从视频中分析帕金森病的基于姿势的震类型和水平
Haozheng Zhang1, Edmond S L Ho2, Francis Xiatian Zhang1
1Department of Computer Science, Durham University, Durham, UK.
International journal of computer assisted radiology and surgery
|January 18, 2024
概括
一个新的深度学习系统可以从视频中准确识别帕金森 (PT),帮助早期诊断帕金森病 (PD). 这种具有成本效益的工具支持临床医生,特别是在资源有限的地方.
科学领域:
- 神经学 神经学
- 人工智能的人工智能
- 生物医学工程 生物医学工程
背景情况:
- 目前的帕金森病 (PD) 诊断依赖于临床检查,准确度不同 (73-84%) 并取决于评估者的经验.
- 需要一个自动化,可解释的系统来提高PD诊断决策的稳定性.
研究的目的:
- 开发和验证基于深度学习的系统 (SPA-PTA) 来分类帕金森 (PT) 并估计其严重程度.
- 支持使用消费级视频早期检测PD.
主要方法:
- 使用了一种具有轻量级金字塔式通道挤压融合架构的新型注意力模块进行PT分析.
- 输入数据包括面向前方的个人的消费者级视频.
- 使用PT分类和严重程度估计任务的leave-one-out交叉验证来评估系统性能.
主要成果:
- 实现了91.3%的准确性和80.0%的F1分数,用于对PT与非PT进行分类.
- 在多类震严重程度评级任务中获得了76.4%的准确率和76.7%的F1分数.
结论:
- 该SPA-PTA系统提供了具有成本效益的PT分类和严重程度估计,作为未被诊断的PD患者的早期预警.
- 在资源有限的环境中提供PD诊断支持的潜在解决方案.
相关概念视频
01:15Parkinson's Disease: Overview
551
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...
551
01:24Parkinson's Disease: Treatment
272
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...
272