帕金森病的分类在黑色物质的基于补丁的MRI中
Sayyed Shahid Hussain1, Xu Degang1, Pir Masoom Shah2,3
1School of Automation, Central South University, Changsha 410010, China.
Diagnostics (Basel, Switzerland)
|September 9, 2023
概括
这项研究引入了使用卷积神经网络 (CNN) 的帕金森病 (PD) 新型计算机辅助诊断系统. 与传统的机器学习方法相比,CNN模型在MRI扫描中诊断PD时取得了更高的准确性.
科学领域:
- 神经学 神经学
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 帕金森病 (PD) 是一种影响运动功能的渐进性神经疾病,由于复杂的表现和重叠的症状,诊断具有挑战,导致~25%的不准确性.
- 目前的诊断方法通常依赖于手工制作的功能和传统的机器学习,这些功能可能无法捕捉到PD的复杂模式.
- 中脑中黑质区域是PD受影响的关键区域,使其成为诊断成像的关键目标.
研究的目的:
- 提出和评估使用卷积神经网络 (CNN) 的帕金森病计算机辅助诊断系统.
- 利用CNN进行自动特征提取,并从T2加权的MRI扫描中学习,以改善PD诊断.
- 将拟议的CNN系统的诊断性能与既有机器学习技术进行比较.
主要方法:
- 利用来自帕金森病进展标记计划 (PPMI) 数据集的T2加权MRI数据,包括患有PD的患者和健康对照 (HC).
- 提取了中脑切片,记录它们进行对齐,并使用33x33的窗口将黑质区域隔离出来进行分析.
- 开发并实施一个卷积神经网络 (CNN) 模型,根据所选的MRI区域对PD进行分类.
主要成果:
- 拟议的基于CNN的系统在与传统的机器学习算法 (如Naive Bayes,决策树,支持矢量机器和人工神经网络) 相比,显示出更高的诊断准确性.
- 标准性能指标包括精度,灵敏度,特异性和曲线下的面积 (AUC) 用于全面评估.
- CNN模型有效地从MRI扫描中学习和提取相关特征,为其在PD检测中的卓越性能做出了贡献.
结论:
- 卷积神经网络提供了一个从MRI数据中准确和自动诊断帕金森病的有希望的方法.
- 开发的CNN系统显示出克服与当前方法相关的诊断不准确性的潜力.
- 进一步的研究可以探索更大的数据集和先进的CNN架构,以提高PD诊断和患者管理.
更多相关视频
06:09Semi-Quantitative Determination of Dopaminergic Neuron Density in the Substantia Nigra of Rodent Models using Automated Image Analysis
Published on: February 2, 2021
4.5K
06:07Author Spotlight: Establishing a New Fluorescence-Based Protocol for In Vivo Mitochondrial Morphology Analysis in Parkinson's Disease
Published on: June 23, 2023
1.6K
相关概念视频
Neural Regulation
39.5K
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.
39.5K
Parkinson's Disease: Overview
592
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...
592
Parkinson's Disease: Treatment
295
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...
295
