Journal
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
Volume 12, Issue 10, Pages 9825-9839Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s12652-020-02727-z
Keywords
Diabetic retinopathy (DR); Pre-trained convolutional neural network; Retinal fundus images; Spatial pooling; Composite deep Neural network; Multi-modal features; Gated-attention; Transfer learning
Ask authors/readers for more resources
The proposed composite deep neural network architecture with gated-attention mechanism improves automatic diagnosis of diabetic retinopathy by utilizing multi-modal representations over uni-modal representations. The model achieved higher accuracy and Kappa score for diabetic retinopathy severity level prediction, demonstrating improved performance compared to existing best models.
Diabetic Retinopathy (DR) is a micro vascular complication caused by long-term diabetes mellitus. Unidentified diabetic retinopathy leads to permanent blindness. Early identification of this disease requires frequent complex diagnostic procedure which is expensive and time consuming. In this article, we propose a composite deep neural network architecture with gated-attention mechanism for automated diagnosis of diabetic retinopathy. The feature descriptors obtained from multiple pre-trained deep Convolutional Neural Networks (CNNs) are used to represent color fundus retinal images. Spatial pooling methods are introduced to get the reduced versions of these representations without loosing much information. The proposed composite DNN learns independently from each of these reduced representations through different channels and contributes to improving the model generalization. In addition, model also includes gated attention blocks which allows the model to emphasize more on lesion portions of the retinal images while reduced attention to the non-lesion regions. Our experiments on APTOS-2019 Kaggle blindness detection challenge reveal that, the proposed approach leads to improved performance when compared to the existing best models. Our empirical studies also reveal that, the proposed approach leads to more generalised predictions with multi-modal representations when compared to those of uni-modal representations. The proposed composite deep neural network model recorded an accuracy of 82.54% (up arrow 2%), and a Kappa score of 79 (up arrow 9points) for diabetic retinopathy severity level prediction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available