Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging

Abstract Objective To explore the potential of radiomics features derived from T2-weighted fluid-attenuated inversion recovery (T2W FLAIR) images to distinguish idiopathic Parkinson’s disease (PD) patients from healthy controls (HCs). Methods T2W FLAIR images from 1727 subjects were retrospectively...

Full description

Saved in:
Bibliographic Details
Main Authors: Junyan Fu, Hongyi Chen, Chengling Xu, Zhongzheng Jia, Qingqing Lu, Haiyan Zhang, Yue Hu, Kun Lv, Jun Zhang, Daoying Geng
Format: Article
Language:English
Published: SpringerOpen 2025-04-01
Series:Insights into Imaging
Subjects:
Online Access:https://doi.org/10.1186/s13244-025-01961-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850139132633808896
author Junyan Fu
Hongyi Chen
Chengling Xu
Zhongzheng Jia
Qingqing Lu
Haiyan Zhang
Yue Hu
Kun Lv
Jun Zhang
Daoying Geng
author_facet Junyan Fu
Hongyi Chen
Chengling Xu
Zhongzheng Jia
Qingqing Lu
Haiyan Zhang
Yue Hu
Kun Lv
Jun Zhang
Daoying Geng
author_sort Junyan Fu
collection DOAJ
description Abstract Objective To explore the potential of radiomics features derived from T2-weighted fluid-attenuated inversion recovery (T2W FLAIR) images to distinguish idiopathic Parkinson’s disease (PD) patients from healthy controls (HCs). Methods T2W FLAIR images from 1727 subjects were retrospectively obtained from five cohorts and divided into a training set (395 PD/574 HC), an internal test set (99 PD/144 HC) and an external test set (295 PD/220 HC). Regions of interest (ROIs), including bilateral globus pallidus (GP), putamen (PU), substantia nigra (SN), and red nucleus (RN), were manually delineated. The radiomics features were extracted from ROIs. Six independent machine learning (ML) classifiers were trained on the training set, and validated on the internal and external test sets. Results A selection of five, two, three, and ten highly correlated diagnostic features were identified from SN, RN, GP, and PU regions, respectively. Six ML classifiers were implemented based on the combined 20 radiomics features. In the internal test cohort, the six models achieved AUC of 0.96–0.98 with the accuracy ranging from 0.80 to 0.90. In the external test cohort, the multilayer perceptron model demonstrated the highest AUC of 0.85 (95% CI: 0.80–0.89) with an accuracy of 0.78. Conclusion ML models based on the conventional T2W FLAIR images demonstrated promising diagnostic performance for PD and those models may serve as a basis for future investigations on PD diagnosis with the aid of ML methods. Critical relevance statement Our study confirmed that early screening of Parkinson’s Disease based on the conventional T2W FLAIR images was feasible with the aid of machine learning algorithms in a large multicenter cohort and those models had certain generalization. Key Points Conventional head MRI is routinely performed in Parkinson’s disease (PD) but exhibits inadequate specificity for diagnosis. Machine learning (ML) models based on conventional T2W FLAIR images showed favorable accuracy for PD diagnosis. ML algorithm enables early screening of PD on routine T2W FLAIR sequence. Graphical Abstract
format Article
id doaj-art-1c3053f063bb4d39af32c4279cbec2ba
institution OA Journals
issn 1869-4101
language English
publishDate 2025-04-01
publisher SpringerOpen
record_format Article
series Insights into Imaging
spelling doaj-art-1c3053f063bb4d39af32c4279cbec2ba2025-08-20T02:30:24ZengSpringerOpenInsights into Imaging1869-41012025-04-0116111110.1186/s13244-025-01961-3Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imagingJunyan Fu0Hongyi Chen1Chengling Xu2Zhongzheng Jia3Qingqing Lu4Haiyan Zhang5Yue Hu6Kun Lv7Jun Zhang8Daoying Geng9Department of Radiology, Huashan Hospital, Fudan UniversityAcademy for Engineering and Technology, Fudan UniversityDepartment of Radiology, Huashan Hospital, Fudan UniversityDepartment of Radiology, Affiliated Hospital of Nantong UniversityDepartment of Radiology, The First Affiliated Hospital of Ningbo UniversityDepartment of Radiology, The Second Affiliated Hospital of Xuzhou Medical UniversityDepartment of Radiology, Huashan Hospital, Fudan UniversityDepartment of Radiology, Huashan Hospital, Fudan UniversityDepartment of Radiology, Huashan Hospital, Fudan UniversityDepartment of Radiology, Huashan Hospital, Fudan UniversityAbstract Objective To explore the potential of radiomics features derived from T2-weighted fluid-attenuated inversion recovery (T2W FLAIR) images to distinguish idiopathic Parkinson’s disease (PD) patients from healthy controls (HCs). Methods T2W FLAIR images from 1727 subjects were retrospectively obtained from five cohorts and divided into a training set (395 PD/574 HC), an internal test set (99 PD/144 HC) and an external test set (295 PD/220 HC). Regions of interest (ROIs), including bilateral globus pallidus (GP), putamen (PU), substantia nigra (SN), and red nucleus (RN), were manually delineated. The radiomics features were extracted from ROIs. Six independent machine learning (ML) classifiers were trained on the training set, and validated on the internal and external test sets. Results A selection of five, two, three, and ten highly correlated diagnostic features were identified from SN, RN, GP, and PU regions, respectively. Six ML classifiers were implemented based on the combined 20 radiomics features. In the internal test cohort, the six models achieved AUC of 0.96–0.98 with the accuracy ranging from 0.80 to 0.90. In the external test cohort, the multilayer perceptron model demonstrated the highest AUC of 0.85 (95% CI: 0.80–0.89) with an accuracy of 0.78. Conclusion ML models based on the conventional T2W FLAIR images demonstrated promising diagnostic performance for PD and those models may serve as a basis for future investigations on PD diagnosis with the aid of ML methods. Critical relevance statement Our study confirmed that early screening of Parkinson’s Disease based on the conventional T2W FLAIR images was feasible with the aid of machine learning algorithms in a large multicenter cohort and those models had certain generalization. Key Points Conventional head MRI is routinely performed in Parkinson’s disease (PD) but exhibits inadequate specificity for diagnosis. Machine learning (ML) models based on conventional T2W FLAIR images showed favorable accuracy for PD diagnosis. ML algorithm enables early screening of PD on routine T2W FLAIR sequence. Graphical Abstracthttps://doi.org/10.1186/s13244-025-01961-3Parkinson’s diseaseMachine learningMagnetic resonance imagingSubstantia nigraPutamen
spellingShingle Junyan Fu
Hongyi Chen
Chengling Xu
Zhongzheng Jia
Qingqing Lu
Haiyan Zhang
Yue Hu
Kun Lv
Jun Zhang
Daoying Geng
Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
Insights into Imaging
Parkinson’s disease
Machine learning
Magnetic resonance imaging
Substantia nigra
Putamen
title Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
title_full Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
title_fullStr Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
title_full_unstemmed Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
title_short Harnessing routine MRI for the early screening of Parkinson’s disease: a multicenter machine learning study using T2-weighted FLAIR imaging
title_sort harnessing routine mri for the early screening of parkinson s disease a multicenter machine learning study using t2 weighted flair imaging
topic Parkinson’s disease
Machine learning
Magnetic resonance imaging
Substantia nigra
Putamen
url https://doi.org/10.1186/s13244-025-01961-3
work_keys_str_mv AT junyanfu harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT hongyichen harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT chenglingxu harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT zhongzhengjia harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT qingqinglu harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT haiyanzhang harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT yuehu harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT kunlv harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT junzhang harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging
AT daoyinggeng harnessingroutinemrifortheearlyscreeningofparkinsonsdiseaseamulticentermachinelearningstudyusingt2weightedflairimaging