Koen A. Vermeer

A model based method for retinal blood vessel detection

Retinal blood vessels are important structures in ophthalmological images. Many detection methods are available, but the results are not always satisfactory. In this paper, we present a novel model based method for blood vessel detection in retinal images. It is based on a Laplace and thresholding segmentation step, followed by a classification step to improve performance. The last step assures incorporation of the inner part of large vessels with specular reflection. The method gives a sensitivity of 92% with a specificity of 91%. The method can be optimized for the specific properties of the blood vessels in the image and it allows for detection of vessels that appear to be split due to specular reflection.

Detecting glaucomatous wedge shaped defects in polarimetric images

Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images.

Automated detection of wedge-shaped defects in polarimetric images of the retinal nerve fibre layer

PurposeAutomated glaucoma detection in images obtained by scanning laser polarimetry is currently insensitive to local abnormalities, impairing its performance. The purpose of this investigation was to test and validate a recently proposed algorithm for detecting wedge-shaped defects.MethodsIn all, 31 eyes of healthy subjects and 37 eyes of glaucoma patients were imaged with a GDx. Each image was classified by two experts in one of four classes, depending on how clear any wedge could be identified. The detection algorithm itself aimed at detecting and combining the edges of the wedge. The performance of both the experts and the algorithm were evaluated.ResultsThe interobserver correlation, expressed as ICC(3,1), was 0.77. For the clearest cases, the algorithm yielded a sensitivity of 80% at a specificity of 93%, with an area under the ROC of 0.95. Including less obvious cases by the experts resulted in a sensitivity of 55% at a specificity of 95%, with an area under the ROC of 0.89.ConclusionsIt is possible to automatically detect many wedge-shaped defects at a fairly low rate of false-positives. Any detected wedge defect is presented in a user-friendly way, which may assist the clinician in making a diagnosis.

The effect of cataract on eye movement perimetry

Purpose. To determine how different grades of cataract affect sensitivity threshold and saccadic reaction time (SRT) in eye movement perimetry (EMP). Methods. In EMP, the visual field is tested by assessing the saccades that a subject makes towards peripheral stimuli using an eye tracker. Forty-eight cataract patients underwent pre- and postoperative EMP examination in both eyes. The subjects had to fix a central stimulus presented on the eye tracker monitor and to look at any detected peripheral stimulus upon its appearance. A multilevel mixed model was used to determine the factors that affected the sensitivity threshold and the SRT as a function of cataract grade. Results. We found no effect of cataract severity (LOCS III grades I through IV) on SRT and the sensitivity thresholds. In cataract of LOCS III grade V, however, we found an increase by 27% and 21% (p < 0.001), respectively, compared to the SRT and the sensitivity threshold in LOCS III grade I. Eyes that underwent cataract surgery showed no change in mean SRTs and sensitivity thresholds after surgery in LOCS III grade IV and lower. Conclusion. The present study shows that EMP can be readily used in patients with cataract with LOCS III grade IV and below.

Event-based progression detection strategies using scanning laser polarimetry images of the human retina

Monitoring glaucoma patients and ensuring optimal treatment requires accurate and precise detection of progression. Many glaucomatous progression detection strategies may be formulated for Scanning Laser Polarimetry (SLP) data of the local nerve fiber thickness. In this paper, several strategies, all based on repeated GDx VCC SLP measurements, are tested to identify the optimal one for clinical use. The parameters of the methods were adapted to yield a set specificity of 97.5% on real image series. For a fixed sensitivity of 90%, the minimally detectable loss was subsequently determined for both localized and diffuse loss. Due to the large size of the required data set, a previously described simulation method was used for assessing the minimally detectable loss. The optimal strategy was identified and was based on two baseline visits and two follow-up visits, requiring two-out-of-four positive tests. Its associated minimally detectable loss was 5-12 μm, depending on the reproducibility of the measurements.

Progression detection of glaucoma from polarimetric images

Detecting glaucoma progression is crucial for assessing the effectivity of the treatment. This paper describes three methods for detecting progression related changes in polarimetric images of the retinal nerve fiber layer (NFL), both on a global and on a local scale. Detecting global changes proved not to be feasible due to poor reproducibility of the measurements at the pixel level. Local progression on the other hand could be detected. A distribution based approach did not work, but locating specific areas with minimum size and minimum NFL decrease did give relevant results. The described algorithm yielded a TPR of 0.42 and an FPR of 0.095 on our datasets. It proved to be able to outline suspect areas that show NFL reduction.

Detecting Wedge Shaped Defects in Polarimetric Images of the Retinal Nerve Fiber Layer

Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry images of the retinal nerve fiber layer is unavailable; an automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and then combined into wedge shaped defects. The results of our method on a limited set of 45 images yields a sensitivity of 88% and a specificity of 92%. More importantly, it shows that it is possible to automatically extract local RNFL defects such as wedges.