Automatic detection of red lesions in digital color fundus photographs

Automatic detection of microaneurysms and hemorrhages in digital fundus images

An efficient approach for automatic detection of red lesions in ocular fundus images based on pixel classification and mathematical morphology is proposed. Experimental evaluation of the proposed approach demonstrates better performance over other red lesion detection algorithms, and when determining whether an image contains red lesions the proposed approach achieves a sensitivity of 100% and specificity of 91%.

General retinal vessel segmentation using regularization-based multiconcavity modeling

Detecting blood vessels in retinal images with the presence of bright and dark lesions is a challenging unsolved problem. In this paper, a novel multiconcavity modeling approach is proposed to handle both healthy and unhealthy retinas simultaneously. The differentiable concavity measure is proposed to handle bright lesions in a perceptive space. The line-shape concavity measure is proposed to remove dark lesions which have an intensity structure different from the line-shaped vessels in a retina. The locally normalized concavity measure is designed to deal with unevenly distributed noise due to the spherical intensity variation in a retinal image. These concavity measures are combined together according to their statistical distributions to detect vessels in general retinal images. Very encouraging experimental results demonstrate that the proposed method consistently yields the best performance over existing state-of-the-art methods on the abnormal retinas and its accuracy outperforms the human observer, which has not been achieved by any of the state-of-the-art benchmark methods. Most importantly, unlike existing methods, the proposed method shows very attractive performances not only on healthy retinas but also on a mixture of healthy and pathological retinas.

Automated detection of diabetic retinopathy: barriers to translation into clinical practice

Automated identification of diabetic retinopathy (DR), the primary cause of blindness and visual loss for those aged 18-65 years, from color images of the retina has enormous potential to increase the quality, cost-effectiveness and accessibility of preventative care for people with diabetes. Through advanced image analysis techniques, retinal images are analyzed for abnormalities that define and correlate with the severity of DR. Translating automated DR detection into clinical practice will require surmounting scientific and nonscientific barriers. Scientific concerns, such as DR detection limits compared with human experts, can be studied and measured. Ethical, legal and political issues can be addressed, but are difficult or impossible to measure. The primary objective of this review is to survey the methods, potential benefits and limitations of automated detection in order to better manage translation into clinical practice, based on extensive experience with the systems we have developed.

Automated early detection of diabetic retinopathy

PURPOSE

To compare the performance of automated diabetic retinopathy (DR) detection, using the algorithm that won the 2009 Retinopathy Online Challenge Competition in 2009, the Challenge2009, against that of the one currently used in EyeCheck, a large computer-aided early DR detection project.

DESIGN

Evaluation of diagnostic test or technology.

PARTICIPANTS

Fundus photographic sets, consisting of 2 fundus images from each eye, were evaluated from 16670 patient visits of 16,670 people with diabetes who had not previously been diagnosed with DR.

METHODS

The fundus photographic set from each visit was analyzed by a single retinal expert; 793 of the 16,670 sets were classified as containing more than minimal DR (threshold for referral). The outcomes of the 2 algorithmic detectors were applied separately to the dataset and were compared by standard statistical measures.

MAIN OUTCOME MEASURES

The area under the receiver operating characteristic curve (AUC), a measure of the sensitivity and specificity of DR detection.

RESULTS

Agreement was high, and examination results indicating more than minimal DR were detected with an AUC of 0.839 by the EyeCheck algorithm and an AUC of 0.821 for the Challenge2009 algorithm, a statistically nonsignificant difference (z-score, 1.91). If either of the algorithms detected DR in combination, the AUC for detection was 0.86, the same as the theoretically expected maximum. At 90% sensitivity, the specificity of the EyeCheck algorithm was 47.7% and that of the Challenge2009 algorithm was 43.6%.

CONCLUSIONS

Diabetic retinopathy detection algorithms seem to be maturing, and further improvements in detection performance cannot be differentiated from best clinical practices, because the performance of competitive algorithm development now has reached the human intrareader variability limit. Additional validation studies on larger, well-defined, but more diverse populations of patients with diabetes are needed urgently, anticipating cost-effective early detection of DR in millions of people with diabetes to triage those patients who need further care at a time when they have early rather than advanced DR.

Three-dimensional analysis of retinal layer texture: identification of fluid-filled regions in SD-OCT of the macula

Optical coherence tomography (OCT) is becoming one of the most important modalities for the noninvasive assessment of retinal eye diseases. As the number of acquired OCT volumes increases, automating the OCT image analysis is becoming increasingly relevant. In this paper, a method for automated characterization of the normal macular appearance in spectral domain OCT (SD-OCT) volumes is reported together with a general approach for local retinal abnormality detection. Ten intraretinal layers are first automatically segmented and the 3-D image dataset flattened to remove motion-based artifacts. From the flattened OCT data, 23 features are extracted in each layer locally to characterize texture and thickness properties across the macula. The normal ranges of layer-specific feature variations have been derived from 13 SD-OCT volumes depicting normal retinas. Abnormalities are then detected by classifying the local differences between the normal appearance and the retinal measures in question. This approach was applied to determine footprints of fluid-filled regions--SEADs (Symptomatic Exudate-Associated Derangements)--in 78 SD-OCT volumes from 23 repeatedly imaged patients with choroidal neovascularization (CNV), intra-, and sub-retinal fluid and pigment epithelial detachment. The automated SEAD footprint detection method was validated against an independent standard obtained using an interactive 3-D SEAD segmentation approach. An area under the receiver-operating characteristic curve of 0.961 +/- 0.012 was obtained for the classification of vertical, cross-layer, macular columns. A study performed on 12 pairs of OCT volumes obtained from the same eye on the same day shows that the repeatability of the automated method is comparable to that of the human experts. This work demonstrates that useful 3-D textural information can be extracted from SD-OCT scans and--together with an anatomical atlas of normal retinas--can be used for clinically important applications.

Automated quantification of inherited phenotypes from color images: a twin study of the variability of optic nerve head shape

PURPOSE

Discovery and description of heritable optic nerve head (ONH) phenotypes have been haphazard. In this preliminary study, the authors test the hypothesis that inheritable phenotypes can be discovered and quantified computationally by estimating three-dimensional ONH shape parameters from stereo color photographs from the Twins Eye Study in Tasmania and determining how much of the variability in ONH shape is accounted for by genetic influence.

METHODS

Three-dimensional ONH shape was estimated by an automated algorithm from stereoscopic optic disc color photographs of a random sample of 172 subjects (344 eyes, 45 pairs of monozygotic [MZ] and 41 dizygotic [DZ] twins). Shape resemblances between eyes were quantified with a distance metric. The heritability of the shape resemblance was determined both through the distribution of the discongruence indices and through structural equation modeling techniques (ACE model).

RESULTS

Significantly different discongruence indices were found for MZ (1.0286; 95% CI, 0.9872-1.0701) and DZ twins (1.4218; 95% CI, 1.2631-1.5804); larger indices for DZ twins indicated that variability was substantially determined by genetic factors. The standardized variances of the A(dditive genetic), C(ommon environmental), and (nonshared) E(nvironmental) components were 0.80, 2.00 × 10(-15) and 0.20, respectively, for all OD, and 0.79, 3.24 × 10(-14), and 0.21 for all OS.

CONCLUSIONS

This preliminary study shows that quantitative phenotyping of the ONH shape from color images leads to phenotypes that can be measured and are largely under genetic control. The association of these inherited phenotypes with genotypes deserves confirmation and further study.

Algorithms for the automated detection of diabetic retinopathy using digital fundus images: a review

Diabetes is a chronic end organ disease that occurs when the pancreas does not secrete enough insulin or the body is unable to process it properly. Over time, diabetes affects the circulatory system, including that of the retina. Diabetic retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. Ophthalmologists recognize diabetic retinopathy based on features, such as blood vessel area, exudes, hemorrhages, microaneurysms and texture. In this paper we review algorithms used for the extraction of these features from digital fundus images. Furthermore, we discuss systems that use these features to classify individual fundus images. The classifications efficiency of different DR systems is discussed. Most of the reported systems are highly optimized with respect to the analyzed fundus images, therefore a generalization of individual results is difficult. However, this review shows that the classification results improved has improved recently, and it is getting closer to the classification capabilities of human ophthalmologists.

Multiscale AM-FM methods for diabetic retinopathy lesion detection

In this paper, we propose the use of multiscale amplitude-modulation-frequency-modulation (AM-FM) methods for discriminating between normal and pathological retinal images. The method presented in this paper is tested using standard images from the early treatment diabetic retinopathy study. We use 120 regions of 40 x 40 pixels containing four types of lesions commonly associated with diabetic retinopathy (DR) and two types of normal retinal regions that were manually selected by a trained analyst. The region types included microaneurysms, exudates, neovascularization on the retina, hemorrhages, normal retinal background, and normal vessels patterns. The cumulative distribution functions of the instantaneous amplitude, the instantaneous frequency magnitude, and the relative instantaneous frequency angle from multiple scales are used as texture feature vectors. We use distance metrics between the extracted feature vectors to measure interstructure similarity. Our results demonstrate a statistical differentiation of normal retinal structures and pathological lesions based on AM-FM features. We further demonstrate our AM-FM methodology by applying it to classification of retinal images from the MESSIDOR database. Overall, the proposed methodology shows significant capability for use in automatic DR screening.

Retinal imaging and image analysis

Many important eye diseases as well as systemic diseases manifest themselves in the retina. While a number of other anatomical structures contribute to the process of vision, this review focuses on retinal imaging and image analysis. Following a brief overview of the most prevalent causes of blindness in the industrialized world that includes age-related macular degeneration, diabetic retinopathy, and glaucoma, the review is devoted to retinal imaging and image analysis methods and their clinical implications. Methods for 2-D fundus imaging and techniques for 3-D optical coherence tomography (OCT) imaging are reviewed. Special attention is given to quantitative techniques for analysis of fundus photographs with a focus on clinically relevant assessment of retinal vasculature, identification of retinal lesions, assessment of optic nerve head (ONH) shape, building retinal atlases, and to automated methods for population screening for retinal diseases. A separate section is devoted to 3-D analysis of OCT images, describing methods for segmentation and analysis of retinal layers, retinal vasculature, and 2-D/3-D detection of symptomatic exudate-associated derangements, as well as to OCT-based analysis of ONH morphology and shape. Throughout the paper, aspects of image acquisition, image analysis, and clinical relevance are treated together considering their mutually interlinked relationships.

Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs

The detection of microaneurysms in digital color fundus photographs is a critical first step in automated screening for diabetic retinopathy (DR), a common complication of diabetes. To accomplish this detection numerous methods have been published in the past but none of these was compared with each other on the same data. In this work we present the results of the first international microaneurysm detection competition, organized in the context of the Retinopathy Online Challenge (ROC), a multiyear online competition for various aspects of DR detection. For this competition, we compare the results of five different methods, produced by five different teams of researchers on the same set of data. The evaluation was performed in a uniform manner using an algorithm presented in this work. The set of data used for the competition consisted of 50 training images with available reference standard and 50 test images where the reference standard was withheld by the organizers (M. Niemeijer, B. van Ginneken, and M. D. Abràmoff). The results obtained on the test data was submitted through a website after which standardized evaluation software was used to determine the performance of each of the methods. A human expert detected microaneurysms in the test set to allow comparison with the performance of the automatic methods. The overall results show that microaneurysm detection is a challenging task for both the automatic methods as well as the human expert. There is room for improvement as the best performing system does not reach the performance of the human expert. The data associated with the ROC microaneurysm detection competition will remain publicly available and the website will continue accepting submissions.

A system for computerised retinal haemorrhage analysis

Background

Our aim was to develop an objective computerised system for measuring different types of retinal haemorrhages in differing digital images, for use as a research tool. Despite developing various fully automated systems of retinal haemorrhage measurement we ultimately found user interaction to be necessary to achieve satisfactory validity of segmentation, and developed an interactive system of haemorrhage assessment based on this.

Findings

The Haemorrhage Assessment System (HAS) presented here is an open access interactive program with graphical user interface allowing the ophthalmically trained user to easily delineate different haemorrhage types, optic disc and fovea. The system then automatically calculates a variety of measures, including mean haemorrhage area, total haemorrhage area, centre of mass, distance of centre of mass from disc and fovea, eccentricity and orientation. This paper presents evidence for the validity of HAS by comparison against established software and known results for geometric images.

Conclusion

The system should be of use to experimenters studying the distribution and topography of vitreoretinal haemorrhages who require a means of accurately quantifying an ophthalmologist's gold standard assessment of a digital image.

Information fusion for diabetic retinopathy CAD in digital color fundus photographs

The purpose of computer-aided detection or diagnosis (CAD) technology has so far been to serve as a second reader. If, however, all relevant lesions in an image can be detected by CAD algorithms, use of CAD for automatic reading or prescreening may become feasible. This work addresses the question how to fuse information from multiple CAD algorithms, operating on multiple images that comprise an exam, to determine a likelihood that the exam is normal and would not require further inspection by human operators. We focus on retinal image screening for diabetic retinopathy, a common complication of diabetes. Current CAD systems are not designed to automatically evaluate complete exams consisting of multiple images for which several detection algorithm output sets are available. Information fusion will potentially play a crucial role in enabling the application of CAD technology to the automatic screening problem. Several different fusion methods are proposed and their effect on the performance of a complete comprehensive automatic diabetic retinopathy screening system is evaluated. Experiments show that the choice of fusion method can have a large impact on system performance. The complete system was evaluated on a set of 15,000 exams (60,000 images). The best performing fusion method obtained an area under the receiver operator characteristic curve of 0.881. This indicates that automated prescreening could be applied in diabetic retinopathy screening programs.

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

Application of higher order spectra for the identification of diabetes retinopathy stages

Diabetic retinopathy (DR) is a condition where the retina is damaged due to fluid leaking from the blood vessels into the retina. In extreme cases, the patient will become blind. Therefore, early detection of diabetic retinopathy is crucial to prevent blindness. Various image processing techniques have been used to identify the different stages of diabetes retinopathy. The application of non-linear features of the higher-order spectra (HOS) was found to be efficient as it is more suitable for the detection of shapes. The aim of this work is to automatically identify the normal, mild DR, moderate DR, severe DR and prolific DR. The parameters are extracted from the raw images using the HOS techniques and fed to the support vector machine (SVM) classifier. This paper presents classification of five kinds of eye classes using SVM classifier. Our protocol uses, 300 subjects consisting of five different kinds of eye disease conditions. We demonstrate a sensitivity of 82% for the classifier with the specificity of 88%.

Automated diagnosis of retinopathy by content-based image retrieval

PURPOSE

To describe a novel computer-based image analysis method that is being developed to assist and automate the diagnosis of retinal disease.

METHODS

Content-based image retrieval is the process of retrieving related images from large database collections using their pictorial content. The content feature list becomes the index for storage, search, and retrieval of related images from a library based upon specific visual characteristics. Low-level analyses use feature description models and higher-level analyses use perceptual organization and spatial relationships, including clinical metadata, to extract semantic information.

RESULTS

We defined, extracted, and tested a large number of region- and lesion-based features from a dataset of 395 retinal images. Using a statistical hold-one-out method, independent queries for each image were submitted to the system and a diagnostic prediction was formulated. The diagnostic sensitivity for all stratified levels of age-related macular degeneration ranged from 75% to 100%. Similarly, the sensitivity of detection and accuracy for proliferative diabetic retinopathy ranged from 75% to 91.7% and for nonproliferative diabetic retinopathy, ranged from 75% to 94.7%. The overall purity of the diagnosis (specificity) for all disease states in the dataset was 91.3%.

CONCLUSIONS

The probabilistic nature of content-based image retrieval permits us to make statistically relevant predictions regarding the presence, severity, and manifestations of common retinal diseases from digital images in an automated and deterministic manner.

Optimal wavelet transform for the detection of microaneurysms in retina photographs

In this paper, we propose an automatic method to detect microaneurysms in retina photographs. Microaneurysms are the most frequent and usually the first lesions to appear as a consequence of diabetic retinopathy. So, their detection is necessary for both screening the pathology and follow up (progression measurement). Automating this task, which is currently performed manually, would bring more objectivity and reproducibility. We propose to detect them by locally matching a lesion template in subbands of wavelet transformed images. To improve the method performance, we have searched for the best adapted wavelet within the lifting scheme framework. The optimization process is based on a genetic algorithm followed by Powell's direction set descent. Results are evaluated on 120 retinal images analyzed by an expert and the optimal wavelet is compared to different conventional mother wavelets. These images are of three different modalities: there are color photographs, green filtered photographs, and angiographs. Depending on the imaging modality, microaneurysms were detected with a sensitivity of respectively 89.62%, 90.24%, and 93.74% and a positive predictive value of respectively 89.50%, 89.75%, and 91.67%, which is better than previously published methods.

A probabilistic framework for content-based diagnosis of retinal disease

Diabetic retinopathy is the leading cause of blindness in the working age population in the industrialized world. Computer assisted analysis has the potential to assist in the early detection of diabetes by regular screening of large populations. The widespread availability of digital fundus cameras today is leading to the accumulation of large image archives of diagnosed patient data that captures historical knowledge of retinal pathology. Through this research we are developing a content-based image retrieval method to verify our hypothesis that retinal pathology can be identified and quantified from visually similar retinal images in an image archive. We will present diagnostic results for specificity and sensitivity on a population of 395 fundus images representing the normal fundus and 14 stratified disease states.

The automatic detection of the optic disc location in retinal images using optic disc location regression

The automatic detection of the position of the optic disc is an important step in the automatic analysis of retinal images. A method to detect the approximate position of the optic disc using kNN regression is presented. The method starts by building a regression model of the optic disc position. Using a prior vessel segmentation all vessel pixels are searched for those which are inside the optic disc according to the regression model. The regression output is blurred to handle noise. The point which is closest to the middle of the optic disc is chosen. The method was tested on 1000 screening images and was able to find the correct position in 99.9% of all cases.

Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes

OBJECTIVE

To evaluate the performance of a system for automated detection of diabetic retinopathy in digital retinal photographs, built from published algorithms, in a large, representative, screening population.

RESEARCH DESIGN AND METHODS

We conducted a retrospective analysis of 10,000 consecutive patient visits, specifically exams (four retinal photographs, two left and two right) from 5,692 unique patients from the EyeCheck diabetic retinopathy screening project imaged with three types of cameras at 10 centers. Inclusion criteria included no previous diagnosis of diabetic retinopathy, no previous visit to ophthalmologist for dilated eye exam, and both eyes photographed. One of three retinal specialists evaluated each exam as unacceptable quality, no referable retinopathy, or referable retinopathy. We then selected exams with sufficient image quality and determined presence or absence of referable retinopathy. Outcome measures included area under the receiver operating characteristic curve (number needed to miss one case [NNM]) and type of false negative.

RESULTS

Total area under the receiver operating characteristic curve was 0.84, and NNM was 80 at a sensitivity of 0.84 and a specificity of 0.64. At this point, 7,689 of 10,000 exams had sufficient image quality, 4,648 of 7,689 (60%) were true negatives, 59 of 7,689 (0.8%) were false negatives, 319 of 7,689 (4%) were true positives, and 2,581 of 7,689 (33%) were false positives. Twenty-seven percent of false negatives contained large hemorrhages and/or neovascularizations.

CONCLUSIONS

Automated detection of diabetic retinopathy using published algorithms cannot yet be recommended for clinical practice. However, performance is such that evaluation on validated, publicly available datasets should be pursued. If algorithms can be improved, such a system may in the future lead to improved prevention of blindness and vision loss in patients with diabetes.

Improvement of automated detection method of hemorrhages in fundus images

This paper describes an improved method for detecting hemorrhages in fundus images. The detection of hemorrhages is one of the important factors in the early diagnosis of diabetic retinopathy. So, we had suggested several methods for detecting abnormalities in fundus images, but our methods had some problems. We propose a new method for preprocessing and false positive elimination in the present study. The brightness of the fundus image was changed by the nonlinear curve with brightness values of the hue saturation value (HSV) space. In order to emphasize brown regions, gamma correction was performed on each red, green, and blue-bit image. Subsequently, the histograms of each red, blue, and blue-bit image were extended. After that, the hemorrhage candidates were detected using density analysis. Finally, false positives were removed by using rule-based method and 3 Mahalanobis distance classifiers with a 45-feature analysis. To evaluate the new method for the detection of hemorrhages, we examined 125 fundus images, including 35 images with hemorrhages and 90 normal images. The sensitivity and specificity for the detection of abnormal cases were 80% and 80%, respectively.

Automatic detection of red lesions in retinal images using a multilayer perceptron neural network

Diabetic Retinopathy (DR) is an important cause of visual impairment among people of working age in industrialized countries. Automatic detection of DR clinical signs in retinal images would be an important contribution to the diagnosis and screening of the disease. The aim of the present study is to automatically detect some of these clinical signs: red lesions (RLs), like hemorrhages (HEs) and microaneurysms (MAs). Based on their properties, we extracted a set of features from image regions and selected the subset which best discriminated between these RLs and the retinal background. A multilayer perceptron (MLP) classifier was subsequently used to obtain the final segmentation of RLs. Our database was composed of 100 images with variable color, brightness, and quality. 50 of them were used to obtain the examples to train the MLP classifier. The remaining 50 images were used to test the performance of the method. Using a lesion based criterion, we reached a mean sensitivity of 86.1% and a mean positive predictive value of 71.4%. With an image-based criterion, we achieved a 100% mean sensitivity, 60.0% mean specificity and 80.0% mean accuracy.

Cost-effectiveness of implementing automated grading within the national screening programme for diabetic retinopathy in Scotland

AIMS

National screening programmes for diabetic retinopathy using digital photography and multi-level manual grading systems are currently being implemented in the UK. Here, we assess the cost-effectiveness of replacing first level manual grading in the National Screening Programme in Scotland with an automated system developed to assess image quality and detect the presence of any retinopathy.

METHODS

A decision tree model was developed and populated using sensitivity/specificity and cost data based on a study of 6722 patients in the Grampian region. Costs to the NHS, and the number of appropriate screening outcomes and true referable cases detected in 1 year were assessed.

RESULTS

For the diabetic population of Scotland (approximately 160,000), with prevalence of referable retinopathy at 4% (6400 true cases), the automated strategy would be expected to identify 5560 cases (86.9%) and the manual strategy 5610 cases (87.7%). However, the automated system led to savings in grading and quality assurance costs to the NHS of 201,600 pounds per year. The additional cost per additional referable case detected (manual vs automated) totalled 4088 pounds and the additional cost per additional appropriate screening outcome (manual vs automated) was 1990 pounds.

CONCLUSIONS

Given that automated grading is less costly and of similar effectiveness, it is likely to be considered a cost-effective alternative to manual grading.

Retinal blood vessel segmentation using line operators and support vector classification

In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. A line detector, previously used in mammography, is applied to the green channel of the retinal image. It is based on the evaluation of the average grey level along lines of fixed length passing through the target pixel at different orientations. Two segmentation methods are considered. The first uses the basic line detector whose response is thresholded to obtain unsupervised pixel classification. As a further development, we employ two orthogonal line detectors along with the grey level of the target pixel to construct a feature vector for supervised classification using a support vector machine. The effectiveness of both methods is demonstrated through receiver operating characteristic analysis on two publicly available databases of color fundus images.

Automatic detection of microaneurysms in color fundus images

This paper addresses the automatic detection of microaneurysms in color fundus images, which plays a key role in computer assisted diagnosis of diabetic retinopathy, a serious and frequent eye disease. The algorithm can be divided into four steps. The first step consists in image enhancement, shade correction and image normalization of the green channel. The second step aims at detecting candidates, i.e. all patterns possibly corresponding to MA, which is achieved by diameter closing and an automatic threshold scheme. Then, features are extracted, which are used in the last step to automatically classify candidates into real MA and other objects; the classification relies on kernel density estimation with variable bandwidth. A database of 21 annotated images has been used to train the algorithm. The algorithm was compared to manually obtained gradings of 94 images; sensitivity was 88.5% at an average number of 2.13 false positives per image.

The efficacy of automated "disease/no disease" grading for diabetic retinopathy in a systematic screening programme

AIM

To assess the efficacy of automated "disease/no disease" grading for diabetic retinopathy within a systematic screening programme.

METHODS

Anonymised images were obtained from consecutive patients attending a regional primary care based diabetic retinopathy screening programme. A training set of 1067 images was used to develop automated grading algorithms. The final software was tested using a separate set of 14 406 images from 6722 patients. The sensitivity and specificity of manual and automated systems operating as "disease/no disease" graders (detecting poor quality images and any diabetic retinopathy) were determined relative to a clinical reference standard.

RESULTS

The reference standard classified 8.2% of the patients as having ungradeable images (technical failures) and 62.5% as having no retinopathy. Detection of technical failures or any retinopathy was achieved by manual grading with 86.5% sensitivity (95% confidence interval 85.1 to 87.8) and 95.3% specificity (94.6 to 95.9) and by automated grading with 90.5% sensitivity (89.3 to 91.6) and 67.4% specificity (66.0 to 68.8). Manual and automated grading detected 99.1% and 97.9%, respectively, of patients with referable or observable retinopathy/maculopathy. Manual and automated grading detected 95.7% and 99.8%, respectively, of technical failures.

CONCLUSION

Automated "disease/no disease" grading of diabetic retinopathy could safely reduce the burden of grading in diabetic retinopathy screening programmes.

Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features

PURPOSE

To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression.

METHODS

Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard.

RESULTS

The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58).

CONCLUSIONS

The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis

PURPOSE

To describe and evaluate a machine learning-based, automated system to detect exudates and cotton-wool spots in digital color fundus photographs and differentiate them from drusen, for early diagnosis of diabetic retinopathy.

METHODS

Three hundred retinal images from one eye of 300 patients with diabetes were selected from a diabetic retinopathy telediagnosis database (nonmydriatic camera, two-field photography): 100 with previously diagnosed bright lesions and 200 without. A machine learning computer program was developed that can identify and differentiate among drusen, (hard) exudates, and cotton-wool spots. A human expert standard for the 300 images was obtained by consensus annotation by two retinal specialists. Sensitivities and specificities of the annotations on the 300 images by the automated system and a third retinal specialist were determined.

RESULTS

The system achieved an area under the receiver operating characteristic (ROC) curve of 0.95 and sensitivity/specificity pairs of 0.95/0.88 for the detection of bright lesions of any type, and 0.95/0.86, 0.70/0.93, and 0.77/0.88 for the detection of exudates, cotton-wool spots, and drusen, respectively. The third retinal specialist achieved pairs of 0.95/0.74 for bright lesions and 0.90/0.98, 0.87/0.98, and 0.92/0.79 per lesion type.

CONCLUSIONS

A machine learning-based, automated system capable of detecting exudates and cotton-wool spots and differentiating them from drusen in color images obtained in community based diabetic patients has been developed and approaches the performance level of retinal experts. If the machine learning can be improved with additional training data sets, it may be useful for detecting clinically important bright lesions, enhancing early diagnosis, and reducing visual loss in patients with diabetes.

Analysis of retinal vasculature using a multiresolution Hermite model

This paper presents a vascular representation and segmentation algorithm based on a multiresolution Hermite model (MHM). A two-dimensional Hermite function intensity model is developed which models blood vessel profiles in a quad-tree structure over a range of spatial resolutions. The use of a multiresolution representation simplifies the image modeling and allows for a robust analysis by combining information across scales. Estimation over scale also reduces the overall computational complexity. As well as using MHM for vessel labelling, the local image modeling can accurately represent vessel directions, widths, amplitudes, and branch points which readily enable the global topology to be inferred. An expectation-maximization (EM) type of optimization scheme is used to estimate local model parameters and an information theoretic test is then applied to select the most appropriate scale/feature model for each region of the image. In the final stage, Bayesian stochastic inference is employed for linking the local features to obtain a description of the global vascular structure. After a detailed description and analysis of MHM, experimental results on two standard retinal databases are given that demonstrate its comparative performance. These show MHM to perform comparably with other retinal vessel labelling methods.

Automated microaneurysm detection using local contrast normalization and local vessel detection

Screening programs using retinal photography for the detection of diabetic eye disease are being introduced in the UK and elsewhere. Automatic grading of the images is being considered by health boards so that the human grading task is reduced. Microaneurysms (MAs) are the earliest sign of this disease and so are very important for classifying whether images show signs of retinopathy. This paper describes automatic methods for MA detection and shows how image contrast normalization can improve the ability to distinguish between MAs and other dots that occur on the retina. Various methods for contrast normalization are compared. Best results were obtained with a method that uses the watershed transform to derive a region that contains no vessels or other lesions. Dots within vessels are handled successfully using a local vessel detection technique. Results are presented for detection of individual MAs and for detection of images containing MAs. Images containing MAs are detected with sensitivity 85.4% and specificity 83.1%.

Web-based screening for diabetic retinopathy in a primary care population: the EyeCheck project

The objective of this study was to evaluate the feasibility of ATA category 2 Web-based screening for diabetic retinopathy in a primary care population in the Netherlands. A total of 1,676 patients in a primary care setting, with diabetes, without known diabetic retinopathy, and without previous screening by an ophthalmologist, were included between January 1 and December 31, 2003. Patients underwent a brief questionnaire and two field retinal photography. Photographs were independently read by two ophthalmologists. Outcome measures were gradability of the photographs, need for pharmacologic pupil dilation, assessment as suspect for presence of diabetic retinopathy, of neovascularization and of diabetic retinopathy, and agreement between graders. Of the population studied, 11.3% of patients required pupil dilation, average transmission time of images was 73 sec, 12.0% of patients had ungradable photographs, 10.4% of the patients with gradable photographs were assessed as "suspect for diabetic retinopathy," and 2.0% were assessed to need urgent referral. Red lesions were present in 3.5% and bright lesions were present in 1.6% of all gradable patients. Neovascularization of the disk was found in one patient. Type 1 patients had much higher rates of "suspect for diabetic retinopathy" (34.5%) than type 2 patients (9.4%). Interrater agreement kappa was 0.93. Web-based screening, using open source technology and uncompressed images, is feasible in a primary care setting, with a high rate of inter-rater agreement. Dilate-as-needed may be a sensible approach for retinal photography. The high incidence of "suspect for diabetic retinopathy" in type 1 diabetes patients illustrates that web-based diabetic retinopathy screening programs for these patients may detect diabetic retinopathy that would otherwise have gone undetected.