Cross-Field Transformer for Diabetic Retinopathy Grading on Two-field Fundus Images

Hou, Junlin; Xu, Jilan; Xiao, Fan; Zhao, Ran; Zhang, Yuejie; Zou, Haidong; Lu, Lina; Xue, Wenwen; Feng, Rui

doi:10.1109/bibm55620.2022.9995459

Cited by 7 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison methods : To validate the effectiveness of the proposed PACNet on grading DR task, we compare our approach with several typical classification and DR grading methods, for example, CANet [27], alexnet [45], mobilenet_v2 [46], densenet121 [47], VGG16 [48], ResNet‐50 [49], EfficientNet‐b0 [50], and CrossFiT [51]. For a fair comparison, we split our new dataset into two subsets by 10‐fold cross‐validation for all methods.…”

Section: Resultsmentioning

confidence: 99%

A new retinal OCT‐angiography diabetic retinopathy dataset for segmentation and DR grading

Wang

Dai

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

PurposeDiabetic retinopathy (DR) is one of the most common diseases caused by diabetes and can lead to vision loss or even blindness. The wide‐field optical coherence tomography (OCT) angiography is non‐invasive imaging technology and convenient to diagnose DR.MethodsA newly constructed Retinal OCT‐Angiography Diabetic retinopathy (ROAD) dataset is utilized for segmentation and grading tasks. It contains 1200 normal images, 1440 DR images, and 1440 ground truths for DR image segmentation. To handle the problem of grading DR, we propose a novel and effective framework, named projective map attention‐based convolutional neural network (PACNet).ResultsThe experimental results demonstrate the effectiveness of our PACNet. The accuracy of the proposed framework for grading DR is 87.5% on the ROAD dataset.ConclusionsThe information on ROAD can be viewed at URL https://mip2019.github.io/ROAD. The ROAD dataset will be helpful for the development of the early detection of DR field and future research.Translational RelevanceThe novel framework for grading DR is a valuable research and clinical diagnosis method.

show abstract

Section: Resultsmentioning

confidence: 99%

A new retinal OCT‐angiography diabetic retinopathy dataset for segmentation and DR grading

Wang

Dai

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…There are also some improvements in the model for DR grading. Hou et al 5 proposed a Cross-Field Transformer (CrossFiT), which can effectively use dual-field correspondence to improve the DR grading performance. However, these methods have some problems because the features of DR are complex and variable, and it is difficult for a single-scale feature extractor to accurately extract all the lesion features.…”

Section: Introductionmentioning

confidence: 99%

A graph convolutional network with dynamic weight fusion of multi-scale local features for diabetic retinopathy grading

Wang,

Guo

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a serious ocular complication that can pose a serious risk to a patient’s vision and overall health. Currently, the automatic grading of DR is mainly using deep learning techniques. However, the lesion information in DR images is complex, variable in shape and size, and randomly distributed in the images, which leads to some shortcomings of the current research methods, i.e., it is difficult to effectively extract the information of these various features, and it is difficult to establish the connection between the lesion information in different regions. To address these shortcomings, we design a multi-scale dynamic fusion (MSDF) module and combine it with graph convolution operations to propose a multi-scale dynamic graph convolutional network (MDGNet) in this paper. MDGNet firstly uses convolution kernels with different sizes to extract features with different shapes and sizes in the lesion regions, and then automatically learns the corresponding weights for feature fusion according to the contribution of different features to model grading. Finally, the graph convolution operation is used to link the lesion features in different regions. As a result, our proposed method can effectively combine local and global features, which is beneficial for the correct DR grading. We evaluate the effectiveness of method on two publicly available datasets, namely APTOS and DDR. Extensive experiments demonstrate that our proposed MDGNet achieves the best grading results on APTOS and DDR, and is more accurate and diverse for the extraction of lesion information.

show abstract

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification

Hou,

Xu,

Xiao

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Cross-Field Transformer for Diabetic Retinopathy Grading on Two-field Fundus Images

Cited by 7 publications

References 15 publications

A new retinal OCT‐angiography diabetic retinopathy dataset for segmentation and DR grading

A new retinal OCT‐angiography diabetic retinopathy dataset for segmentation and DR grading

A graph convolutional network with dynamic weight fusion of multi-scale local features for diabetic retinopathy grading

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification

Contact Info

Product

Resources

About