A Unified Deep Learning Approach for Prediction of Parkinson's Disease

TL;DR

This paper introduces a deep learning framework combining convolutional and recurrent neural networks for accurate Parkinson's disease prediction from medical images, leveraging transfer learning across diverse clinical settings.

Contribution

It presents a unified deep learning approach that integrates knowledge from DNNs for Parkinson's diagnosis, enabling effective prediction across various medical imaging environments.

Findings

High accuracy in Parkinson's prediction across multiple datasets

Effective transfer learning across different medical imaging modalities

Robustness of the model in real clinical environments

Abstract

The paper presents a novel approach, based on deep learning, for diagnosis of Parkinson's disease through medical imaging. The approach includes analysis and use of the knowledge extracted by Deep Convolutional and Recurrent Neural Networks (DNNs) when trained with medical images, such as Magnetic Resonance Images and DaTscans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson's across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson's, using different medical image sets from real environments.