Jan Odstrcilik

Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database

Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

Automatic no-reference quality assessment for retinal fundus images using vessel segmentation

Fundus imaging is the most commonly used modality to collect information about the human eye background. Objective and quantitative assessment of quality for the acquired images is essential for manual, computer-aided and fully automatic diagnosis. In this paper, we present a no-reference quality metric to quantify image noise and blur and its application to fundus image quality assessment. The proposed metric takes the vessel tree visible on the retina as guidance to determine an image quality score. In our experiments, the performance of this approach is demonstrated by correlation analysis with the established full-reference metrics peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM). We found a Spearman rank correlation for PSNR and SSIM of 0.89 and 0.91. For real data, our metric correlates reasonable to a human observer, indicating high agreement to human visual perception.

Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration

An automatic method of segmenting the retinal vessel tree and estimating status of retinal neural fibre layer (NFL) from high resolution fundus camera images is presented. First, reliable blood vessel segmentation, using 2D directional matched filtering, enables to remove areas occluded by blood vessels thus leaving remaining retinal area available to the following NFL detection. The local existence of rather faint and hardly visible NFL is detected by combining several newly designed local textural features, sensitive to subtle NFL characteristics, into feature vectors submitted to a trained neural-network classifier. Obtained binary retinal maps of NFL distribution show a good agreement with both medical expert evaluations and quantitative results obtained by optical coherence tomography.

Improvement of Vessel Segmentation by Matched Filtering in Colour Retinal Images

A method for segmentation of vessel structure in colour retinal fundus images is presented, based on 2D matched filtering correlating the local image areas with 2D masks obtained via averaging of brightness profiles of vessels for several different vessel widths.Each of the basic masks is rotated in twelve different directions; this way, 60 masks for 5 different widths, each with 12 orientations are produced and used as 2D convolution kernels of the matched filters. The maximum response of all the filter responses for a concrete local area thus carries - if there is a vessel present - the information both on the width and orientation of the vessel segment. Compared to the previously published results [6], the segmentation has been improved primarily in two directions: the width resolution has been increased from 3 to 5 classes with a better approximation of the brightness profiles, and the orientation information is now utilized to provide vessel direction maps that are further used in the following phase of complementing the missing vessel segments. The parametric maps representing the maximum responses of the filters are then combined and finally tresholded thus obtaining binary vessel maps to be morphologically cleaned in order to remove the artefacts due to noise and also to complement the obviously missing parts of vessels. The method was designed and tested using the high-resolution fundus camera images provided by a cooperating ophthalmological clinic, and also statistically tested based on the standard public image database DRIVE.

Hybrid retinal image registration using phase correlation

Abstract This paper deals with registration of retinal images, which were taken by high-resolution digital colour fundus cameras. The proposed method describes successful application of phase correlation method. It combines several basic steps — global correction of shift, rotation and scaling, detection of landmarks, their correspondences and finally image registration using second-order polynomial model. The method is tested on two sets of images. The first set contains images from the diabetic patients where many retinal pathologies can disturb the registration process. The second set contains images from healthy subjects, which were acquired by different illumination conditions. The method was evaluated using four different criteria - tree objective and one subjective. These criteria are also compared. The achieved registration accuracy of the landmarks position error is 1·13 and 0·93 pixels for respective image sets. Finally, the simple scheme for retinal pathology visualisation of registered fundus pairs is presented.

Analysis of Visual Appearance of Retinal Nerve Fibers in High Resolution Fundus Images: A Study on Normal Subjects

The retinal ganglion axons are an important part of the visual system, which can be directly observed by fundus camera. The layer they form together inside the retina is the retinal nerve fiber layer (RNFL). This paper describes results of a texture RNFL analysis in color fundus photographs and compares these results with quantitative measurement of RNFL thickness obtained from optical coherence tomography on normal subjects. It is shown that local mean value, standard deviation, and Shannon entropy extracted from the green and blue channel of fundus images are correlated with corresponding RNFL thickness. The linear correlation coefficients achieved values 0.694, 0.547, and 0.512 for respective features measured on 439 retinal positions in the peripapillary area from 23 eyes of 15 different normal subjects.

Non-mydriatic video ophthalmoscope to measure fast temporal changes of the human retina

The analysis of fast temporal changes of the human retina can be used to get insight to normal physiological behavior and to detect pathological deviations. This can be important for the early detection of glaucoma and other eye diseases. We developed a small, lightweight, USB powered video ophthalmoscope that allows taking video sequences of the human retina with at least 25 frames per second without dilating the pupil. Short sequences (about 10 s) of the optic nerve head (20° x 15°) are recorded from subjects and registered offline using two-stage process (phase correlation and Lucas-Kanade approach) to compensate for eye movements. From registered video sequences, different parameters can be calculated. Two applications are described here: measurement of (i) cardiac cycle induced pulsatile reflection changes and (ii) eye movements and fixation pattern. Cardiac cycle induced pulsatile reflection changes are caused by changing blood volume in the retina. Waveform and pulse parameters like amplitude and rise time can be measured in any selected areas within the retinal image. Fixation pattern ΔY(ΔX) can be assessed from eye movements during video acquisition. The eye movements ΔX[t], ΔY[t] are derived from image registration results with high temporal (40 ms) and spatial (1,86 arcmin) resolution. Parameters of pulsatile reflection changes and fixation pattern can be affected in beginning glaucoma and the method described here may support early detection of glaucoma and other eye disease.

Registration of Image Sequences from Experimental Low-Cost Fundus Camera

This paper describes new registration approach for registration of low SNR retinal image sequences. We combine two approaches - Fourier-based method for large shift correction and Lucas-Kanade tracking for small shift and rotation correction. We also propose method for evaluation of registration results, which uses spatial variation of minimum value in intensity profiles through blood-vessels. We achieved precision of registration below 2.1 pixels, which is acceptable with regards to image SNR (around 10dB). The final averaging of registered sequence leads to improvement of image quality and improvement in SNR over 10 dB.

The effect of Benzothiazolone-2 on the expression of Metallothionein-3 in modulating Alzheimer's disease

Metallothioneins (MTs) are a class of ubiquitously occurring low‐molecular‐weight cysteine‐ and metal‐rich proteins containing sulfur‐based metal clusters. MT‐3 exhibits neuro‐inhibitory activity. The possibility to enhance the expression of MT‐3 or protect it from degradation is an attractive therapeutic target, because low levels of MT‐3 were found in brains of Alzheimers disease (AD) patients.

Retinal image registration for eye movement estimation

This paper describes a novel methodology for eye fixation measurement using a unique videoophthalmoscope setup and advanced image registration approach. The representation of the eye movements via Poincare plot is also introduced. The properties, limitations and perspective of this methodology are finally discussed.