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

Huang, Yijin; Lin, Li; Cheng, Pujin; Lyu, Junyan; Tang, Xiaoying

doi:10.1007/978-3-030-87196-3_11

Cited by 19 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

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%

“…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%

See 1 more Smart Citation

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

Alam

Yamashita

Ramesh

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a major cause of vision impairment in diabetic patients worldwide. Due to its prevalence, early clinical diagnosis is essential to improve treatment management of DR patients. Despite recent demonstration of successful machine learning (ML) models for automated DR detection, there is a significant clinical need for robust models that can be trained with smaller cohorts of dataset and still perform with high diagnostic accuracy in independent clinical datasets (i.e., high model generalizability). Towards this need, we have developed a self-supervised contrastive learning (CL) based pipeline for classification of referable vs non-referable DR. Self-supervised CL based pretraining allows enhanced data representation, therefore, the development of robust and generalized deep learning (DL) models, even with small, labeled datasets. We have integrated a neural style transfer (NST) augmentation in the CL pipeline to produce models with better representations and initializations for the detection of DR in color fundus images. We compare our CL pretrained model performance with two state of the art baseline models pretrained with Imagenet weights. We further investigate the model performance with reduced labeled training data (down to 10 percent) to test the robustness of the model when trained with small, labeled datasets. The model is trained and validated on the EyePACS dataset and tested independently on clinical datasets from the University of Illinois, Chicago (UIC). Compared to baseline models, our CL pretrained FundusNet model had higher area under the receiver operating characteristics (ROC) curve (AUC) (CI) values (0.91 (0.898 to 0.930) vs 0.80 (0.783 to 0.820) and 0.83 (0.801 to 0.853) on UIC data). At 10 percent labeled training data, the FundusNet AUC was 0.81 (0.78 to 0.84) vs 0.58 (0.56 to 0.64) and 0.63 (0.60 to 0.66) in baseline models, when tested on the UIC dataset. CL based pretraining with NST significantly improves DL classification performance, helps the model generalize well (transferable from EyePACS to UIC data), and allows training with small, annotated datasets, therefore reducing ground truth annotation burden of the clinicians.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

Alam

Yamashita

Ramesh

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…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%

An FPGA-based edge computing and accelerating platform for fast diabetic retinopathy diagnosis

Qiu

Huang

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is one of the leading causes of blindness. Early DR screening may significantly reduce the risk of vision impairments. Traditional DR diagnosis relies on a professional ophthalmologist to examine the fundus image of a potential patient. However, in remote and underdeveloped areas, medical resources are relatively limited, hindering professional and timely DR diagnosis. In such context, there is an urgent need to develop convenient and fast DR screening methods to provide effective intervention plans. In this work, we implemented and validated a real-time DR diagnosis system on field-programmable gate array (FPGA) board. We first trained a DR grading CNN of interest on GPUs, and then deployed it on FPGA after quantization. Two CNN architectures, ResNet50 and MobileNetV2, are investigated. With 16-bit quantization, ResNet50 and MobileNetV2 respectively achieve 0.828 and 0.753 Kappa scores on the publicly-accessible EyePACS test set. Improvements in average processing time have also been observed: 16.92ms over CPU and 0.21ms over GPU.

show abstract

“…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%

LesionPaste: One-Shot Anomaly Detection for Medical Images

Huang¹,

Huang²,

Tang³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Due to the high cost of manually annotating medical images, especially for large-scale datasets, anomaly detection has been explored through training models with only normal data. Lacking prior knowledge of true anomalies is the main reason for the limited application of previous anomaly detection methods, especially in the medical image analysis realm. In this work, we propose a one-shot anomaly detection framework, namely LesionPaste, that utilizes true anomalies from a single annotated sample and synthesizes artificial anomalous samples for anomaly detection. First, a lesion bank is constructed by applying augmentation to randomly selected lesion patches. Then, MixUp is adopted to paste patches from the lesion bank at random positions in normal images to synthesize anomalous samples for training. Finally, a classification network is trained using the synthetic abnormal samples and the true normal data. Extensive experiments are conducted on two publicly-available medical image datasets with different types of abnormalities. On both datasets, our proposed LesionPaste largely outperforms several state-of-the-art unsupervised and semi-supervised anomaly detection methods, and is on a par with the fully-supervised counterpart. To note, LesionPaste is even better than the fully-supervised method in detecting early-stage diabetic retinopathy.

show abstract

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

Cited by 19 publications

References 15 publications

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

Contrastive learning-based pretraining improves representation and transferability of diabetic retinopathy classification models

An FPGA-based edge computing and accelerating platform for fast diabetic retinopathy diagnosis

LesionPaste: One-Shot Anomaly Detection for Medical Images

Contact Info

Product

Resources

About