Abstract
Early detection of retinopathy plays an important role in the care of people with diabetes. Classification of diabetic retinopathy in fundus images is very challenging because the blood vessels in the retinal images are too small. Morphology of objects with multi-level saliency is the recent choice because of the activation of feature extraction. However, the challenges of the input models are very complex with the blood. The color, lighting or context can become the reasons that create the decline of the primary key for training. This paper proposes a method for classification of diabetic retinopathy using saliency and shape detection of objects based on a deep Bottleneck U-Net (DbU-Net) and support vector machines in retinal blood vessels. The proposed method includes four stages: preprocessing, feature extraction using DbU-Net, saliency prediction and classification based on the support vector machine. To evaluate this method, its results are compared to the results of the other methods by using the same datasets of STARE and DRIVE for testing with evaluation criteria such as sensitivity, specificity, and accuracy. The accuracy of the proposed method is about 97.1% in these datasets. To assess the levels of diabetes, the diagnostician must initially identify the retinal image with diabetes or not. The result of this paper may help the diagnostician to easily do this.
Highlights
The diagnosis of abnormality in medical images depends on many factors such as doctor skills, equipments, etc
This paper proposed a method for diabetic classification in retinal vessels based on the deep Bottleneck U-Net with saliency
With the evaluation of the segmentation based on a wide range of deep learning models, Jaccard Index (JI) value was used to evaluate the results of the proposed method
Summary
The diagnosis of abnormality in medical images depends on many factors such as doctor skills, equipments, etc. Diabetes damages the blood vessels of all organs in the human body. It is most evident in the microvasculature. The body responds by secreting factors that stimulate the growth of new blood vessels to nourish these areas of the retina. This paper proposed a method for diabetic classification in retinal vessels based on the deep Bottleneck U-Net with saliency. The proposed method includes four stages: preprocessing, feature extraction using deep Bottleneck U-Net (DbU-Net), saliency prediction and classification based on support vector machines. Proposing the deep Bottleneck U-Net (DbU-Net) to match diabetic classification in retinal vessels, the structure of U-Net adapts with multi levels of saliency and retinal blood vessels images.
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have