Diabetic Retinopathy Detection using CNN, Transformer and MLP based Architectures

Kumar, Nikhil; Karthikeyan, B.

doi:10.1109/ispacs51563.2021.9651024

Cited by 16 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the excellent performance of the vanilla Transformer in various computer vision tasks, many recent works [12], [26]- [29] have explored the effectiveness of the Transformer architecture to address the limitation of CNNs in fundus image classification. Especially, N. S. Kumar et al [30] evaluate the DR grading architectures of Transformer, CNN, and Multi-Layer Perceptron (MLP) in terms of model convergence time, accuracy, and model scale, demonstrating that the Transformer-based model outperforms the CNN and MLP architectures in terms of not only accuracy but also achieving comparable model convergence time.…”

Section: B Transformer Based Methodsmentioning

confidence: 99%

Sq-Swin: Siamese Quadratic Swin Transformer for Lettuce Browning Prediction

Wang

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: B Transformer Based Methodsmentioning

confidence: 99%

Sq-Swin: Siamese Quadratic Swin Transformer for Lettuce Browning Prediction

Wang

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

“…They obtained an Acc of 0.861, a Se of 0.854, and a Sp of 0.875. Kumar and Karthikeyan ( 2021 ) used different models such as EfficientNet and Swin-Transformer with 3,600 fundus images and obtained an Acc of 0.864 on Swin-Transformer. Lahmar and Idri ( 2022 ) presented automatic two-class classification using 28 hybrid architectures.…”

Section: Literature Reviewmentioning

confidence: 99%

Smart grading of diabetic retinopathy: an intelligent recommendation-based fine-tuned EfficientNetB0 framework

Anand,

Koundal,

Alghamdi

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Diabetic retinopathy is a condition that affects the retina and causes vision loss due to blood vessel destruction. The retina is the layer of the eye responsible for visual processing and nerve signaling. Diabetic retinopathy causes vision loss, floaters, and sometimes blindness; however, it often shows no warning signals in the early stages. Deep learning-based techniques have emerged as viable options for automated illness classification as large-scale medical imaging datasets have become more widely available. To adapt to medical image analysis tasks, transfer learning makes use of pre-trained models to extract high-level characteristics from natural images. In this research, an intelligent recommendation-based fine-tuned EfficientNetB0 model has been proposed for quick and precise assessment for the diagnosis of diabetic retinopathy from fundus images, which will help ophthalmologists in early diagnosis and detection. The proposed EfficientNetB0 model is compared with three transfer learning-based models, namely, ResNet152, VGG16, and DenseNet169. The experimental work is carried out using publicly available datasets from Kaggle consisting of 3,200 fundus images. Out of all the transfer learning models, the EfficientNetB0 model has outperformed with an accuracy of 0.91, followed by DenseNet169 with an accuracy of 0.90. In comparison to other approaches, the proposed intelligent recommendation-based fine-tuned EfficientNetB0 approach delivers state-of-the-art performance on the accuracy, recall, precision, and F1-score criteria. The system aims to assist ophthalmologists in early detection, potentially alleviating the burden on healthcare units.

show abstract

“…Recently, Kumar et al [ 19 ] tested the classification performance of several major CNNs and Transformers as well as MLPs on APTOS dataset. They found that Transformers perform better than CNNs and MLPs overall.…”

Section: Introductionmentioning

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

Diabetic Retinopathy Detection using CNN, Transformer and MLP based Architectures

Cited by 16 publications

References 2 publications

Sq-Swin: Siamese Quadratic Swin Transformer for Lettuce Browning Prediction

Sq-Swin: Siamese Quadratic Swin Transformer for Lettuce Browning Prediction

Smart grading of diabetic retinopathy: an intelligent recommendation-based fine-tuned EfficientNetB0 framework

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

Contact Info

Product

Resources

About