Diabetic Retinopathy Classification Using A Hybrid and Efficient MobileNetV2-SVM Model

Taufiqurrahman, Shidqie; Handayani, Astri; Hermanto, Beni Rio; Mengko, Tati L. R.

doi:10.1109/tencon50793.2020.9293739

Cited by 23 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison with these studies shows that our model has outperformed prior published models, with overall five-class classification accuracy rates of 87.6% and 84.9% on 80:20 hold-out validation and 10-fold CV, respectively ( Table 6 ). In [ 39 ], the model attained 79% accuracy using a 10-fold cross-validation method, but the results were obtained with data augmentation. In [ 40 ], the model attained 81% accuracy with data augmentation and end-to-end learning.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Diabetic Retinopathy Detection Using Horizontal and Vertical Patch Division-Based Pre-Trained DenseNET with Digital Fundus Images

et al. 2022

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a common complication of diabetes that can lead to progressive vision loss. Regular surveillance with fundal photography, early diagnosis, and prompt intervention are paramount to reducing the incidence of DR-induced vision loss. However, manual interpretation of fundal photographs is subject to human error. In this study, a new method based on horizontal and vertical patch division was proposed for the automated classification of DR images on fundal photographs. The novel sides of this study are given as follows. We proposed a new non-fixed-size patch division model to obtain high classification results and collected a new fundus image dataset. Moreover, two datasets are used to test the model: a newly collected three-class (normal, non-proliferative DR, and proliferative DR) dataset comprising 2355 DR images and the established open-access five-class Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 dataset comprising 3662 images. Two analysis scenarios, Case 1 and Case 2, with three (normal, non-proliferative DR, and proliferative DR) and five classes (normal, mild DR, moderate DR, severe DR, and proliferative DR), respectively, were derived from the APTOS 2019 dataset. These datasets and these cases have been used to demonstrate the general classification performance of our proposal. By applying transfer learning, the last fully connected and global average pooling layers of the DenseNet201 architecture were used to extract deep features from input DR images and each of the eight subdivided horizontal and vertical patches. The most discriminative features are then selected using neighborhood component analysis. These were fed as input to a standard shallow cubic support vector machine for classification. Our new DR dataset obtained 94.06% and 91.55% accuracy values for three-class classification with 80:20 hold-out validation and 10-fold cross-validation, respectively. As can be seen from steps of the proposed model, a new patch-based deep-feature engineering model has been proposed. The proposed deep-feature engineering model is a cognitive model, since it uses efficient methods in each phase. Similar excellent results were seen for three-class classification with the Case 1 dataset. In addition, the model attained 87.43% and 84.90% five-class classification accuracy rates using 80:20 hold-out validation and 10-fold cross-validation, respectively, on the Case 2 dataset, which outperformed prior DR classification studies based on the five-class APTOS 2019 dataset. Our model attained about >2% classification results compared to others. These findings demonstrate the accuracy and robustness of the proposed model for classification of DR images.

show abstract

Section: Discussionmentioning

confidence: 99%

“…As can be seen from Table 6 , most of the models (see Majumder and Kehtarnavaz [ 40 ], Kassani et al [ 42 ], Taufiqurrahman et al [ 39 ], and Gangwar and Ravi [ 43 ]) applied data augmentation to overcome image classification on the unbalanced dataset. However, data augmentation is not a good way to show the performance of the model.…”

Section: Discussionmentioning

confidence: 99%

Automated Diabetic Retinopathy Detection Using Horizontal and Vertical Patch Division-Based Pre-Trained DenseNET with Digital Fundus Images

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Traditionally, the output layer of pre-trained models is replaced by a multi-layer neural network classifier and a softmax layer with a size equivalent to the number of classes to be recognised. Nevertheless, Taufiqurrahman et al [11] suggested restructuring the MobileNetV2 model by replacing the fully connected layer with a Support Vector Machine (SVM) classifier. This modified version, MobileNetV2-SVM, obtained better performance than its original model.…”

Section: Related Workmentioning

confidence: 99%

“…As in the research, [17], [8], [6], [11], [7], this research aims to use InceptionV3, CNN, EfficientNetsB5 to detect DR due to their efficiency previous studies. However, these models will be validated using the same dataset to compare their results.…”

Section: Related Workmentioning

confidence: 99%

Prediction of Diabetic Retinopathy using Convolutional Neural Networks

Alsuwat¹,

Alalawi²,

Alhazmi³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is among the most dangerous diabetic complications that can lead to lifelong blindness if left untreated. One of the essential difficulties in DR is early discovery, which is crucial for therapy progress. The accurate diagnosis of the DR stage is famously complicated and demands a skilled analysis by the expert being of fundus images. This paper detects DR and classifies its stage using retina images by applying conventional neural networks and transfer learning models. Three deep learning models were investigated: trained from scratch CNN and pre-trained InceptionV3 and Efficient-NetsB5. Experiment results show that the proposed CNN model outperformed the pre-trained models with a 9 to 25% relative improvement in F1-score compared to pre-trained InceptionV3 and EfficientNetsB5, respectively.

show abstract

“…While doing this, it is necessary to prevent excessive fit of the model. Considering all these situations, the data augmentation technique was used [12]. At this stage, the images were reprocuded by using horizontal and vertical shifts and angular change techniques.…”

Section: Data Augmentationmentioning

confidence: 99%

Diabetic Retinopathy Detection with Deep Transfer Learning Methods

Çınarer

Kiliç

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

View full text Add to dashboard Cite

Diabetic retinopathy is an eye disease that occurs with damage to the retina and has many different complications, ranging from permanent blindness. The aim of this study is to develop a (convolutional neural network) CNN model that determines with high accuracy whether fundus images are diabetic retinopathy. The performance of the model has been verified in Kaggle APTOS 2019 dataset with AlexNET and VggNET-16 deep transfer learning algorithms. Various image processing techniques have been used as well as deep learning methods to further improve the classification performance. Images in the data set were rescaled to 224 × 224 × 3 and converted to Grayscale color space. Besides Gauss filter applied to eliminate the noise in the images. The area under the curve (AUC), precision, recall, and accuracy metrics of the deep transfer learning models used in this study were compared. The AlexNet model achieved a 98.6% AUC score, 95.2% accuracy, and the VggNET-16 model achieved a 99.6% AUC score and 98.1% accuracy. VggNET-16 was found to have higher confidence. Our results show that with the correct optimization of the CNN model applied in diabetic retinopathy classification, deep transfer learning models can achieve high performance and can be used in the detection of diabetic retinopathy patients.

show abstract

Diabetic Retinopathy Classification Using A Hybrid and Efficient MobileNetV2-SVM Model

Cited by 23 publications

References 14 publications

Automated Diabetic Retinopathy Detection Using Horizontal and Vertical Patch Division-Based Pre-Trained DenseNET with Digital Fundus Images

Automated Diabetic Retinopathy Detection Using Horizontal and Vertical Patch Division-Based Pre-Trained DenseNET with Digital Fundus Images

Prediction of Diabetic Retinopathy using Convolutional Neural Networks

Diabetic Retinopathy Detection with Deep Transfer Learning Methods

Contact Info

Product

Resources

About