Related Experiment Video
Updated: May 10, 2025
Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
Published on: February 19, 2021
Harnessing routine MRI for the early screening of Parkinson's disease: a multicenter machine learning study using
Junyan Fu1, Hongyi Chen2, Chengling Xu1
1Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China.
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.
Insights
Machine learning models using T2W FLAIR MRI radiomics show promise for early Parkinson's disease (PD) screening. These models achieved high accuracy in distinguishing PD patients from healthy controls in a large multicenter study.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence
Background:
- Conventional MRI has limited specificity for Parkinson's disease (PD) diagnosis.
- Radiomics analysis of T2-weighted fluid-attenuated inversion recovery (T2W FLAIR) images offers potential for enhanced diagnostic capabilities.
Purpose of the Study:
- To evaluate the efficacy of radiomics features from T2W FLAIR MRI in differentiating idiopathic PD patients from healthy controls.
- To develop and validate machine learning (ML) models for PD detection using conventional MRI sequences.
Main Methods:
- Retrospective analysis of T2W FLAIR images from 1727 subjects across five cohorts.
- Manual delineation of regions of interest including globus pallidus, putamen, substantia nigra, and red nucleus.
- Extraction of radiomics features and training of six ML classifiers on a training set, with validation on internal and external test sets.
Main Results:
- Key radiomics features were identified from specific brain regions (SN, RN, GP, PU).
- ML models achieved high diagnostic performance, with AUCs ranging from 0.96-0.98 in the internal test set.
- The multilayer perceptron model showed strong performance in the external test set with an AUC of 0.85 and accuracy of 0.78.
Conclusions:
- ML models utilizing T2W FLAIR radiomics demonstrate significant potential for PD diagnosis.
- These models can facilitate early screening of Parkinson's disease using routine MRI sequences.
- The findings support the use of ML-based radiomics as a foundation for future PD diagnostic research.
