Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item A Transfer Learning Approach for Diabetic Retinopathy Classification Using Deep Convolutional Neural Networks(Institute of Electrical and Electronics Engineers Inc., 2018) Krishnan, A.S.; Clive, D.R.; Bhat, V.; Ramteke, P.B.; Koolagudi, S.G.Diabetic Retinopathy is a disease in which the retina is damaged due to diabetes mellitus. It is a leading cause for blindness today. Detection and quantification of such mellitus from retinal images is tedious and requires expertise. In this paper, an automatic identification of severity of Diabetic Retinopathy using Convolutional Neural Networks (CNNs) with a transfer learning approach has been proposed to aid the diagnostic process. A comparison of different CNN architectures such as ResNet, Inception-ResNet-v2 etc. is done using the quadratic weighted kappa metric. The qualitative and quantitative evaluation of the proposed approach is carried out on the Diabetic Retinopathy detection dataset from Kaggle. From the results, we observe that the proposed model achieves a kappa score of 0.76. © 2018 IEEE.Item Diabetic Retinopathy Severity Classification based on attention mechanism(Institute of Electrical and Electronics Engineers Inc., 2023) Jha, A.; Ananthanarayana, V.S.One of the significant factors causing blindness is diabetic retinopathy, a typical microvascular side effect of diabetes. Highly qualified professionals often examine colored fundus photos to identify this catastrophic condition. It takes much time and effort for ophthalmologists to diagnose diabetic retinopathy (DR) manually. The number of diabetes patients has dramatically increased during the last several years, which has made automated DR diagnosis a research hotspot. This paper proposes a hybrid deep learning model using a pre-trained DenseNet architecture integrated with CBAM for feature refinement. The dataset provided by the Kaggle Asia Pacific Tele-Ophthalmology Society (APTOS), having 3662 fundus images, is used in this research. In the multiclass classification experiment, we achieved 86.22% accuracy and 91.44 Kappa score(QWK). The local interpretable model-agnostic explanations (LIME) framework is used to assess predictions further and produce visual explanations, which can assist in decreasing the drawback of black-box models in aiding medical decision-making. © 2023 IEEE.Item Diabetic Retinopathy Detection Using Novel Loss Function in Deep Learning(Springer Science and Business Media Deutschland GmbH, 2024) Singh, S.; Annappa, B.; Dodia, S.Globally, the number of diabetics has significantly increased in recent years. Several age groups are affected. Diabetic Retinopathy (DR) affects those with diabetes for a long time. DR is a side effect of diabetes that affects the retina’s blood vessels and is caused by high blood sugar levels. Therefore, early detection and treatment are preferred. Manual recognition concerns and a lack of technology support for ophthalmologists are the most complex problems. Nowadays, Deep Learning (DL) based approaches are used significantly for creating DR detection systems because of the ongoing development of Artificial Intelligence (AI) techniques. This paper uses the APTOS dataset of retina images to train four deep Convolution Neural Network (CNN) models using a novel loss function. The four DL models used are VGG16, Resnet50, DenseNet121, and DenseNet169 to explain their rich properties and improve the classification for different phases of DR. The experimental results of this study demonstrate that VGG16 produced the lowest accuracy of 73.26% on the APTOS dataset, while DenseNet169-based detection gives the most significant result of 96.68% accuracy among the four approaches. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item Automated identification of diabetic retinopathy stages using digital fundus images(2008) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.; Lim, C.M.; Kagathi, M.Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources for mass screening of diabetic retinopathy. In this work, we have proposed a computer-based approach for the detection of diabetic retinopathy stage using fundus images. Image preprocessing, morphological processing techniques and texture analysis methods are applied on the fundus images to detect the features such as area of hard exudates, area of the blood vessels and the contrast. Our protocol uses total of 140 subjects consisting of two stages of DR and normal. Our extracted features are statistically significant (p<0.0001) with distinct mean±SD as shown in Table 1. These features are then used as an input to the artificial neural network (ANN) for an automatic classification. The detection results are validated by comparing it with expert ophthalmologists. We demonstrated a classification accuracy of 93%, sensitivity of 90% and specificity of 100%. © 2007 Springer Science+Business Media, LLC.Item Automatic identification of diabetic maculopathy stages using fundus images(2009) Nayak, J.; Subbanna Bhat, P.S.; Acharya, R.Diabetes mellitus is a major cause of visual impairment and blindness. Twenty years after the onset of diabetes, almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will have some degree of retinopathy. Prolonged diabetes retinopathy leads to maculopathy, which impairs the normal vision depending on the severity of damage of the macula. This paper presents a computer-based intelligent system for the identification of clinically significant maculopathy, non-clinically significant maculopathy and normal fundus eye images. Features are extracted from these raw fundus images which are then fed to the classifier. Our protocol uses feed-forward architecture in an artificial neural network classifier for classification of different stages. Three different kinds of eye disease conditions were tested in 350 subjects. We demonstrated a sensitivity of more than 95% for these classifiers with a specificity of 100%, and results are very promising. Our systems are ready to run clinically on large amounts of datasets. © 2009 Informa Healthcare USA, Inc.