浙江医学2024，Vol.46Issue(13)：1381-1386,后插3,7.DOI:10.12056/j.issn.1006-2785.2024.46.13.2023-2313
基于人工智能MRI脑区容积比变化对早期帕金森病的诊断价值
Diagnostic value of artificial intelligence-based MRI brain volume ratio changes in early Parkinson's disease
摘要
Abstract
Objective To explore the diagnostic value of MRI-based brain volume automatic analysis software in early Parkinson's disease(PD).Methods Sixty early-stage PD patients who visited the Department of Neurology at Taizhou Hospital of Zhejiang Province from November 2021 to August 2023,as well as 88 healthy individuals who underwent physical examinations during the same period,were selected as the study subjects.The new automatic segmentation software uAl Sphere was used to accurately calculate the volume ratio of various brain regions.The volume ratios of different brain regions between two groups of research subjects were compared,and differential brain regions and regions of interest were selected to conduct univariate and multivariate logistic regression and joint diagnostic analyses.Results Compared with the healthy control group,there were statistically significant differences in the volume ratio of brain regions such as hippocampus,globus pallidus,putamen,thalamus,and choroid plexus in early PD patients(all P＜0.05).The diagnostic system formed by combining the volume ratios of these five brain regions can be used for the diagnosis of early PD,with an AUC of 0.939.Conclusion The use of uAl Sphere brain volume automatic analysis technology can assist in the clinical diagnosis of early PD.关键词
帕金森病/磁共振成像/脑容积/联影软件/人工智能Key words
Parkinson's disease/Magnetic resonance imaging/Brain volume/United Imaging/Artificial intelligence引用本文复制引用
庞坚信,张黄琦,鲍统安,张美仙,陈邦文,季文斌..基于人工智能MRI脑区容积比变化对早期帕金森病的诊断价值[J].浙江医学,2024,46(13):1381-1386,后插3,7.基金项目
浙江省卫生健康科技计划项目(2021KY1201) （2021KY1201）
