Sarah Barman

Blood vessel segmentation methodologies in retinal images - A survey

Retinal vessel segmentation algorithms are a fundamental component of automatic retinal disease screening systems. This work examines the blood vessel segmentation methodologies in two dimensional retinal images acquired from a fundus camera and a survey of techniques is presented. The aim of this paper is to review, analyze and categorize the retinal vessel extraction algorithms, techniques and methodologies, giving a brief description, highlighting the key points and the performance measures. We intend to give the reader a framework for the existing research; to introduce the range of retinal vessel segmentation algorithms; to discuss the current trends and future directions and summarize the open problems. The performance of algorithms is compared and analyzed on two publicly available databases (DRIVE and STARE) of retinal images using a number of measures which include accuracy, true positive rate, false positive rate, sensitivity, specificity and area under receiver operating characteristic (ROC) curve.

Relationship between intraocular lens biomaterials and posterior capsule opacification

Purpose: To determine whether posterior capsule opacification (PCO) is influenced by intraocular lens (IOL) material. Setting: A British teaching hospital eye department. Methods: Ninety eyes were prospectively randomized to receive a poly(methyl methacrylate) (PMMA), silicone, or AcrySof® IOL. All lenses had 6,0 mm optics and PMMA haptics. A standardized surgical protocol was performed by a single surgeon using an extracapsular technique with capsulorhexis. Patients having surgical complications were excluded, and all patients had standardized medication and follow‐up. Posterior capsule opacification was assessed by a digital retroillumination camera using a dedicated software program based on the analysis of texture in the image and calculated as the percentage area of opacified capsule. Data were analyzed 2 years postoperatively. Results: There was a significant difference in percentage of PCO at 2 years among the three lens types (P < .0001). The AcrySof lenses were associated with less PCO (median 11.75%) than PMMA (43.65%) and silicone (33.50%) lenses (P < .001 and P = .025, respectively). The difference between PMMA and silicone lenses was not statistically significant. Conclusion: Intraocular lenses made from AcrySof were associated with a significantly reduced degree of PCO.

The effect of polymethylmethacrylate, silicone, and polyacrylic intraocular lenses on posterior capsular opacification 3 years after cataract surgery

OBJECTIVE To compare the visual outcome, neodymium:YAG (Nd:YAG) capsulotomy rates, and percentage of posterior capsular opacification (PCO) seen with polymethylmethacrylate (PMMA), silicone, and polyacrylic intraocular lens implants 3 years after surgery. DESIGN Randomized, prospective trial. PARTICIPANTS Ninety eyes of 81 patients were examined at a British teaching hospital. INTERVENTION Ninety eyes were prospectively randomized to receive a PMMA, silicone, or polyacrylic (AcrySof, Alcon, Fort Worth, TX) implant. All lenses had 6-mm disc optics with PMMA haptics. A standardized surgical protocol was performed by a single surgeon using an extracapsular technique with capsulorhexis; any surgical complications were excluded and all patients had standardized postoperative medication and follow-up. MAIN OUTCOME MEASURES Patients were seen at 6 months and 1, 2, and 3 years after surgery. At 3 years, logarithm of the minimum angle of resolution (LogMAR) visual acuity and Pelli-Robson contrast sensitivity were measured and YAG capsulotomy rates determined. Posterior capsular opacification was assessed objectively by digital retroillumination imaging using dedicated software and calculated as the percentage area of opacified capsule. RESULTS At 3 years, the overall follow-up rate was 71%: 19 patients were available for examination with polyacrylic lens implants, 22 with silicone, and 23 with PMMA. There was a significant difference in percentage PCO at 3 years among the lens types (P = 0.0001). Polyacrylic lenses were associated with less PCO (10%) than silicone (40%) and PMMA lenses (56%). The YAG capsulotomy rate was 0% for polyacrylic, 14% for silicone, and 26% for PMMA (P = 0.05). The visual acuity and contrast sensitivity were not significantly different among the three groups if patients with age-related macular degeneration and those requiring YAG capsulotomies are excluded. CONCLUSIONS Intraocular lenses made from polyacrylic are associated with a significantly reduced degree of PCO and lower YAG rates.

An Ensemble Classification-Based Approach Applied to Retinal Blood Vessel Segmentation

This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. This method uses an ensemble system of bagged and boosted decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. The feature vector encodes information to handle the healthy as well as the pathological retinal image. The method is evaluated on the publicly available DRIVE and STARE databases, frequently used for this purpose and also on a new public retinal vessel reference dataset CHASE_DB1 which is a subset of retinal images of multiethnic children from the Child Heart and Health Study in England (CHASE) dataset. The performance of the ensemble system is evaluated in detail and the incurred accuracy, speed, robustness, and simplicity make the algorithm a suitable tool for automated retinal image analysis.

An approach to localize the retinal blood vessels using bit planes and centerline detection

The change in morphology, diameter, branching pattern or tortuosity of retinal blood vessels is an important indicator of various clinical disorders of the eye and the body. This paper reports an automated method for segmentation of blood vessels in retinal images. A unique combination of techniques for vessel centerlines detection and morphological bit plane slicing is presented to extract the blood vessel tree from the retinal images. The centerlines are extracted by using the first order derivative of a Gaussian filter in four orientations and then evaluation of derivative signs and average derivative values is performed. Mathematical morphology has emerged as a proficient technique for quantifying the blood vessels in the retina. The shape and orientation map of blood vessels is obtained by applying a multidirectional morphological top-hat operator with a linear structuring element followed by bit plane slicing of the vessel enhanced grayscale image. The centerlines are combined with these maps to obtain the segmented vessel tree. The methodology is tested on three publicly available databases DRIVE, STARE and MESSIDOR. The results demonstrate that the performance of the proposed algorithm is comparable with state of the art techniques in terms of accuracy, sensitivity and specificity.

Automatic Exudate Detection from Non-dilated Diabetic Retinopathy Retinal Images Using Fuzzy C-means Clustering

Exudates are the primary sign of Diabetic Retinopathy. Early detection can potentially reduce the risk of blindness. An automatic method to detect exudates from low-contrast digital images of retinopathy patients with non-dilated pupils using a Fuzzy C-Means (FCM) clustering is proposed. Contrast enhancement preprocessing is applied before four features, namely intensity, standard deviation on intensity, hue and a number of edge pixels, are extracted to supply as input parameters to coarse segmentation using FCM clustering method. The first result is then fine-tuned with morphological techniques. The detection results are validated by comparing with expert ophthalmologists’ hand-drawn ground-truths. Sensitivity, specificity, positive predictive value (PPV), positive likelihood ratio (PLR) and accuracy are used to evaluate overall performance. It is found that the proposed method detects exudates successfully with sensitivity, specificity, PPV, PLR and accuracy of 87.28%, 99.24%, 42.77%, 224.26 and 99.11%, respectively.

A review of ant algorithms

Ant algorithms are optimisation algorithms inspired by the foraging behaviour of real ants in the wild. Introduced in the early 1990s, ant algorithms aim at finding approximate solutions to optimisation problems through the use of artificial ants and their indirect communication via synthetic pheromones. The first ant algorithms and their development into the Ant Colony Optimisation (ACO) metaheuristic is described herein. An overview of past and present typical applications as well as more specialised and novel applications is given. The use of ant algorithms alongside more traditional machine learning techniques to produce robust, hybrid, optimisation algorithms is addressed, with a look towards future developments in this area of study.

An Automatic Approach for Learning and Tuning Gaussian Interval Type-2 Fuzzy Membership Functions Applied to Lung CAD Classification System

The potential of type-2 fuzzy sets to manage high levels of uncertainty in the subjective knowledge of experts or of numerical information has focused on control and pattern classification systems in recent years. One of the main challenges in designing a type-2 fuzzy logic system (FLS) is how to estimate the parameters of the type-2 fuzzy membership function (T2MF) and the footprint of uncertainty (FOU) from imperfect and noisy datasets. This paper presents an automatic approach to learn and tune Gaussian interval type-2 membership functions (IT2MFs) with application to multidimensional pattern classification problems. T2MFs and their FOUs are tuned according to the uncertainties in the training dataset by a combination of genetic algorithm (GA) and cross-validation techniques. In our GA-based approach, the structure of the chromosome has fewer genes than other GA methods, and chromosome initialization is more precise. The proposed approach addresses the application of the interval type-2 fuzzy logic system (IT2FLS) for the problem of nodule classification in a lung computer-aided detection system. The designed IT2FLS is compared with its type-1 fuzzy logic system (T1FLS) counterpart. The results demonstrate that the IT2FLS outperforms the T1FLS by more than 30% in terms of classification accuracy.

Posterior capsular opacification with hydrogel, polymethylmethacrylate, and silicone intraocular lenses: two-year results of a randomized prospective trial.

PURPOSE To compare the visual outcome, percentage of posterior capsular opacification, and laser capsulotomy rates with polymethylmethacrylate, silicone, and hydrogel intraocular lens implants at 1 and 2 years postoperatively. METHODS Ninety-three eyes of 93 patients were randomized to receive a polymethylmethacrylate, silicone, or hydrogel intraocular lens implant. A standardized surgical protocol was followed by a single surgeon using phacoemulsification with capsulorhexis; any patients with surgical complications were excluded, and all patients received standardized medication and follow-up. Patients were examined at days 1 and 7, months 1, 3, and 6, and years 1 and 2 after surgery. At each assessment, best-corrected logMAR visual acuity and Pelli-Robson contrast sensitivity were measured. Posterior capsular opacification was objectively assessed by digital retroillumination imaging with the use of a dedicated software program and calculated as the percentage area of opacified capsule. Laser capsulotomy was performed if the eye had lost 2 lines of visual acuity with a clinically opaque capsule. RESULTS At 2 years postoperatively, the mean percentage area of posterior capsular opacification for hydrogel lenses was 63%; for polymethylmethacrylate, 46%; and for silicone, 17%. Hydrogel intraocular lenses were associated with 17% more posterior capsule opacification than were polymethylmethacrylate lenses (95% confidence interval, 1-33; P =. 037) and 45% more than were silicone lenses (95% confidence interval, 33-58; P <.0001) at 2 years. Polymethylmethacrylate lenses had 28% more posterior capsule opacification than silicone lenses (95% confidence interval, 13-43; P <.0001) at 2 years. Twenty-eight percent of patients with hydrogel intraocular lenses required an Nd:YAG laser posterior capsulotomy at 2 years, compared with 14% with polymethylmethacrylate, whereas no patients with silicone lenses needed a capsulotomy (P =.014). Visual acuity was not significantly different among the three groups, but patients with silicone intraocular lenses had significantly better contrast sensitivity than those with hydrogel lenses (P =.046). CONCLUSIONS Intraocular lenses made of this specific hydrogel were associated with a significantly higher degree of posterior capsular opacification and more laser capsulotomies than polymethylmethacrylate and silicone intraocular lenses.

Shape and Texture Based Plant Leaf Classification

This article presents a novel method for classification of plants using their leaves. Most plant species have unique leaves which differ from each other by characteristics such as the shape, colour, texture and the margin. The method introduced in this study proposes to use two of these features: the shape and the texture. The shape-based method will extract the contour signature from every leaf and then calculate the dissimilarities between them using the Jeffrey-divergence measure. The orientations of edge gradients will be used to analyse the macro-texture of the leaf. The results of these methods will then be combined using an incremental classification algorithm.