medical-10

Diabetic Retinopathy Grading

3260 papers • 126 benchmarks • 313 datasets

Grading the severity of diabetic retinopathy from (ophthalmic) fundus images

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in diabetic-retinopathy-grading-10

Trend

Dataset

Best Model

Actions

Kaggle EyePACS

Libraries

i

Use these libraries to find diabetic-retinopathy-grading-10 models and implementations

Datasets

Kaggle EyePACS

Retinal-Lesions

DRTiD

Subtasks

No subtasks available.

Most implemented papers

Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images

Xiaoying Tang, Li Lin, Pujin Cheng, Yijin Huang, Junyan Lyu•Fri Jul 16 2021

This work proposes a self-supervised framework, namely lesion-based contrastive learning for automated diabetic retinopathy (DR) grading, whereby lesion patches are employed to encourage the feature extractor to learn representations that are highly discriminative for DR grading.

49

Content

0

Paper Graph

Identifying the Key Components in ResNet-50 for Diabetic Retinopathy Grading from Fundus Images: A Systematic Investigation

Xiaoying Tang, Li Lin, Pujin Cheng, Yijin Huang, Junyan Lyu•Tue Oct 26 2021

This work demonstrates that the DR grading framework is sensitive to input resolution, objective function, and composition of data augmentation, and achieves a state-of-the-art result on the EyePACS test set with only image-level labels.

45 0

Paper Graph

OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing

Wenjie Zhu, Peijie Qiu, O. Dumitrascu, Jacob Jacob, Mohammad Farazi, Zhangsihao Yang, Keshav Nandakumar, Yalin Wang•Sun Feb 05 2023

This work leveraged the Optimal Transport (OT) theory to propose an unpaired image-to-image translation scheme for mapping low-quality retinal CFPs to high-quality counterparts, and validated the integrated framework, OTRE, on three publicly available retinal image datasets.

17 0

Paper Graph

nnMobileNet: Rethinking CNN for Retinopathy Research

Wenhui Zhu, Peijie Qiu, Xiwen Chen, Xin Li, Natasha Lepore, O. Dumitrascu, Yalin Wang•Thu Jun 01 2023

It is found that an optimized MobileNet, through selective modifications, can surpass ViT-based models in various RD benchmarks, including diabetic retinopathy grading, detection of multiple fundus diseases, and classification of diabetic macular edema.

18 0

Paper Graph

BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading

Ziyuan Zhao, Kerui Zhang, Xuejie Hao, Jing Tian, M. Chua, Li Chen, Xin Xu•Tue May 14 2019

A new deep learning architecture, called BiRA-Net, is proposed, which combines the attention model for feature extraction and bilinear model for fine-grained classification, and a new loss function, called grading loss, which leads to improved training convergence of the proposed approach.

79 0

Paper Graph

Reproduction study using public data of: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs

L. A. Bongo, Kajsa Møllersen, M. Voets•Sun Mar 11 2018

The challenges of reproducing deep learning method results are shown, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis is shown.

192 0

Paper Graph

Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image

Tianzhu Zhang, Yanwu Xu, Yehui Yang, Fangxin Shang, Binghong Wu, Dalu Yang, Lei Wang, Wensheng Zhang•Sun Aug 02 2020

This article presents a robust framework, which collaboratively utilizes patch-level and image-level annotations, for DR severity grading, and proves that the algorithm is robust when facing image quality and distribution variations that commonly exist in real-world practice.

59 0

Paper Graph

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

Ismail Ben Ayed, J. Dolz, H. Lombaert, A. Galdrán, H. Chakor•Wed Sep 30 2020

This paper proposes a straightforward approach to enforce this constraint for the task of predicting Diabetic Retinopathy (DR) severity from eye fundus images based on the well-known notion of Cost-Sensitive classification, and expands standard classification losses with an extra term that acts as a regularizer.

34 0

Paper Graph

INSightR-Net: Interpretable Neural Network for Regression using Similarity-based Comparisons to Prototypical Examples

L. Hesse, A. Namburete•Sat Jul 30 2022

This work proposes an inherently interpretable CNN for regression using similarity-based comparisons (INSightR-Net) and demonstrates its methods on the task of diabetic retinopathy grading and quantified the quality of the explanations using sparsity and diversity.

16 0

Paper Graph

SSiT: Saliency-Guided Self-Supervised Image Transformer for Diabetic Retinopathy Grading

Pujin Cheng, Yijin Huang, Junyan Lyu, R. Tam, Xiaoying Tang•Wed Oct 19 2022

Saliency-guided Self-Supervised image Transformer (SSiT) is proposed for Diabetic Retinopathy (DR) grading from fundus images, and significantly outperforms other representative state-of-the-art SSL methods on all downstream datasets and under various evaluation settings.

34 0

Paper Graph

Adding a benchmark result helps the community track progress.