Early and accurate diagnosis of Parkinson's Disease (PD) remains challenging. This study compares deep learning architectures for MRI-based PD classification, introducing the first three-dimensional (3D) implementation of Convolutional Kolmogorov-Arnold Networks (ConvKANs), a new approach that combines convolution layers with adaptive, spline-based activations. We evaluated Convolutional Neural Networks (CNNs), ConvKANs, and Graph Convolutional Networks (GCNs) using three open-source datasets; a total of 142 participants (75 with PD and 67 age-matched healthy controls). For 2D analysis, we extracted 100 axial slices centred on the midbrain from each T1-weighted scan. For 3D analysis, we used the entire volumetric scans. ConvKANs integrate learnable B-spline functions with convolutional layers. GCNs represent MRI data as graphs, theoretically capturing structural relationships that may be overlooked by traditional approaches. Interpretability visualizations, including the first ConvKAN spline activation maps, and projections of graph node embeddings, were depicted. ConvKANs demonstrated high performance across datasets and dimensionalities, achieving the highest 2D AUROC (0.98) in one dataset and matching CNN peak 3D performance (1.00). CNN models performed well, while GCN models improved in 3D analyses, reaching up to 0.97 AUROC. 3D implementations yielded higher AUROC values compared to 2D counterparts across all models. ConvKAN implementation shows promise for MRI analysis in PD classification, particularly in the context of early diagnosis. The improvement in 3D analyses highlights the value of volumetric data in capturing subtle PD-related changes. While MRI is not currently used for PD diagnosis, these findings suggest its potential as a component of a multimodal diagnostic approach, especially for early detection.