Publications by authors named "Peik Yen Teh"
Classification of Parkinson's disease by deep learning on midbrain MRI.
Front Aging Neurosci
August 2024
Article Synopsis
- Susceptibility map weighted imaging (SMWI) and quantitative susceptibility mapping (QSM) improve the evaluation of nigrosome-1 (N1) and assist in diagnosing Parkinson's disease through deep learning classification algorithms.
- The study compared four diagnostic methods for Parkinson's disease, including a composite marker, two different deep learning models focused on morphological abnormalities and volume, and traditional neuroradiological evaluations.
- Results showed high classification performance across all methods, with the QSM-NMS marker and neuroradiologist evaluations performing the best, indicating good clinical relevance, though further validation is needed for earlier stages of the disease.
Background: Neuromelanin- and iron-sensitive MRI studies in Parkinson's disease (PD) are limited by small sample sizes and lack detailed clinical correlation. In a large case-control PD cohort, we evaluated the diagnostic accuracy of quantitative iron-neuromelanin MRI parameters from the substantia nigra (SN), their radiological utility, and clinical association.
Methods: PD patients and age-matched controls were prospectively recruited for motor assessment and midbrain neuromelanin- and iron-sensitive [quantitative susceptibility mapping (QSM) and susceptibility map-weighted imaging (SMWI)] MRI.