Keywords: Diagnosis/Prediction, biomarkers
Motivation: Improving early Parkinson’s disease diagnosis using advanced MRI techniques and machine learning to detect subtle neuroanatomical and microstructural changes.
Goal(s): To develop a machine learning model using quantitative MRI features to accurately diagnose early-stage Parkinson’s disease.
Approach: This study used QSM and DKI features, analyzed with an SVM model, to differentiate early-stage Parkinson’s disease from healthy controls and advanced-stage PD.
Results: The SVM model demonstrated moderate accuracy in detecting early-stage PD (accuracy: 0.78, AUC: 0.90) and high accuracy for advanced-stage PD (accuracy: 0.97, AUC: 0.97), with DKI's kurtosis feature crucial for classification.
Impact: This study demonstrates the potential of combining QSM and DKI features to improve early-stage Parkinson's disease diagnosis, offering clinicians a non-invasive tool for detection. It paves the way for future research into MRI-based biomarkers for disease progression monitoring.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords