An Explainable AI System for Parkinson’s Disease Diagnosis from MRI Images
Date
2026
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
university of bordj bou arreridj
Abstract
Parkinson’s disease, one of the most common neurodegenerative disorders worldwide, is
still difficult to identify in its early stages with traditional clinical techniques. A deep learningbased
method for automatically identifying Parkinson’s disease from brain MRI pictures is
presented in this thesis. The NTUA Parkinson dataset, which consists of over 43,000 brain
MRI pictures categorized into PD and Non-PD classes, was used to refine the Xception convolutional
neural network, which had previously been trained on ImageNet. The model was
tested as a feature extractor in conjunction with two machine learning classifiers, Random Forest
(81.40%) and XGBoost (79.13%), as well as as a stand-alone deep learning classifier with
an accuracy of 84.19%.To ensure interpretability, three Explainable AI (XAI) techniques were
applied: Grad-CAM for visual explanation, SHAP for quantifying feature importance, and a
Grad-CAM-based segmentation approach to localize the brain regions most associated with
the disease, particularly the Substantia Nigra and Basal Ganglia. Finally, a fully functional
desktop application, ParkinsonAI, was developed using CustomTkinter to integrate detection,
patient management, XAI visualization, and medical report generation, complemented by a
commercial web platform built with PHP and JavaScript for distribution to researchers and
healthcare institutions.
Description
Keywords
Parkinson’s Disease, Magnetic Resonance Imaging (MRI), NTUA Dataset, Deep Learning, Convolutional Neural Networks (CNNs), Xception, Transfer Learning, Ran iv dom Forest, XGBoost, Explainable Artificial Intelligence (XAI), Grad-CAM, SHAP iv