2021
DOI: 10.1007/978-3-030-87196-3_11
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
2

Relationship

2
7

Authors

Journals

citations
Cited by 19 publications
(11 citation statements)
references
References 15 publications
0
11
0
Order By: Relevance
“…Therefore, compared to conventional augmentations (such as the ones used in the original SimCLR 18 ), the model generalizes better when augmented with NST using texture-rich artistic images (AUC of 0.91 vs 0.83 when FundusNet used NST vs did not used NST on top of regular augmentations). We compare the NST based framework with another recent work that proposed a lesion based CL framework 25 for DR classification, where the model input is segmented lesions, rather than the whole fundus images. The augmentation technique used in this work is similar to that of original SimCLR paper.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Therefore, compared to conventional augmentations (such as the ones used in the original SimCLR 18 ), the model generalizes better when augmented with NST using texture-rich artistic images (AUC of 0.91 vs 0.83 when FundusNet used NST vs did not used NST on top of regular augmentations). We compare the NST based framework with another recent work that proposed a lesion based CL framework 25 for DR classification, where the model input is segmented lesions, rather than the whole fundus images. The augmentation technique used in this work is similar to that of original SimCLR paper.…”
Section: Discussionmentioning
confidence: 99%
“…In this paper, our key novel contributions are following: (i) we present 'FundusNet'-a novel CL based framework with neural style transfer (NST) based augmentation that achieves high classification performance; (ii) our novel NST based image augmentation technique effectively improves the representation learning capability of the CL network from fundus images as demonstrated by comparing to a state of the art lesion based CL model 25 . The model with FundusNet weights is independently evaluated on external clinical data, which achieves high sensitivity and specificity, when compared to three baseline models (two fully supervised models and one CL model); and iii) The CL-pretrained model also performed well even when the labelled dataset was reduced to 10% of its original size, suggesting the potential of CL to train models for DR diagnosis using small, labeled datasets.…”
mentioning
confidence: 99%
“…A lot of work has been done on neural network-based fundus image diagnosis, including optic disc detection, fovea localization, DR grading, fundus blood vessel segmentation, microaneurysm detection. 10,[17][18][19] To continuously improve the accuracy of detection, different pre-processing methods, multi-network models and attention module were proposed. A. Li et al 13 obtained significantly improved results compared to the state of the art network by introducing category attention block and global attention block.…”
Section: Related Workmentioning
confidence: 99%
“…IDRiD. IDRiD [17] consists of 81 DR fundus images, with pixel-wise lesion annotations of microaneurysms (MA), hemorrhages (HE), soft exudates (SE) and hard exudates (EX) [7] (see Fig. A2 MosMed.…”
Section: Datasetsmentioning
confidence: 99%