Novel nested patch-based feature extraction model for automated Parkinson's Disease symptom classification using MRI...

Area of Science:

• Neurology
• Medical Imaging
• Machine Learning

Background:

• Parkinson's disease (PD) presents with diverse clinical and MRI findings.
• Accurate classification of PD stages, comorbid dementia, and motor symptoms is crucial for patient management.

Purpose of the Study:

• To develop and validate a handcrafted image classification model for PD.
• The model aims to classify PD stages, detect dementia, and discriminate motor symptoms.

Main Methods:

• A novel automated system (NP-PHOG-MFSMCIMV) was developed using texture features extracted via pyramid histogram-oriented gradient (PHOG).
• Feature selection involved neighborhood component analysis (NCA), Chi2, mRMR, and ReliefF, followed by k-nearest neighbor (kNN) and support vector machine (SVM) classification.
• Iterative majority voting (IMV) was employed for final classification, with results validated using ten-fold cross-validation.

Main Results:

• The NP-PHOG-MFSMCIMV model achieved high accuracies: 99.22% for PD stages, 98.70% for PD dementia, and 99.53% for PD symptoms.
• These results demonstrate the model's effectiveness across different classification tasks within Parkinson's disease.

Conclusions:

• The developed NP-PHOG-MFSMCIMV model exhibits excellent performance in automated classification of Parkinson's disease states.
• Accuracies exceeding 98% validate the model's potential for clinical application in PD assessment.