Damon Wing Kee Wong

Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma Screening

Glaucoma is a chronic eye disease that leads to vision loss. As it cannot be cured, detecting the disease in time is important. Current tests using intraocular pressure (IOP) are not sensitive enough for population based glaucoma screening. Optic nerve head assessment in retinal fundus images is both more promising and superior. This paper proposes optic disc and optic cup segmentation using superpixel classification for glaucoma screening. In optic disc segmentation, histograms, and center surround statistics are used to classify each superpixel as disc or non-disc. A self-assessment reliability score is computed to evaluate the quality of the automated optic disc segmentation. For optic cup segmentation, in addition to the histograms and center surround statistics, the location information is also included into the feature space to boost the performance. The proposed segmentation methods have been evaluated in a database of 650 images with optic disc and optic cup boundaries manually marked by trained professionals. Experimental results show an average overlapping error of 9.5% and 24.1% in optic disc and optic cup segmentation, respectively. The results also show an increase in overlapping error as the reliability score is reduced, which justifies the effectiveness of the self-assessment. The segmented optic disc and optic cup are then used to compute the cup to disc ratio for glaucoma screening. Our proposed method achieves areas under curve of 0.800 and 0.822 in two data sets, which is higher than other methods. The methods can be used for segmentation and glaucoma screening. The self-assessment will be used as an indicator of cases with large errors and enhance the clinical deployment of the automatic segmentation and screening.

Level-set based automatic cup-to-disc ratio determination using retinal fundus images in ARGALI

Glaucoma is a leading cause of permanent blindness. However, disease progression can be limited if detected early. The optic cup-to-disc ratio (CDR) is one of the main clinical indicators of glaucoma, and is currently determined manually, limiting its potential in mass screening. In this paper, we propose an automatic CDR determination method using a variational level-set approach to segment the optic disc and cup from retinal fundus images. The method is a core component of ARGALI, a system for automated glaucoma risk assessment. Threshold analysis is used in pre-processing to estimate the initial contour. Due to the presence of retinal vasculature traversing the disc and cup boundaries which can cause inaccuracies in the detected contours, an ellipse-fitting post-processing step is also introduced. The method was tested on 104 images from the Singapore Malay Eye Study, and it was found the results produced a clinically acceptable variation of up to 0.2 CDR units from the manually graded samples, with potential use in mass screening.

ARGALI: An Automatic Cup-to-Disc Ratio Measurement System for Glaucoma Analysis Using Level-set Image Processing

Glaucoma is a leading cause of blindness worldwide, accounting for 12.3% of the permanently blind according to the World Heath Organization. The disease is particularly prevalent in Asia, with up to 50% of total glaucoma cases found in the region. Although glaucomatous damage is irreversible, studies have shown that early detection can be effective in slowing or halting glaucomatous atrophy. The ratio of the size of the optic cup to the optic disc, also known as the cup-to-disc ratio (CDR), is an important indicator for glaucoma assessment, since glaucomatous progression corresponds to increased excavation of the optic cup. In current clinical practice, the CDR is measured manually and can be subjective, limiting its use in screening for early detection. We describe the ARGALI system which automatically calculates the CDR from non-stereographic retinal fundus photographs, providing a fast, objective and consistent measurement. The ARGALI system consists of a series of steps. As the optic disc occupies only a small region of the entire retinal image, a region of interest is first extracted via pixel intensity analysis. Variational level-set algorithm is next used to segment the optic disc. Optic cup segmentation is more challenging due to the cup’s interweavement with blood vessels and surrounding tissues. A multi-modal approach consisting of different methods is used extract the cup. To obtain a smoother contour, ellipse fitting is applied to the extracted cup and disc. A neural network has also been proposed to fuse the results obtained via the various modes. The ARGALI system was tested using images collected from patients at the Singapore Eye Research Institute and achieves an RMS error of 0.05 with a risk assessment accuracy of 95%. The results are promising for ARGALI to be developed into a low cost, objective and efficient screening system for automatic assessment glaucoma risk assessment.

Validating retinal fundus image analysis algorithms: Issues and a proposal

This paper concerns the validation of automatic retinal image analysis (ARIA) algorithms. For reasons of space and consistency, we concentrate on the validation of algorithms processing color fundus camera images, currently the largest section of the ARIA literature. We sketch the context (imaging instruments and target tasks) of ARIA validation, summarizing the main image analysis and validation techniques. We then present a list of recommendations focusing on the creation of large repositories of test data created by international consortia, easily accessible via moderated Web sites, including multicenter annotations by multiple experts, specific to clinical tasks, and capable of running submitted software automatically on the data stored, with clear and widely agreed-on performance criteria, to provide a fair comparison.

Automated segmentation of optic disc and optic cup in fundus images for glaucoma diagnosis

The vertical Cup-to-Disc Ratio (CDR) is an important indicator in the diagnosis of glaucoma. Automatic segmentation of the optic disc (OD) and optic cup is crucial towards a good computer-aided diagnosis (CAD) system. This paper presents a statistical model-based method for the segmentation of the optic disc and optic cup from digital color fundus images. The method combines knowledge-based Circular Hough Transform and a novel optimal channel selection for segmentation of the OD. Moreover, we extended the method to optic cup segmentation, which is a more challenging task. The system was tested on a dataset of 325 images. The average Dice coefficient for the disc and cup segmentation is 0.92 and 0.81 respectively, which improves significantly over existing methods. The proposed method has a mean absolute CDR error of 0.10, which outperforms existing methods. The results are promising and thus demonstrate a good potential for this method to be used in a mass screening CAD system.

Model-based optic nerve head segmentation on retinal fundus images

The optic nerve head (optic disc) plays an important role in the diagnosis of retinal diseases. Automatic localization and segmentation of the optic disc is critical towards a good computer-aided diagnosis (CAD) system. In this paper, we propose a method that combines edge detection, the Circular Hough Transform and a statistical deformable model to detect the optic disc from retinal fundus images. The algorithm was evaluated against a data set of 325 digital color fundus images, which includes both normal images and images with various pathologies. The result shows that the average error in area overlap is 11.3% and the average absolute area error is 10.8%, which outperforms existing methods. The result indicates a high correlation with ground truth segmentation and thus demonstrates a good potential for this system to be integrated with other retinal CAD systems.

Optic cup and disk extraction from retinal fundus images for determination of cup-to-disc ratio

The ratio of the optic cup to disc (CDR) in retinal fundus images is one of the principal physiological characteristics in the diagnosis of glaucoma. Currently the CDR is manually determined which can be subjective and limits its use in mass screening. To automatically extract the disc, a variational level set method is proposed in this paper. For the cup, two methods making use of color intensity and threshold level set are evaluated. A batch of 73 retinal images from the Singapore Eye Research Centre was used to assess the performance of the determined CDR to the clinical CDR, and it was found that the threshold and variational level set methods produced 97% accuracy in the determined CDR results, an 18% improvement over the color intensity method. The results indicate potential applicability of the methods for automated and objective mass screening for early detection of glaucoma.

Intelligent fusion of cup-to-disc ratio determination methods for glaucoma detection in ARGALI

Glaucoma is a leading cause of permanent blindness. ARGALI, an automated system for glaucoma detection, employs several methods for segmenting the optic cup and disc from retinal images, combined using a fusion network, to determine the cup to disc ratio (CDR), an important clinical indicator of glaucoma. This paper discusses the use of SVM as an alternative fusion strategy in ARGALI, and evaluates its performance against the component methods and neural network (NN) fusion in the CDR calculation. The results show SVM and NN provide similar improvements over the component methods, but with SVM having a greater consistency over the NN, suggesting potential for SVM as a viable option in ARGALI.

Automatic optic disc segmentation with peripapillary atrophy elimination

Optic disc segmentation from retinal fundus image is a fundamental but important step for automatic glaucoma diagnosis. In this paper, an optic disc segmentation method is proposed based on peripapillary atrophy elimination. The elimination is done through edge filtering, constraint elliptical Hough transform and peripapillary atrophy detection. With the elimination, edges that are likely from non-disc structures especially peripapillary atrophy are excluded to make the segmentation more accurate. The proposed method has been tested in a database of 650 images with disc boundaries marked by trained professionals manually. The experimental results by the proposed method show average m1, m2 and mVD of 10.0%, 7.4% and 4.9% respectively. It can be used to compute cup to disc ratio as well as other features for application in automatic glaucoma diagnosis systems.

Towards automatic detection of age-related macular degeneration in retinal fundus images

Age-related macular degeneration (AMD) is a leading cause of blindness worldwide. The disease is highly associated with age, and becoming increasingly prevalent in our aging societies. Drusen is a pathological feature that is well-associated with AMD. In this paper, we present a method of detecting drusen in retinal fundus images. The method first determines the location of the macula, which is used as a landmark for a clinical drusen grading overlay. Subsequently, regions of drusen are identified though a maximal region-based pixel intensity approach via RGB and HSV channels. Methods of reducing the effect of retinal and choroidal vessels are also described. The system is tested on a sample set of 16 fundus images from a clinical study, with half having drusen. Experiments on the results show a sensitivity and specificity of 0.75 on the test image set.