# A deep-learning pipeline for the diagnosis and grading of common blinding ophthalmic diseases based on lesion-focused classification model

## TL;DR

This paper presents a deep-learning pipeline that accurately diagnoses and grades four common blinding eye diseases using lesion-focused classification, improving early detection and treatment.

## Contribution

The novel contribution is a deep-learning pipeline combining segmentation and classification models for accurate diagnosis and grading of blinding ophthalmic diseases.

## Key findings

- The model achieved a micro AUROC of 0.995 on internal validation data.
- The model maintained high accuracy in external validation on Neimeng and Guangxi cohorts.
- Disease staging achieved AUROCs of 0.877 for AMD, 0.972 for RVO, and 0.961 for DR.

## Abstract

Glaucoma (GLAU), Age-related Macular Degeneration (AMD), Retinal Vein Occlusion (RVO), and Diabetic Retinopathy (DR) are common blinding ophthalmic diseases worldwide.

This approach is expected to enhance the early detection and treatment of common blinding ophthalmic diseases, contributing to the reduction of individual and economic burdens associated with these conditions.

We propose an effective deep-learning pipeline that combine both segmentation model and classification model for diagnosis and grading of four common blinding ophthalmic diseases and normal retinal fundus.

In total, 102,786 fundus images of 75,682 individuals were used for training validation and external validation purposes. We test our model on internal validation data set, the micro Area Under the Receiver Operating Characteristic curve (AUROC) of which reached 0.995. Then, we fine-tuned the diagnosis model to classify each of the four disease into early and late stage, respectively, which achieved AUROCs of 0.597 (GL), 0.877 (AMD), 0.972 (RVO), and 0.961 (DR) respectively. To test the generalization of our model, we conducted two external validation experiments on Neimeng and Guangxi cohort, all of which maintained high accuracy.

Our algorithm demonstrates accurate artificial intelligence diagnosis pipeline for common blinding ophthalmic diseases based on Lesion-Focused fundus that overcomes the low-accuracy of the traditional classification method that based on raw retinal images, which has good generalization ability on diverse cases in different regions.