Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Sikder, Niloy; Chowdhury, Md. Sanaullah; Arif, Abu Shamim Mohammad; Nahid, Abdullah-Al

doi:10.1109/iccit48885.2019.9038439

Cited by 20 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN models such as CNN [19] and CNN512 [20] obtained 77% and 84% accuracy, respectively, which is 17.4% and 10.3% less than the proposed model. The CNN variant models mentioned in the literature [9,11,17] and [21][22][23][24][25] performed better but not greater than the proposed model.…”

Section: Aptos Resultsmentioning

confidence: 75%

“…A new early blind recognition technique [23] was designed using the color information obtained from RF images based on the ensemble learning scheme such as Extra tree model. Different deep learning-based classifiers [24] have been analyzed such as VGG16, ResNet50, InceptionV3 and DenseNet121 to partition the retina areas and categorize DR severity grades.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Scale Attention-Based Mechanism in Gradient Boosting Convolutional Neural Network for Diabetic Retinopathy Grade Classification

2022

IJIES

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is a common complication of Diabetes Mellitus (DM) that produces retinal abnormalities and can lead to blindness if not diagnosed and treated on time. To address this concern, an adaptive Convolutional Neural Network (CNN) model with Gradient Boosting (GB) called ResNetGB has been used from the literature where a Principal Component Analysis (PCA) based Fully Connected (FC) layer is used to capture the discriminative characteristics from the Retinal Fundus (RF) samples. It is essential to extract more effective features to categorize the DR grades. Hence, in this article, the Multi-Scale Attention (MSA) strategy is incorporated into the ResNetGB model for effective DR grade classification. First, the encoder network is used to embed the RF image in a high-level interpretational space in which the mixture of mid and high-level characteristics is considered to enhance the representation. Then, a Multi-Scale Feature Pyramid (MSFP) is added to define the retinal pattern in various localities and the MSA strategy is applied to the high-level interpretation. Moreover, the entire MSA-ResNetGB framework is trained by the cross-entropy loss to categorize the patients with respective DR grades. Finally, the experimental analysis exhibit that the MSA-ResNetGB model achieves the 94.40% and 94.17% accuracy on two benchmark datasets: Kaggle-APTOS and IDRiD, respectively compared to the cutting-edge models.

show abstract

Section: Aptos Resultsmentioning

confidence: 75%

Section: Related Workmentioning

confidence: 99%

Multi-Scale Attention-Based Mechanism in Gradient Boosting Convolutional Neural Network for Diabetic Retinopathy Grade Classification

2022

IJIES

View full text Add to dashboard Cite

show abstract

“…They got an accuracy of 91.9%, a sensitivity of 84%, specificity of 98.1%, and Kappa of 96.9% for SC1 on the APTOS2019 dataset. Sikder et al [32] used an ensemble learning algorithm called ET classifier to classify the colored information of the fundus images from the APTOS2019 dataset. They filtered the dataset by removing many noisy samples and achieved an accuracy of 91% and a recall of 89.43% for SC1.…”

Section: B Dr Screening Methodsmentioning

confidence: 99%

“…1) Preprocessing The retinal fundus images are usually not calibrated and are surrounded by a black area, as shown in Fig 1(a). To center the retina and remove the black area around it, firstly, the retina circle is cropped, and the background is removed using the method presented in [32], and then it is resized to 512 × 512 pixels. Usually, the DR datasets are imbalanced, i.e., the numbers of images of different classes are significantly different; we increase the data of minority classes using data augmentation.…”

Section: B Custom-designed Cnn Modelmentioning

confidence: 99%

Automatic Diabetic Retinopathy Diagnosis Using Adaptive Fine-Tuned Convolutional Neural Network

2021

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a complication of diabetes that leads to blindness. The manual screening of color fundus images to detect DR at early stages is expensive and time consuming. Deep learning (DL) techniques have been employed for automatic DR screening on fundus images due to their outstanding performance in many applications. However, training a DL model needs a huge amount of data, which are usually unavailable in the case of DR, and overfitting is unavoidable. Employing a two-stage transfer learning method, we developed herein an intelligent computer-aided system using a pre-trained convolutional neural network (CNN) for automatic DR screening on fundus images. A CNN model learns the domain-specific hierarchy of low-to high-level features. Given this, using the regions of interest (ROIs) of lesions extracted from the annotated fundus images, the first layer of a pre-trained CNN model is re-initialized. The model is then fine-tuned, such that the low-level layers learn the local structures of the lesion and normal regions. As the fully connected layer (FC) layers encode high-level features, which are global in nature and domain specific, we replace them with a new FC layer based on the principal component analysis PCA and use it in an unsupervised manner to extract discriminate features from the fundus images. This step reduces the model complexity, significantly avoiding the overfitting problem. This step also lets the model adopt the fundus image structures, making it suitable for DR feature detection. Finally, we add a gradient boosting-based classification layer. The evaluation of the proposed system using a 10-fold cross-validation on two challenging datasets (i.e., EyePACS and Messidor) indicates that it outperforms state-of-the-art methods. It will be useful for the initial screening of DR patients and will help graders in deciding quickly as regards patient referral to an ophthalmologist for further diagnosis and treatment.

show abstract

“…Dekhil et al adopted a transfer learning approach and classified the dataset's samples using the ImageNet architecture, which was previously trained on 3.2 million images [30]. Sikder et al presented a method incorporating the ExtraTree classifier, which is a popular ensemble learning algorithm [31]. Their paper used several image processing techniques to pre-process the retinal images and extracted histogram features from them.…”

Section: Employed Dataset and Prior Work On Itmentioning

confidence: 99%

Severity Classification of Diabetic Retinopathy Using an Ensemble Learning Algorithm through Analyzing Retinal Images

et al. 2021

Self Cite

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) refers to the damages endured by the retina as an effect of diabetes. DR has become a severe health concern worldwide, as the number of diabetes patients is soaring uncountably. Periodic eye examination allows doctors to detect DR in patients at an early stage to initiate proper treatments. Advancements in artificial intelligence and camera technology have allowed us to automate the diagnosis of DR, which can benefit millions of patients indeed. This paper inscribes a novel method for DR diagnosis based on the gray-level intensity and texture features extracted from fundus images using a decision tree-based ensemble learning technique. This study primarily works with the Asia Pacific Tele-Ophthalmology Society 2019 Blindness Detection (APTOS 2019 BD) dataset. We undertook several steps to curate its contents to make them more suitable for machine learning applications. Our approach incorporates several image processing techniques, two feature extraction techniques, and one feature selection technique, which results in a classification accuracy of 94.20% (margin of error: ±0.32%) and an F-measure of 93.51% (margin of error: ±0.5%). Several other parameters regarding the proposed method’s performance have been presented to manifest its robustness and reliability. Details on each employed technique have been included to make the provided results reproducible. This method can be a valuable tool for mass retinal screening to detect DR, thus drastically reducing the rate of vision loss attributed to it.

show abstract

Early Blindness Detection Based on Retinal Images Using Ensemble Learning

Cited by 20 publications

References 15 publications

Multi-Scale Attention-Based Mechanism in Gradient Boosting Convolutional Neural Network for Diabetic Retinopathy Grade Classification

Multi-Scale Attention-Based Mechanism in Gradient Boosting Convolutional Neural Network for Diabetic Retinopathy Grade Classification

Automatic Diabetic Retinopathy Diagnosis Using Adaptive Fine-Tuned Convolutional Neural Network

Severity Classification of Diabetic Retinopathy Using an Ensemble Learning Algorithm through Analyzing Retinal Images

Contact Info

Product

Resources

About