可以帮助分析老鼠帕金森症行为研究.
- 为了减少在行为分析中的劳动依赖,同时保持准确性.
- 探索AI/ML集成用于自动化行为研究任务.
主要方法:
- 利用DeepLabCut (DLC),一种动物姿势估计软件,在步行测试期间分析帕金森病老鼠的运动行为.
- 在3个小时内通过28个视频 (24个实验视频,4个培训视频) 训练了DLC模型.
- 从视频坐标上量化前腿运动,使用R脚本计算步骤和侧开关,并将结果与手动得分进行比较.
主要成果:
- DLC辅助的评分显示与手动评分的绝对一致性很好 (kappa = 0.9,p < 0.0001).
- 每段视频的分析时间从手动的10-15分钟减少到DLC辅助的3-4分钟.
- 通过DLC辅助的得分实现了与手动得分相提并论的准确性.
结论:
- 人工智能/ML,特别是DLC,为分析帕金森症老鼠行为提供了一种可行和高效的方法.
- 这种方法大大减少了行为数据分析所需的工作量和时间.
- 人工智能和机器学习的整合有望实现这些研究任务的最终完全自动化.
相关概念视频
Parkinson's Disease: Treatment
377
Neurodegenerative disorders, such as Parkinson's Disease (PD), involve the gradual and irreversible destruction of neurons in particular brain areas. These disorders exhibit standard features like proteinopathies, selective vulnerability of some neurons, and an interaction of intrinsic properties, genetics, and environmental influences in neural injury.
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
377
Parkinson's Disease: Overview
703
Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is...
703


