A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability (2020-08-22T00:00:00.000000Z)

TL;DR

A large fine-grained annotated DR dataset containing 2,842 images (FGADR) is constructed to enable extensive studies on DR diagnosis and a novel inductive transfer learning method is introduced for the third task.

Abstract

People with diabetes are at risk of developing an eye disease called diabetic retinopathy (DR). This disease occurs when high blood glucose levels cause damage to blood vessels in the retina. Computer-aided DR diagnosis has become a promising tool for the early detection and severity grading of DR, due to the great success of deep learning. However, most current DR diagnosis systems do not achieve satisfactory performance or interpretability for ophthalmologists, due to the lack of training data with consistent and fine-grained annotations. To address this problem, we construct a large fine-grained annotated DR dataset containing 2,842 images (FGADR). Specifically, this dataset has 1,842 images with pixel-level DR-related lesion annotations, and 1,000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency. The proposed dataset will enable extensive studies on DR diagnosis. Further, we establish three benchmark tasks for evaluation: 1. DR lesion segmentation; 2. DR grading by joint classification and segmentation; 3. Transfer learning for ocular multi-disease identification. Moreover, a novel inductive transfer learning method is introduced for the third task. Extensive experiments using different state-of-the-art methods are conducted on our FGADR dataset, which can serve as baselines for future research. Our dataset will be released in https://csyizhou.github.io/FGADR/.

Authors

Ling Shao

32 papers

Boyang Wang

2 papers

Shanshan Cui

2 papers

TL;DR

Abstract

Authors

References52 items

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images

JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation

SUNet: A Lesion Regularized Model for Simultaneous Diabetic Retinopathy and Diabetic Macular Edema Grading

High-Resolution Diabetic Retinopathy Image Synthesis Manipulated by Grading and Lesions

DME-Net: Diabetic Macular Edema Grading by Auxiliary Task Learning

Deep learning algorithm predicts diabetic retinopathy progression in individual patients

An Interpretable Ensemble Deep Learning Model for Diabetic Retinopathy Disease Classification

Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images

Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey

A Framework for Identifying Diabetic Retinopathy Based on Anti-noise Detection and Attention-Based Fusion

Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images

Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research

Synthesizing retinal and neuronal images with generative adversarial nets

DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications

Attention U-Net: Learning Where to Look for the Pancreas

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Squeeze-and-Excitation Networks

Automated Identification of Diabetic Retinopathy Using Deep Learning.

Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

Lesion Detection and Grading of Diabetic Retinopathy via Two-Stages Deep Convolutional Neural Networks

Towards Adversarial Retinal Image Synthesis

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Densely Connected Convolutional Networks

Red Lesion Detection Using Dynamic Shape Features for Diabetic Retinopathy Screening

Learning Deep Features for Discriminative Localization

Deep Residual Learning for Image Recognition

Rethinking the Inception Architecture for Computer Vision

Automatic Grading of Diabetic Retinopathy on a Public Database

U-Net: Convolutional Networks for Biomedical Image Segmentation

Fractional Max-Pooling

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE

Splat Feature Classification With Application to Retinal Hemorrhage Detection in Fundus Images

Interrater reliability: the kappa statistic

An Ensemble-Based System for Microaneurysm Detection and Diabetic Retinopathy Grading

[International clinical diabetic retinopathy disease severity scale].

A Survey on Transfer Learning

Hierarchical detection of red lesions in retinal images by multiscale correlation filtering

A Comparative Study of Methods for Transductive Transfer Learning

Ridge-based vessel segmentation in color images of the retina

GENERATIVE ADVERSARIAL NETS

Kaggle Diabetic Retinopathy Detection Competition

International Competition on Ocular Disease Intelligent Recognition

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names