Parkinson's Disease Detection with Ensemble Architectures based on ILSVRC Models
This work addresses Parkinson's Disease diagnosis for medical applications, but it is incremental as it applies existing ensemble methods to a specific domain.
The paper tackled Parkinson's Disease detection from MR brain images by proposing ensemble architectures based on ILSVRC models, achieving up to 95% detection accuracy and showing that pretraining on unrelated ImageNet data improves performance when training data is limited.
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.