Sheila C. Nemeth

Automatic detection of diabetic retinopathy and age-related macular degeneration in digital fundus images

PURPOSE To describe and evaluate the performance of an algorithm that automatically classifies images with pathologic features commonly found in diabetic retinopathy (DR) and age-related macular degeneration (AMD). METHODS Retinal digital photographs (N = 2247) of three fields of view (FOV) were obtained of the eyes of 822 patients at two centers: The Retina Institute of South Texas (RIST, San Antonio, TX) and The University of Texas Health Science Center San Antonio (UTHSCSA). Ground truth was provided for the presence of pathologic conditions, including microaneurysms, hemorrhages, exudates, neovascularization in the optic disc and elsewhere, drusen, abnormal pigmentation, and geographic atrophy. The algorithm was used to report on the presence or absence of disease. A detection threshold was applied to obtain different values of sensitivity and specificity with respect to ground truth and to construct a receiver operating characteristic (ROC) curve. RESULTS The system achieved an average area under the ROC curve (AUC) of 0.89 for detection of DR and of 0.92 for detection of sight-threatening DR (STDR). With a fixed specificity of 0.50, the systems sensitivity ranged from 0.92 for all DR cases to 1.00 for clinically significant macular edema (CSME). CONCLUSIONS A computer-aided algorithm was trained to detect different types of pathologic retinal conditions. The cases of hard exudates within 1 disc diameter (DD) of the fovea (surrogate for CSME) were detected with very high accuracy (sensitivity = 1, specificity = 0.50), whereas mild nonproliferative DR was the most challenging condition (sensitivity = 0.92, specificity = 0.50). The algorithm was also tested on images with signs of AMD, achieving a performance of AUC of 0.84 (sensitivity = 0.94, specificity = 0.50).

Computer-aided methods for quantitative assessment of longitudinal changes in retinal images presenting with maculopathy

This paper presents the results from applying a computer- based methodology for making precise measurements of longitudinal changes in a patients digital retinal images presenting with age-related macular degeneration. The digital retinal image analysis system applies recognized principles in automatic image segmentation and integrates the automation with a graphical user interface. Drusen, retinal lesions associated with age-related macular degeneration (ARMD), were segmented using a region-growing algorithm. The algorithm calculates the 76 percentile intensity in a region to provide seed points for the neighborhood-growing algorithm. Twenty-one cases were analyzed. Agreement statistics (kappa) were determined by comparing the automated results with those provided from manually derived measurements. Agreement statistics ranged from 0.49 to 0.71 for different regions of the retina. The manual analysis ground truth was performed by trained graders from the University of Wisconsin Reading Center using guidelines found in the Wisconsin Age-Related Maculopathy Degeneration Grading Scheme (WARMGS). Because of the time required, the ophthalmic graders can only grade (size, area, type) the most prominent drusen in specific regions, resulting in a small sampling of drusen lesions in the retina. The computer-based approach allows one to efficiently and comprehensively grade all of the lesions for larger numbers of images. The additional advantage, however, is in the precision and total area that can be graded with the computer-aided technology. Computer-registered longitudinal images produced a precise determination of the temporal changes in the individual lesions. This study has demonstrated a robust segmentation and registration methodology for automatic and semiautomatic detection and measurement of abnormal regions in longitudinal retinal images.

A Multiscale Optimization Approach to Detect Exudates in the Macula

Pathologies that occur on or near the fovea, such as clinically significant macular edema (CSME), represent high risk for vision loss. The presence of exudates, lipid residues of serous leakage from damaged capillaries, has been associated with CSME, in particular if they are located one optic disc-diameter away from the fovea. In this paper, we present an automatic system to detect exudates in the macula. Our approach uses optimal thresholding of instantaneous amplitude (IA) components that are extracted from multiple frequency scales to generate candidate exudate regions. For each candidate region, we extract color, shape, and texture features that are used for classification. Classification is performed using partial least squares (PLS). We tested the performance of the system on two different databases of 652 and 400 images. The system achieved an area under the receiver operator characteristic curve (AUC) of 0.96 for the combination of both databases and an AUC of 0.97 for each of them when they were evaluated independently.

Automated image quality evaluation of retinal fundus photographs in diabetic retinopathy screening

This paper presents a system that can automatically determine whether the quality of a retinal image is sufficient for computer-based diabetic retinopathy (DR) screening. The system integrates global histogram features, textural features, and vessel density, as well as a local non-reference perceptual sharpness metric. A partial least square (PLS) classifier is trained to distinguish low quality images from normal quality images. The system was evaluated on a large, representative set of 1884 non-mydriatic retinal images from 412 subjects. An area under the ROC curve of 96% was achieved.

Optical imaging device of retinal function

An optical imaging device of retina function (OID-RF) has been constructed to record changes in reflected 700-nm light from the fundus caused by retinal activation in response to a visual 535-nm stimulus. The resulting images reveal areas of the retina activated by visual stimulation. This device is a modified fundus camera designed to provide a patterned, moving visual stimulus over a 45-degree field of view to the subject in the green wavelength portion of the visual spectrum while simultaneously imaging the fundus in another, longer wavelength range. Data was collected from 3 normal subjects and recorded for 13 seconds at 4 Hz; 3 seconds were recorded during pre-stimulus baseline, 5 seconds during the stimulus, and 5 seconds post-stimulus. This procedure was repeated several times and, after image registration, the images were averaged to improve signal to noise. The change in reflected intensity from the retina due to the stimulus was then calculated by comparison to the pre-stimulus state. Reflected intensity from areas of stimulated retina began to increase steadily within 1 second after stimulus onset and decayed after stimulus offset. These results indicated that a functional optical signal can be recorded from the human eye.

Automated retinal vessel type classification in color fundus images

Automated retinal vessel type classification is an essential first step toward machine-based quantitative measurement of various vessel topological parameters and identifying vessel abnormalities and alternations in cardiovascular disease risk analysis. This paper presents a new and accurate automatic artery and vein classification method developed for arteriolar-to-venular width ratio (AVR) and artery and vein tortuosity measurements in regions of interest (ROI) of 1.5 and 2.5 optic disc diameters from the disc center, respectively. This method includes illumination normalization, automatic optic disc detection and retinal vessel segmentation, feature extraction, and a partial least squares (PLS) classification. Normalized multi-color information, color variation, and multi-scale morphological features are extracted on each vessel segment. We trained the algorithm on a set of 51 color fundus images using manually marked arteries and veins. We tested the proposed method in a previously unseen test data set consisting of 42 images. We obtained an area under the ROC curve (AUC) of 93.7% in the ROI of AVR measurement and 91.5% of AUC in the ROI of tortuosity measurement. The proposed AV classification method has the potential to assist automatic cardiovascular disease early detection and risk analysis.

ART-based image analysis for pigmented lesions of the skin

Presents a robust, reliable computer-aided diagnostic tool for analyzing pigmented lesions of the skin, particularly malignant melanoma. The goal is to produce quantitative information to assist clinicians and researchers in diagnosing, monitoring and understanding the physiological processes of melanocytic lesions. The system described combines an adaptive resonance theory (ART) neural network with a comprehensive user interface and image analysis tools to extract quantitative information from color photographs of skin lesions. The ART operates on an RGB image, clustering the image into homogeneous regions. Connected component analysis extracts these regions and computes shape parameters and a color variegation metric. ART offers the advantages of well-understood theoretical properties, an efficient implementation, and clustering properties that are consistent with human perception.

Utility of color information for segmentation of digital retinal images: neural-network-based approach

The goal of this study was to determine the utility of red, green and blue color information in segmenting fundus images for two general categories of retinal tissue: anatomically normal and pathological. The pathologies investigated were microaneurysms and dot blot hemorrhages.

Full automation of morphological segmentation of retinal images: a comparison with human-based analysis

Age-Related Macular Degeneration (ARMD) is the leading cause of irreversible visual loss among the elderly in the US and Europe. A computer-based system has been developed to provide the ability to track the position and margin of the ARMD associated lesion; drusen. Variations in the subjects retinal pigmentation, size and profusion of the lesions, and differences in image illumination and quality present significant challenges to most segmentation algorithms. An algorithm is presented that first classifies the image to optimize the variables of a mathematical morphology algorithm. A binary image is found by applying Otsus method to the reconstructed image. Lesion size and area distribution statistics are then calculated. For training and validation, the University of Wisconsin provided longitudinal images of 22 subjects from their 10 year Beaver Dam Study. Using the Wisconsin Age-Related Maculopathy Grading System, three graders classified the retinal images according to drusen size and area of involvement. The percentages within the acceptable error between the three graders and the computer are as follows: Grader-A: Area: 84% Size: 81%; Grader-B: Area: 63% Size: 76%; Grader-C: Area: 81% Size: 88%. To validate the segmented position and boundary one grader was asked to digitally outline the drusen boundary. The average accuracy based on sensitivity and specificity was 0.87 for thirty four marked regions.

A multiscale decomposition approach to detect abnormal vasculature in the optic disc

This paper presents a multiscale method to detect neovascularization in the optic disc (NVD) using fundus images. Our method is applied to a manually selected region of interest (ROI) containing the optic disc. All the vessels in the ROI are segmented by adaptively combining contrast enhancement methods with a vessel segmentation technique. Textural features extracted using multiscale amplitude-modulation frequency-modulation, morphological granulometry, and fractal dimension are used. A linear SVM is used to perform the classification, which is tested by means of 10-fold cross-validation. The performance is evaluated using 300 images achieving an AUC of 0.93 with maximum accuracy of 88%.