The region of interest localization for glaucoma analysis from retinal fundus image using deep learning

2018 ◽  
Vol 165 ◽  
pp. 25-35 ◽  
Author(s):  
Anirban Mitra ◽  
Priya Shankar Banerjee ◽  
Sudipta Roy ◽  
Somasis Roy ◽  
Sanjit Kumar Setua
Keyword(s):  
Deep Learning ◽  
Region Of Interest ◽  
Fundus Image ◽  
Retinal Fundus Image ◽  
Retinal Fundus

Diabetic Retinopathy Prediction Device System

2019 ◽  
Vol 16 (10) ◽  
pp. 4266-4270
Author(s):  
Meenu Garg ◽  
Sheifali Gupta ◽  
Rakesh Ahuja ◽  
Deepali Gupta
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Treatment Effect ◽  
Physiological Parameters ◽  
Early Prediction ◽  
Fundus Image ◽  
Retinal Fundus Image ◽  
Image Capturing ◽  
The One ◽  
Retinal Fundus

The present study relates to diagnostic devices, and more specifically, to a diabetic retinopathy prediction device, system and method for early prediction of diabetic retinopathy with application of deep learning. The device includes an image capturing device, a memory coupled to processor. The image capturing device obtains a retinal fundus image from the user. The memory comprising executable instructions which upon execution by the processor configures the device to obtain physiological parameters of the user in real-time from the image capturing device, retrieve the obtained retinal fundus image and the one or more obtained physiological parameters and compare the one or more extracted features with at least one pre-stored feature in a database to generate at least a prediction result indicative of detection of the presence, the progression or the treatment effect of the disease in the user.

scholarly journals Early Detection Of Glaucoma Disease In Retinal Fundus Images Using Spatial FCM With Level Set Segmentation

2019 ◽  
Vol 8 (5C) ◽  
pp. 1342-1349
Keyword(s):  
Early Detection ◽  
Optic Disc ◽  
Region Of Interest ◽  
Clinical Parameter ◽  
Fundus Image ◽  
Specificity And Sensitivity ◽  
Retinal Fundus Image ◽  
Optic Cup ◽  
Standard Value ◽  
Retinal Fundus

Glaucoma is a malady of the optic nerve brought about by the expansion in the intraocular weight of the eye. It for the most part influences the optic plate by expanding the cup size. In this proposed method the clinical parameter such as vertical optic cup to disk ratio (CDR) is determined to identify the glaucomatous disease. The segmentation of optic disc (OD) and optic cup in retinal fundus image is an important step in the determination of CDR. Optic Disc is extracted from the fundus image by circular region of interest with Hough transformation. Linear regression fit is used to find the Gold standard value for the experimentally obtained CDR A Bayesian classifier is used to train the classifier set of CDR values obtained. Results produced from the classification obtain a accuracy of 94.28%, sensitivity of 94.38% and specificity of 94.11%. ROC curve is plotted to study the relation between specificity and sensitivity of the CDR and GSV. This proposed approach is robust in segmentation and the region boundaries are precise and is able to yield regions more homogeneous which can be used for objective mass screening of retinal images for early detection of Glaucoma.

scholarly journals Image Preprocessing in Classification and Identification of Diabetic Eye Diseases

2021 ◽  
Author(s):  
Rubina Sarki ◽  
Khandakar Ahmed ◽  
Hua Wang ◽  
Yanchun Zhang ◽  
Jiangang Ma ◽  
...  
Keyword(s):  
Image Processing ◽  
Image Quality ◽  
Geometric Transformation ◽  
Diabetic Patients ◽  
Fundus Image ◽  
Classification Problems ◽  
Specificity And Sensitivity ◽  
Retinal Fundus Image ◽  
Retinal Fundus ◽  
Traditional Image

AbstractDiabetic eye disease (DED) is a cluster of eye problem that affects diabetic patients. Identifying DED is a crucial activity in retinal fundus images because early diagnosis and treatment can eventually minimize the risk of visual impairment. The retinal fundus image plays a significant role in early DED classification and identification. An accurate diagnostic model’s development using a retinal fundus image depends highly on image quality and quantity. This paper presents a methodical study on the significance of image processing for DED classification. The proposed automated classification framework for DED was achieved in several steps: image quality enhancement, image segmentation (region of interest), image augmentation (geometric transformation), and classification. The optimal results were obtained using traditional image processing methods with a new build convolution neural network (CNN) architecture. The new built CNN combined with the traditional image processing approach presented the best performance with accuracy for DED classification problems. The results of the experiments conducted showed adequate accuracy, specificity, and sensitivity.

Feature extraction from retinal fundus image for early detection of diabetic retinopathy

2013 ◽  
Author(s):  
Syna Sreng ◽  
Jun-Ichi Takada ◽  
Noppadol Maneerat ◽  
Don Isarakorn ◽  
Ruttikorn Varakulsiripunth ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Diabetic Retinopathy ◽  
Early Detection ◽  
Fundus Image ◽  
Retinal Fundus Image ◽  
Retinal Fundus
Sign in / Sign up

Export Citation Format

Share Document