Multi-Model Domain Adaptation for Diabetic Retinopathy Classification

Zhang, Guanghua; Sun, Bin; Zhang, Zhaoxia; Pan, Jing; Yang, Weihua; Liu, Yunfang

doi:10.3389/fphys.2022.918929

Cited by 5 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparative results are presented in Table 9 . Zhang et al [ 43 ] proposed a multi-model domain adaptation (MMDA) method, and they trained it on source domains including DDR, IDRiD, Messidor, and Messidor-2 datasets and tested it on the target domain APTOS. Their method achieved high sensitivity but had an accuracy of 90.6%, which is lower than that of VMLRI (93.42%).…”

Section: Experiments and Resultsmentioning

confidence: 99%

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image

Yang,

Cai,

Qiu

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Computer-aided diagnosis systems based on deep learning algorithms have shown potential applications in rapid diagnosis of diabetic retinopathy (DR). Due to the superior performance of Transformer over convolutional neural networks (CNN) on natural images, we attempted to develop a new model to classify referable DR based on a limited number of large-size retinal images by using Transformer. Vision Transformer (ViT) with Masked Autoencoders (MAE) was applied in this study to improve the classification performance of referable DR. We collected over 100,000 publicly fundus retinal images larger than 224×224, and then pre-trained ViT on these retinal images using MAE. The pre-trained ViT was applied to classify referable DR, the performance was also compared with that of ViT pre-trained using ImageNet. The improvement in model classification performance by pre-training with over 100,000 retinal images using MAE is superior to that pre-trained with ImageNet. The accuracy, area under curve (AUC), highest sensitivity and highest specificity of the present model are 93.42%, 0.9853, 0.973 and 0.9539, respectively. This study shows that MAE can provide more flexibility to the input image and substantially reduce the number of images required. Meanwhile, the pretraining dataset scale in this study is much smaller than ImageNet, and the pre-trained weights from ImageNet are not required also.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image

Yang,

Cai,

Qiu

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Although the Messidor-2 dataset has been used by several groups, there are different allocations of referable DR images 20 , 21 and usually used for external validation, not allowing direct comparison with previous traditional machine learning studies 22 , 23 .…”

Section: Discussionmentioning

confidence: 99%

Automated machine learning model for fundus image classification by health-care professionals with no coding experience

Zago Ribeiro,

Nakayama,

Malerbi

et al. 2024

Sci Rep

View full text Add to dashboard Cite

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

show abstract

“…Because there are too few samples for training, overftting is easy; i.e., the model performs better on the training samples, but the generalization efect on the test set is unsatisfactory. To alleviate this phenomenon, we use diferent methods to enhance the dataset, primarily including random horizontal and vertical fipping and arbitrary direction rotation [24]. During training, the loss function takes cross-entropy loss, using AdamW as the optimizer, and weight decay is set to 0.05; we use a transfer-learning approach that uses ImageNet-based pretrained weights.…”

Section: Model Architecture In This Study We Use the Swinmentioning

confidence: 99%

Automatic Diagnosis of Different Types of Retinal Vein Occlusion Based on Fundus Images

Wan,

Hua,

et al. 2023

International Journal of Intelligent Systems

Self Cite

View full text Add to dashboard Cite

Retinal vein occlusion (RVO) is the second common cause of blindness following diabetic retinopathy. The manual screening of fundus images to detect RVO is time consuming. Deep-learning techniques have been used for screening RVO due to their outstanding performance in many applications. However, unlike other images, medical images have smaller lesions, which require a more elaborate approach. To provide patients with an accurate diagnosis, followed by timely and effective treatment, we developed an intelligent method for automatic RVO screening on fundus images. Swin Transformer learns the hierarchy of low-to high-level features like the convolutional neural network. However, Swin Transformer extracts features from fundus images through attention modules, which pay more attention to the interrelationship between the features and each other. The model is more universal, does not rely entirely on the data itself, and focuses not only on local information but has a diffusion mechanism from local to global. To suppress overfitting, we adopt a regularization strategy, label smoothing, which uses one-hot to add noise to reduce the weight of the categories of true sample labels when calculating the loss function. The choice of different models using a 5-fold cross-validation on our own datasets indicates that Swin Transformer performs better. The accuracy of classifying all datasets is 98.75 ± 0.000, and the accuracy of identifying MRVO, CRVO, BRVO, and normal, using the method proposed in the paper, is 94.49 ± 0.094, 99.98 ± 0.015, 98.88 ± 0.08, and 99.42 ± 0.012, respectively. The method will be useful to diagnose RVO and help decide grade through fundus images, which has the potency to provide patients with further diagnosis and treatment.

show abstract

Multi-Model Domain Adaptation for Diabetic Retinopathy Classification

Cited by 5 publications

References 36 publications

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image

Automated machine learning model for fundus image classification by health-care professionals with no coding experience

Automatic Diagnosis of Different Types of Retinal Vein Occlusion Based on Fundus Images

Contact Info

Product

Resources

About