Deep Learning-Based Automated Classification of Multi-Retinal Disease From Fundus Photography
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Deep Learning
- Sponsor
- Beijing Tongren Hospital
- Enrollment
- 10000
- Locations
- 1
- Primary Endpoint
- Sensitivity and specificity
- Last Updated
- 5 years ago
Overview
Brief Summary
The objective of this study is to establish deep learning (DL) algorithm to automatically classify multi-diseases from fundus photography and differentiate major vision-threatening conditions and other retinal abnormalities. The effectiveness and accuracy of the established algorithm will be evaluated in community derived dataset.
Detailed Description
Retinal diseases seriously threaten vision and quality of life, but they often develop insidiously. To date, deep learning (DL) algorithms have shown high prospects in biomedical science, particularly in the diagnosis of ocular diseases, such as diabetic retinopathy, age-related macular degeneration, retinopathy of prematurity, glaucoma, and papilledema. However, there is still a lack of a single algorithm that can classify multi-diseases from fundus photography. This cross-sectional study will establish a DL algorithm to automatically classify multi-diseases from fundus photography and differentiate major vision-threatening conditions and other retinal abnormalities. We will use the receiver operating characteristic (ROC) curve to examine the ability of recognition and classification of diseases. Taken the results of the expert panel as the gold standard, we will use the evaluation indexes, such as sensitivity, specificity, accuracy, positive predictive value, negative predictive value, etc, to compare the diagnostic capacity between the AI recognition system and human ophthalmologist.
Investigators
Eligibility Criteria
Inclusion Criteria
- •fundus photography around 45° field which covers optic disc and macula
- •complete patient identification information;
Exclusion Criteria
- •incomplete patient identification information
Outcomes
Primary Outcomes
Sensitivity and specificity
Time Frame: 1 week
Taken the results of the expert panel as the gold standard, we will use sensitivity and specificity to compare the diagnostic capacity between the AI recognition system and human ophthalmologist.
Accuracy
Time Frame: 1 week
Taken the results of the expert panel as the gold standard, we will use accuracy to compare the diagnostic capacity between the AI recognition system and human ophthalmologist.
Positive and negative predictive value
Time Frame: 1 week
Taken the results of the expert panel as the gold standard, we will use positive and negative predictive value to compare the diagnostic capacity between the AI recognition system and human ophthalmologist.
Area under curve
Time Frame: 1 week
We will use the receiver operating characteristic (ROC) curve to examine the ability of recognition and classification of diseases. Taken the results of the expert panel as the gold standard, we will use the area under curve to compare the diagnostic capacity between the AI recognition system and human ophthalmologist.