Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Parkinson's Disease: Overview

Parkinson's Disease: Overview

Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is to...

Parkinson Disease ll: Pathophysiology

Parkinson Disease ll: Pathophysiology

Parkinson disease (PD) is a progressive neurodegenerative disorder primarily affecting movement, with additional non-motor features. Its pathophysiology involves complex interactions among genetic susceptibility, environmental exposures, and cellular dysfunction, including dopaminergic neuron loss, protein aggregation, and mitochondrial impairment.Selective NeurodegenerationA key feature is the degeneration of dopaminergic neurons in the substantia nigra pars compacta, leading to reduced...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Systemic immune-inflammation index as a novel biomarker for metabolic syndrome: A systematic review and meta-analysis.

Medicine·2026

Same author

Prevalence and Risk Factors of Celiac Disease in Patients With Non-Alcoholic Fatty Liver Disease: A Meta-Analysis.

JGH open : an open access journal of gastroenterology and hepatology·2026

Same author

Artificial intelligence in contrast-induced nephropathy after coronary interventions: A meta-analysis.

Medicine·2026

Same author

The impact of left ventricular assist devices on kidney function: a systematic review and meta-analysis.

The Egyptian heart journal : (EHJ) : official bulletin of the Egyptian Society of Cardiology·2026

Same author

Precise staging of diabetic retinopathy through machine learning analysis of leakage source characteristics: A Radiomics-driven approach integrating OCT-A and FFA.

Photodiagnosis and photodynamic therapy·2026

Same author

Histogram analysis of diffusion weighted magnetic resonance imaging for predicting isocitrate dehydrogenase 1 mutation status in brain gliomas.

Current journal of neurology·2026

Search research articles

Related Experiment Video

Updated: Jul 7, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Explainable Multimodal Retinal Optical Imaging for Clinical Parkinson's Disease Classification Using Fundus

Zohreh Ganji¹, Farzaneh Nikparast¹, Naser Shoeibi²

¹Department of Medical Physics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Student research committee, Mashhad University of medical sciences, Mashhad, Iran.

Photodiagnosis and Photodynamic Therapy

|July 5, 2026

Summary

This summary is machine-generated.

Retinal imaging and structured data can help classify Parkinson's disease (PD). Combining fundus images with tabular data achieved the highest accuracy, suggesting a promising non-invasive diagnostic approach.

Keywords:

Explainable AI Fundus photography Optical coherence tomography Parkinson’s disease Photodiagnosis Retinal optical imaging

More Related Videos

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

Related Experiment Videos

Last Updated: Jul 7, 2026

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking

Published on: September 26, 2019

Area of Science:

Ophthalmology
Neurology
Medical Imaging

Background:

Retinal optical imaging provides a non-invasive method for diagnosing neurodegenerative diseases.
This study explores the potential of retinal imaging and structured data for Parkinson's disease classification.

Purpose of the Study:

To evaluate the efficacy of bilateral fundus photographs, Optical Coherence Tomography (OCT)-derived retinal features, and structured data in classifying Parkinson's disease (PD) at the participant level.
To compare the performance of tabular-only, image-only, and combined image-tabular data fusion models for PD classification.

Main Methods:

Utilized de-identified bilateral fundus photographs, OCT-derived retinal features, and structured tabular data from the Persian Cohort.
Excluded diagnostic and clinical variables (e.g., UPDRS scores) from predictive inputs.
Evaluated three models: tabular-only, image-only (Siamese EfficientNetV2-B1), and a fused Fundus + Tabular model using Feature-wise Linear Modulation (FiLM).
Employed subject-level splitting, out-of-fold calibration, and control analyses (shuffled-conditioning, image-ablation) to validate the FiLM pathway.

Main Results:

The image-only fundus branch achieved an ROC-AUC of 0.826 and PR-AUC of 0.527.
The fused Fundus + Tabular FiLM model demonstrated superior performance with ROC-AUC of 0.845 and PR-AUC of 0.702.
Control analyses confirmed the importance of aligned image-context integration for model performance.

Conclusions:

Bilateral fundus images, OCT-derived retinal features, and structured data can support participant-level Parkinson's disease classification.
The findings are preliminary and require external validation and age-controlled studies before clinical application.
This approach shows potential as a non-invasive diagnostic tool for Parkinson's disease.