M. Usman Akram

Identification and classification of microaneurysms for early detection of diabetic retinopathy

Diabetic retinopathy is a progressive eye disease which may cause blindness if not detected and treated in time. The early detection and diagnosis of diabetic retinopathy is important to protect the patients vision. The accurate detection of microaneurysms (MAs) is a critical step for early detection of diabetic retinopathy because they appear as the first sign of disease. In this paper, we propose a three-stage system for early detection of MAs using filter banks. In the first stage, the system extracts all possible candidate regions for MAs present in retinal image. In order to classify a candidate region as MA or non-MA, the system formulates a feature vector for each region depending upon certain properties, i.e. shape, color, intensity and statistics. We present a hybrid classifier which combines the Gaussian mixture model (GMM), support vector machine (SVM) and an extension of multimodel mediod based modeling approach in an ensemble to improve the accuracy of classification. The proposed system is evaluated using publicly available retinal image databases and achieved higher accuracy which is better than previously published methods.

Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results.

Detection and classification of retinal lesions for grading of diabetic retinopathy

Diabetic Retinopathy (DR) is an eye abnormality in which the human retina is affected due to an increasing amount of insulin in blood. The early detection and diagnosis of DR is vital to save the vision of diabetes patients. The early signs of DR which appear on the surface of the retina are microaneurysms, haemorrhages, and exudates. In this paper, we propose a system consisting of a novel hybrid classifier for the detection of retinal lesions. The proposed system consists of preprocessing, extraction of candidate lesions, feature set formulation, and classification. In preprocessing, the system eliminates background pixels and extracts the blood vessels and optic disc from the digital retinal image. The candidate lesion detection phase extracts, using filter banks, all regions which may possibly have any type of lesion. A feature set based on different descriptors, such as shape, intensity, and statistics, is formulated for each possible candidate region: this further helps in classifying that region. This paper presents an extension of the m-Mediods based modeling approach, and combines it with a Gaussian Mixture Model in an ensemble to form a hybrid classifier to improve the accuracy of the classification. The proposed system is assessed using standard fundus image databases with the help of performance parameters, such as, sensitivity, specificity, accuracy, and the Receiver Operating Characteristics curves for statistical analysis.

Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy

There is an ever-increasing interest in the development of automatic medical diagnosis systems due to the advancement in computing technology and also to improve the service by medical community. The knowledge about health and disease is required for reliable and accurate medical diagnosis. Diabetic Retinopathy (DR) is one of the most common causes of blindness and it can be prevented if detected and treated early. DR has different signs and the most distinctive are microaneurysm and haemorrhage which are dark lesions and hard exudates and cotton wool spots which are bright lesions. Location and structure of blood vessels and optic disk play important role in accurate detection and classification of dark and bright lesions for early detection of DR. In this article, we propose a computer aided system for the early detection of DR. The article presents algorithms for retinal image preprocessing, blood vessel enhancement and segmentation and optic disk localization and detection which eventually lead to detection of different DR lesions using proposed hybrid fuzzy classifier. The developed methods are tested on four different publicly available databases. The presented methods are compared with recently published methods and the results show that presented methods outperform all others.

Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy

Medical image analysis is a very popular research area these days in which digital images are analyzed for the diagnosis and screening of different medical problems. Diabetic retinopathy (DR) is an eye disease caused by the increase of insulin in blood and may cause blindness. An automated system for early detection of DR can save a patients vision and can also help the ophthalmologists in screening of DR. The background or nonproliferative DR contains four types of lesions, i.e., microaneurysms, hemorrhages, hard exudates, and soft exudates. This paper presents a method for detection and classification of exudates in colored retinal images. We present a novel technique that uses filter banks to extract the candidate regions for possible exudates. It eliminates the spurious exudate regions by removing the optic disc region. Then it applies a Bayesian classifier as a combination of Gaussian functions to detect exudate and nonexudate regions. The proposed system is evaluated and tested on publicly available retinal image databases using performance parameters such as sensitivity, specificity, and accuracy. We further compare our system with already proposed and published methods to show the validity of the proposed system.

Retinal images: optic disk localization and detection

Automated localization and detection of the optic disc (OD) is an essential step in the analysis of digital diabetic retinopathy systems. Accurate localization and detection of optic disc boundary is very useful in proliferative diabetic retinopathy where fragile vessels develop in the retina. In this paper, we propose an automated system for optic disk localization and detection. Our method localizes optic disk using average filter and thresholding, extracts the region of interest (ROI) containing optic disk to save time and detects the optic disk boundary using Hough transform. This method can be used in computerized analysis of retinal images, e.g., in automated screening for diabetic retinopathy. The technique is tested on publicly available DRIVE, STARE, diaretdb0 and diaretdb1 databases of manually labeled images which have been established to facilitate comparative studies on localization and detection of optic disk in retinal images. The proposed method achieves an average accuracy of 96.7% for localization and an average area under the receiver operating characteristic curve of 0.958 for optic detection.

An automated system for colored retinal image background and noise segmentation

Retinal images are used for the automated diagnosis of diabetic retinopathy. The retinal image quality must be improved for the detection of features and abnormalities and for this purpose segmentation of retinal images is vital. In this paper, we present a novel automated approach for segmentation of colored retinal images. Our segmentation technique smoothes and strengthens images by separating the background and noisy area from the overall image thus resulting in retinal image enhancement and lower processing time. It contains coarse segmentation and fine segmentation. Standard retinal images databases Diaretdb0 and Diaretdb1 are used to test the validation of our segmentation technique. Experimental results indicate our approach is effective and can get higher segmentation accuracy.

Automated detection of exudates and macula for grading of diabetic macular edema

Medical systems based on state of the art image processing and pattern recognition techniques are very common now a day. These systems are of prime interest to provide basic health care facilities to patients and support to doctors. Diabetic macular edema is one of the retinal abnormalities in which diabetic patient suffers from severe vision loss due to affected macula. It affects the central vision of the person and causes total blindness in severe cases. In this article, we propose an intelligent system for detection and grading of macular edema to assist the ophthalmologists in early and automated detection of the disease. The proposed system consists of a novel method for accurate detection of macula using a detailed feature set and Gaussian mixtures model based classifier. We also present a new hybrid classifier as an ensemble of Gaussian mixture model and support vector machine for improved exudate detection even in the presence of other bright lesions which eventually leads to reliable classification of input retinal image in different stages of macular edema. The statistical analysis and comparative evaluation of proposed system with existing methods are performed on publicly available standard retinal image databases. The proposed system has achieved average value of 97.3%, 95.9% and 96.8% for sensitivity, specificity and accuracy respectively on both databases.

Computer aided system for brain tumor detection and segmentation

Magnetic resonance (MR) images are a very useful tool to detect the tumor growth in brain but precise brain image segmentation is a difficult and time consuming process. In this paper we propose a method for automatic brain tumor diagnostic system from MR images. The system consists of three stages to detect and segment a brain tumor. In the first stage, MR image of brain is acquired and preprocessing is done to remove the noise and to sharpen the image. In the second stage, global threshold segmentation is done on the sharpened image to segment the brain tumor. In the third stage, the segmented image is post processed by morphological operations and tumor masking in order to remove the false segmented pixels. Results and experiments show that our propose technique accurately identifies and segments the brain tumor in MR images.

Detection of neovascularization in retinal images using multivariate m-Mediods based classifier

Diabetic retinopathy is a progressive eye disease and one of the leading causes of blindness all over the world. New blood vessels (neovascularization) start growing at advance stage of diabetic retinopathy known as proliferative diabetic retinopathy. Early and accurate detection of proliferative diabetic retinopathy is very important and crucial for protection of patients vision. Automated systems for detection of proliferative diabetic retinopathy should identify between normal and abnormal vessels present in digital retinal image. In this paper, we proposed a new method for detection of abnormal blood vessels and grading of proliferative diabetic retinopathy using multivariate m-Mediods based classifier. The system extracts the vascular pattern and optic disc using a multilayered thresholding technique and Hough transform respectively. It grades the fundus image in different categories of proliferative diabetic retinopathy using classification and optic disc coordinates. The proposed method is evaluated using publicly available retinal image databases and results show that the proposed system detects and grades proliferative diabetic retinopathy with high accuracy.