.png){kind=icon}
.png){kind=icon}
Return
Explainable Multimodal Retinal Optical Imaging for Clinical Parkinson’s Disease Classification Using Fundus Photography and OCT-Derived Features
.png){kind=icon}
OA
AI
Z
F
N
A
M
S
H
DOI：10.1016/j.pdpdt.2026.105563.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Retinal optical imaging supported non-invasive photodiagnostic PD classification. • Bilateral fundus images were fused with OCT-derived retinal features. • FiLM fusion improved PR-AUC and calibration over unimodal branches. • XAI linked predictions to retinal heatmaps and OCT-driven feature signals.
Keywords:
Retinal optical imaging
Photodiagnosis
Fundus photography
Optical coherence tomography
Explainable AI
Parkinson’s disease
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.6
Papers:
4.7K
Citations:
9.8K
Organization
Cited Papers