Optimizing Neurodegenerative Disease Classification with Canny Segmentation and Voting Classifier: An Imbalanced Dataset Study

Abstract

This study explores the efficacy of a Voting Classifier, combining Logistic Regression, Random Forest, and Gaussian Naive Bayes, in the classification of neurodegenerative diseases, focusing on Alzheimer's Disease (AD), Parkinson’s Disease (PD), and control groups. Utilizing a dataset pre-processed with Canny segmentation and Hu Moments feature extraction, the research aimed to address the challenges posed by imbalanced datasets in medical image classification. The classifier's performance was evaluated through a 5-fold cross-validation approach, with metrics including accuracy, precision, recall, and F1-Score. The results revealed a consistent recall rate of approximately 46% across all folds, indicating the model's effectiveness in identifying cases of neurodegenerative diseases. However, the precision and F1-Score were notably lower, averaging around 22% and 29%, respectively, underscoring the difficulties in achieving accurate classification in imbalanced datasets. The study contributes to the understanding of machine learning applications in medical diagnostics, specifically in the challenging context of neurodegenerative disease classification. It highlights the potential of using advanced image processing techniques combined with machine learning ensembles in enhancing diagnostic accuracy. However, it also draws attention to the inherent challenges in such approaches, particularly regarding precision in imbalanced datasets. Recommendations for future research include exploring data balancing techniques, alternative feature extraction methods, and different machine learning algorithms to improve the precision and overall performance. Additionally, applying the model to a broader and more diverse dataset could provide more generalizable and robust findings. This study is significant for researchers and practitioners in medical imaging and machine learning, offering insights into the complexities and potential of automated disease classification