English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Diabetic Retinopathy (DR) is one of the major causes of visual impairment andblindness across the world. It is usually found in patients who suffer fromdiabetes for a long period. The major focus of this work is to derive optimalrepresentation of retinal images that further helps to improve the performanceof DR recognition models. To extract optimal representation, features extractedfrom multiple pre-trained ConvNet models are blended using proposed multi-modalfusion module. These final representations are used to train a Deep NeuralNetwork (DNN) used for DR identification and severity level prediction. As eachConvNet extracts different features, fusing them using 1D pooling and crosspooling leads to better representation than using features extracted from asingle ConvNet. Experimental studies on benchmark Kaggle APTOS 2019 contestdataset reveals that the model trained on proposed blended featurerepresentations is superior to the existing methods. In addition, we noticethat cross average pooling based fusion of features from Xception and VGG16 isthe most appropriate for DR recognition. With the proposed model, we achieve anaccuracy of 97.41%, and a kappa statistic of 94.82 for DR identification and anaccuracy of 81.7% and a kappa statistic of 71.1% for severity level prediction.Another interesting observation is that DNN with dropout at input layerconverges more quickly when trained using blended features, compared to thesame model trained using uni-modal deep features.

Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction