Identification and classification of microaneurysms for early detection of diabetic retinopathy

Akram, M. Usman; Khalid, Shehzad; Khan, Shoab Ahmed

doi:10.1016/j.patcog.2012.07.002

Cited by 250 publications

(76 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At the scale t k the MA candidates, defined by C t k are extracted by thresholding K he (x; t k ) > α. Since the MAs have a roughly circular shape and a small size, all the regions in C t k larger than 100 pixels and with eccentricity [14] larger than 0.95 are removed. Next, the regions in C t k that intersect the vascular segmentation V b , or without any region with intersections of the global MA candidates C are discarded.…”

Section: Mas Finer Scales Assessmentmentioning

confidence: 99%

Microaneurysms detection using a novel neighborhood analysis

Soares

Castelo‐Branco

Pinheiro

2014

Proceedings of the Ophthalmic Medical Image Analysis First International Workshop

View full text Add to dashboard Cite

Abstract. The earliest sign of the diabetic retinopathy is the appearance of small red dots in retinal fundus images, designated by microaneurysms. In this paper a scale-space based method is proposed for the microaneurysms detection. Initially, the method performs a segmentation of the retinal vasculature and defines a global set of microaneurysms candidates, using both coarser and finer scales. Using the finer scales, a set of microaneurysms candidates are analysed in terms of shape and size. Then, a set of gaussian-shaped matched filters are used to reduce the number of false microaneurysms candidates. Each candidate is labeled as a true microaneurysm using a new neighborhood analysis method. The proposed algorithm was tested with the training Retinopathy Online Challenge (ROC) dataset, revealing a 47% Sensitivity with an average number of 37.9 false positives per image.

show abstract

Section: Mas Finer Scales Assessmentmentioning

confidence: 99%

Microaneurysms detection using a novel neighborhood analysis

Soares

Castelo‐Branco

Pinheiro

2014

Proceedings of the Ophthalmic Medical Image Analysis First International Workshop

View full text Add to dashboard Cite

show abstract

“…So, diabetic retinopathy caused by microaneurysms are not detected. Whereas [22], Only focuses on microaneurysms for the early detection of diabetic retinopathy. Also, all [20][21][22] classify images into two classes.…”

Section: Introductionmentioning

confidence: 99%

“…Also, all [20][21][22] classify images into two classes. While in compare to [20][21][22] our model uses latest state-of-art algorithm such as Convolution Neural Network, and takes advantage of the very powerful GPU by using NVIDIA CUDA Deep Neural Network (cuDNN). Also, we use a huge dataset of 53576 number of images for testing our model (validation) and train on 35100 number of images.…”

Section: Introductionmentioning

confidence: 99%

Detecting Diabetic Retinopathy from Retinal Images Using CUDA Deep Neural Network

Parmar¹,

Lakshmanan²

2017

IJIES

View full text Add to dashboard Cite

A microvascular impediment, Diabetic Retinopathy, is observed due to long term diabetes and is one of the significant reason for visual impedance because of variations in veins of the retina. Significant loss of vision due to Diabetic Retinopathy can be profoundly prevented with proper screening and medication at a more earlier stage. The evaluating procedure comprises of perceiving fine points of interest, for example, microaneurysms, to some greater elements, for example, exudates, and some of the time their position in respect to each other on pictures of the eye. Our task here is to predict the class for each of the images. We classify our images into five categories We are using Convolutional Neural Networks for our prediction model and we train our model on GPU. GPU-accelerated library of primitives aimed at Deep Neural Networks, NVIDIA CUDA Deep Neural Network (cuDNN) is used in our model. Our model has around 85% of accuracy when tested on 53576 number of retinal images. Our solution is elegant and automated, saving a lot of time and manual efforts.

show abstract

“…They extracted the features using various preprocessing algorithms. They combined different classifiers for the final decision of DR. Akram et al [12] extracted the candidate lesions using Gabor filter bank. The final classification was based on hybrid classifier.…”

Section: Introductionmentioning

confidence: 99%

An efficient method for early stage detection of diabetic retinopathy

Shirbahadurkar¹,

Mané²,

Jadhav³

2017

IJET

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is one of the leading causes of blindness. The early detection and treatment of DR is significant to save the human vision. The presence of microaneurysms (MAs) is the first sign of the disease. The correct identification of MAs is an essential for finding of DR at the early stages. In this paper, we propose a three phase system for efficient recognition of MAs. The tentative MA lesions are recovered from the fundus image in the first stage. To accurately classify an extracted candidate region into MA or non-MA, the second stage prepares an attribute vector for each tentative MA lesion based on shape, intensity and statistical properties. The third stage is a classification step to classify as MAs and Non-MAs for early stage detection of DR. We present a holoentropy enabled decision tree classifier which combines entropy and total correlation. The best feature for decision tree is selected based on holoentropy to enhance the correctness of the classification. The implemented system is experimented using fundus image database DIARETDB1. The proposed method achieved an overall accuracy of 97.67%. The proposed system has detected the MAs with higher performance using simple features and holoentropy based decision tree classifier. The proposed system is suitable for early stage detection of DR through the accurate identification of MAs.

show abstract

Identification and classification of microaneurysms for early detection of diabetic retinopathy

Cited by 250 publications

References 29 publications

Microaneurysms detection using a novel neighborhood analysis

Microaneurysms detection using a novel neighborhood analysis

Detecting Diabetic Retinopathy from Retinal Images Using CUDA Deep Neural Network

An efficient method for early stage detection of diabetic retinopathy

Contact Info

Product

Resources

About