用卷积神经网络对帕金森病进行多模式视网膜成像分类
Alexander Richardson1,2,3, Anita Kundu1,2, Ricardo Henao2,3
1Duke Eye Center, Department of Ophthalmology, Duke University School of Medicine, Durham, NC, USA.
Translational vision science & technology
|August 13, 2024
概括
这项研究开发了一个卷积神经网络 (CNN),使用视网膜图像来识别帕金森病 (PD). 人工智能模型实现了高准确度,显示了通过眼部扫描更早诊断PD的潜力.
科学领域:
- 眼科医生 眼科 眼科
- 神经学 神经学
- 人工智能的人工智能
背景情况:
- 视网膜结构和微血管变化与大脑变化相关.
- 以前的研究表明,帕金森病 (PD) 患者的视网膜有明显的差异.
- 机器学习模型已经显示出从视网膜数据中检测神经退行性疾病 (如阿尔茨海默氏症) 的前景.
研究的目的:
- 开发和评估一个卷积神经网络 (CNN) 用于分类帕金森病 (PD) 使用多模式视网膜成像.
- 通过AI评估不同视网膜成像模式在PD检测中的有效性.
主要方法:
- 一个CNN接受了光学连贯断层扫描 (OCT) 状细胞内状层 (GC-IPL) 厚度图,OCT血管图像斑点图像和超宽场 (UWF) 底部照片的训练.
- 该模型使用预训练的VGG19特征提取器,具有图像特定的转换.
- 使用接收机运行特征 (ROC) 曲线和ROC曲线下的面积 (AUC) 值来评估性能.
主要成果:
- 这项研究包括来自249个对照组的371只眼睛和来自52名PD患者的75只眼睛.
- 最好的CNN变种在PD的分类中达到0.918的高AUC.
- 超广场 (UWF) 彩色照片被证明是最有效的成像输入,而GC-IPL厚度图是最不起作用的.
结论:
- 美国有线电视新闻网的一项试点项目成功地从视网膜图像中识别出患有帕金森病的个体,证明了概念的证明.
- 这项研究强调了视网膜成像和人工智能用于PD检测的潜力.
- 需要更大的成像数据集来开发用于自动化PD诊断的临床级算法.
相关概念视频
01:37Neural Regulation
39.2K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.2K
01:15Parkinson's Disease: Overview
501
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...
501
01:24Parkinson's Disease: Treatment
240
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...
240