Parkinson's Disease Detection with Ensemble Architectures based on ILSVRC Models

TL;DR

This paper introduces ensemble neural network architectures using ILSVRC models for Parkinson's Disease detection from MR images, achieving up to 95% accuracy and highlighting the effectiveness of transfer learning in data-scarce scenarios.

Contribution

The study proposes three novel ensemble architectures combining top ILSVRC models, demonstrating superior performance in PD detection from MR images compared to existing methods.

Findings

Ensemble architectures outperform previous approaches with up to 95% accuracy.

Pretrained models on ImageNet significantly improve detection performance.

Transfer learning is effective when training data is limited.

Abstract

In this work, we explore various neural network architectures using Magnetic Resonance (MR) T1 images of the brain to identify Parkinson's Disease (PD), which is one of the most common neurodegenerative and movement disorders. We propose three ensemble architectures combining some winning Convolutional Neural Network models of ImageNet Large Scale Visual Recognition Challenge (ILSVRC). All of our proposed architectures outperform existing approaches to detect PD from MR images, achieving upto 95\% detection accuracy. We also find that when we construct our ensemble architecture using models pretrained on the ImageNet dataset unrelated to PD, the detection performance is significantly better compared to models without any prior training. Our finding suggests a promising direction when no or insufficient training data is available.