scholarly journals Fundus Image Classification Using VGG-19 Architecture with PCA and SVD

Symmetry ◽  
2018 ◽  
Vol 11 (1) ◽  
pp. 1 ◽  
Author(s):  
Muhammad Mateen ◽  
Junhao Wen ◽  
Nasrullah ◽  
Sun Song ◽  
Zhouping Huang
Keyword(s):  
Feature Selection ◽  
Diabetic Retinopathy ◽  
Image Classification ◽  
Medical Image Analysis ◽  
Retinal Disease ◽  
Gaussian Mixture ◽  
Computational Time ◽  
Diabetic Patients ◽  
Fundus Image ◽  
Value Decomposition

Automated medical image analysis is an emerging field of research that identifies the disease with the help of imaging technology. Diabetic retinopathy (DR) is a retinal disease that is diagnosed in diabetic patients. Deep neural network (DNN) is widely used to classify diabetic retinopathy from fundus images collected from suspected persons. The proposed DR classification system achieves a symmetrically optimized solution through the combination of a Gaussian mixture model (GMM), visual geometry group network (VGGNet), singular value decomposition (SVD) and principle component analysis (PCA), and softmax, for region segmentation, high dimensional feature extraction, feature selection and fundus image classification, respectively. The experiments were performed using a standard KAGGLE dataset containing 35,126 images. The proposed VGG-19 DNN based DR model outperformed the AlexNet and spatial invariant feature transform (SIFT) in terms of classification accuracy and computational time. Utilization of PCA and SVD feature selection with fully connected (FC) layers demonstrated the classification accuracies of 92.21%, 98.34%, 97.96%, and 98.13% for FC7-PCA, FC7-SVD, FC8-PCA, and FC8-SVD, respectively.

scholarly journals Effective Fundus Image Decomposition for the Detection of Red Lesions and Hard Exudates to Aid in the Diagnosis of Diabetic Retinopathy

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6549
Author(s):  
Roberto Romero-Oraá ◽  
María García ◽  
Javier Oraá-Pérez ◽  
María I. López-Gálvez ◽  
Roberto Hornero
Keyword(s):  
Diabetic Retinopathy ◽  
Lesion Detection ◽  
Computer Assisted ◽  
Diabetic Patients ◽  
Fundus Image ◽  
Public Database ◽  
Diagnostic Systems ◽  
Hard Exudates ◽  
The Public ◽  
Proprietary Database

Diabetic retinopathy (DR) is characterized by the presence of red lesions (RLs), such as microaneurysms and hemorrhages, and bright lesions, such as exudates (EXs). Early DR diagnosis is paramount to prevent serious sight damage. Computer-assisted diagnostic systems are based on the detection of those lesions through the analysis of fundus images. In this paper, a novel method is proposed for the automatic detection of RLs and EXs. As the main contribution, the fundus image was decomposed into various layers, including the lesion candidates, the reflective features of the retina, and the choroidal vasculature visible in tigroid retinas. We used a proprietary database containing 564 images, randomly divided into a training set and a test set, and the public database DiaretDB1 to verify the robustness of the algorithm. Lesion detection results were computed per pixel and per image. Using the proprietary database, 88.34% per-image accuracy (ACCi), 91.07% per-pixel positive predictive value (PPVp), and 85.25% per-pixel sensitivity (SEp) were reached for the detection of RLs. Using the public database, 90.16% ACCi, 96.26% PPV_p, and 84.79% SEp were obtained. As for the detection of EXs, 95.41% ACCi, 96.01% PPV_p, and 89.42% SE_p were reached with the proprietary database. Using the public database, 91.80% ACCi, 98.59% PPVp, and 91.65% SEp were obtained. The proposed method could be useful to aid in the diagnosis of DR, reducing the workload of specialists and improving the attention to diabetic patients.

scholarly journals A Multilevel Deep Feature Selection Framework for Diabetic Retinopathy Image Classification

2022 ◽  
Vol 70 (2) ◽  
pp. 2261-2276
Author(s):  
Farrukh Zia ◽  
Isma Irum ◽  
Nadia Nawaz Qadri ◽  
Yunyoung Nam ◽  
Kiran Khurshid ◽  
...  
Keyword(s):  
Feature Selection ◽  
Diabetic Retinopathy ◽  
Image Classification ◽  
Deep Feature ◽  
Selection Framework

scholarly journals DAVS-NET: Dense Aggregation Vessel Segmentation Network for retinal vasculature detection in fundus images

PLoS ONE ◽  
2021 ◽  
Vol 16 (12) ◽  
pp. e0261698
Author(s):  
Mohsin Raza ◽  
Khuram Naveed ◽  
Awais Akram ◽  
Nema Salem ◽  
Amir Afaq ◽  
...  
Keyword(s):  
Deep Learning ◽  
Blood Vessels ◽  
Medical Image Analysis ◽  
Retinal Disease ◽  
Disease Diagnosis ◽  
Vessel Segmentation ◽  
Diabetic Patients ◽  
Retinal Vasculature ◽  
Retinal Blood Vessels ◽  
Dense Aggregation

In this era, deep learning-based medical image analysis has become a reliable source in assisting medical practitioners for various retinal disease diagnosis like hypertension, diabetic retinopathy (DR), arteriosclerosis glaucoma, and macular edema etc. Among these retinal diseases, DR can lead to vision detachment in diabetic patients which cause swelling of these retinal blood vessels or even can create new vessels. This creation or the new vessels and swelling can be analyzed as biomarker for screening and analysis of DR. Deep learning-based semantic segmentation of these vessels can be an effective tool to detect changes in retinal vasculature for diagnostic purposes. This segmentation task becomes challenging because of the low-quality retinal images with different image acquisition conditions, and intensity variations. Existing retinal blood vessels segmentation methods require a large number of trainable parameters for training of their networks. This paper introduces a novel Dense Aggregation Vessel Segmentation Network (DAVS-Net), which can achieve high segmentation performance with only a few trainable parameters. For faster convergence, this network uses an encoder-decoder framework in which edge information is transferred from the first layers of the encoder to the last layer of the decoder. Performance of the proposed network is evaluated on publicly available retinal blood vessels datasets of DRIVE, CHASE_DB1, and STARE. Proposed method achieved state-of-the-art segmentation accuracy using a few number of trainable parameters.

scholarly journals DIABETIC RETINOPATHY;

2018 ◽  
Vol 25 (08) ◽  
pp. 1256-1260
Author(s):  
Nasir Ahmad Chaudhary ◽  
Samreen Hameed ◽  
Muhammad Sultan Ul Moazzam ◽  
Sarmad Zahoor ◽  
Sidrah Latif ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Predictive Value ◽  
Tertiary Care ◽  
Retinal Disease ◽  
Cross Sectional Study ◽  
Diabetic Patients ◽  
Cross Sectional ◽  
Retinal Examination ◽  
Tertiary Care Hospitals ◽  
Hba1c Levels

Background: Diabetic retinopathy is one of the most common complications ofdiabetes affecting more than 1/4th of the diabetics and is also the leading cause of blindness inmany parts of the globe. Regular fundoscopic examination for screening is a routine practicein tertiary care hospitals but is not available in the primary care centers. This necessitatesthe development of a reliable screening tool which will allow for early referral of those withcomplications to the specialist centers. Objective: To determine the predictive value of HbA1clevels for the presence of diabetic retinopathy. Study Design: A cross-sectional study. Setting:Diabetic Clinic of Mayo Hospital, Lahore. Period: 04 months, January to April 2017. Method:75 diabetic patients who presented in Diabetic clinic were investigated for HbA1c levels andfundoscopic evaluation was done to detect retinal changes. Results: Out of 75 patients, 35(46.7%) were female, 40 (53.3%) were male. Median age of the patients was 51 years. All patientshad HbA1c levels more than 6.0% and 62% patients had detectable changes on fundi while therest had no detectable retinal disease despite elevated HbA1c levels. Positive predictive value(PPV) of elevated HbA1c levels for the presence of diabetic retinal changes was calculated tobe 62.66%. Conclusion: All the patients who had retinal disease on fundoscopy had HbA1clevels of more than 6.0% (PPV = 62.66) which means that elevated HbA1c levels warrant afundoscopic retinal examination to rule out diabetic retinopathy.

scholarly journals Automated Detection and Classification of Diabetic Retinopathy using ConvNets

2021 ◽  
Vol 9 (10) ◽  
pp. 1360-1369
Author(s):  
Aavani B
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Confusion Matrix ◽  
Diabetic Patients ◽  
Fundus Image ◽  
Data Set ◽  
Permanent Loss ◽  
Process Computer ◽  
Degree Classification

Abstract: Diabetic retinopathy is the leading cause of blindness in diabetic patients. Screening of diabetic retinopathy using fundus image is the most effective way. As the time increases this DR leads to permanent loss of vision. At present, Diabetic retinopathy is still being treated by hand by an ophthalmologist which is a time-consuming process. Computer aided and fully automatic diagnosis of DR plays an important role in now a day. Data-set containing a collection of fundus images of different severity scale is used to analyze the fundus image of DR patients. Here the deep neural network model is trained by using this fundus image and five-degree classification task is performed. We were able to produce an sensitivity of 90%. Keywords: Confusion matrix, Deep convolutional Neural Network, Diabetic Retinopathy, Fundus image, OCT

Sign in / Sign up

Export Citation Format

Share Document