Measurement of Retinal Vessel Widths From Fundus Images Based on 2-D Modeling
IEEE Transactions on Medical ImagingPublished 1 October 2004
J. Lowell, Andrew Hunter, David Steel, Ansu Basu, Robert E. J. Ryder, R.L. Kennedy
Citations255
SJR quartileQ1
SJR score2.63
SNIP3.00
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An algorithm to measure the vessel diameter to subpixel accuracy is presented, based on a two-dimensional difference of Gaussian model, which is optimized to fit aTwo-dimensional intensity vessel segment.
Abstract
Changes in retinal vessel diameter are an important sign of diseases such as hypertension, arteriosclerosis and diabetes mellitus. Obtaining precise measurements of vascular widths is a critical and demanding process in automated retinal image analysis as the typical vessel is only a few pixels wide. This paper presents an algorithm to measure the vessel diameter to subpixel accuracy. The diameter measurement is based on a two-dimensional difference of Gaussian model, which is optimized to fit a two-dimensional intensity vessel segment. The performance of the method is evaluated against Brinchmann-Hansen's half height, Gregson's rectangular profile and Zhou's Gaussian model. Results from 100 sample profiles show that the presented algorithm is over 30% more precise than the compared techniques and is accurate to a third of a pixel.
Keywords
Computer ScienceMedicine
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Neural Networks for Pattern Recognition
12,198 Citations1995Chris Bishop
IEEE Transactions on Pattern Analysis and Machine IntelligenceLearning patterns of activity using real-time tracking
3,235 Citations2000Chris Stauffer, W. Eric L. Grimson
This paper focuses on motion tracking and shows how one can use observed motion to learn patterns of activity in a site and create a hierarchical binary-tree classification of the representations within a sequence.
IEEE Transactions on Medical ImagingLocating blood vessels in retinal images by piecewise threshold probing of a matched filter response
2,577 Citations2000A.D. Hoover, Valentina L. Kouznetsova +1 more
An automated method to locate and outline blood vessels in images of the ocular fundus that uses local and global vessel features cooperatively to segment the vessel network is described.
IEEE Transactions on Medical ImagingDetection of blood vessels in retinal images using two-dimensional matched filters
1,673 Citations1989Subhasis Chaudhuri, S. Chatterjee +3 more
The concept of matched filter detection of signals is used to detect piecewise linear segments of blood vessels in these images and the results are compared to those obtained with other methods.
OphthalmologyFundus Photographic Risk Factors for Progression of Diabetic Retinopathy
801 Citations1991
Severity of intraretinal microvascular abnormalities, hemorrhages and/or microaneurysms, and venous beading were found to be the most important factors in predicting progression to proliferative retinopathy.
The LancetRetinal microvascular abnormalities and incident stroke: the Atherosclerosis Risk in Communities Study
760 Citations2001Tien Yin Wong, Ronald Klein +6 more
Most retinal microvascular characteristics were predictive of incident stroke, and the associations were similar for ischaemic strokes specifically, and for strokes in individuals with hypertension, either with or without diabetes.
Survey of OphthalmologyRetinal Microvascular Abnormalities and their Relationship with Hypertension, Cardiovascular Disease, and Mortality
614 Citations2001Tien Yin Wong, Ronald Klein +4 more
There is no convincing evidence of an independent or direct association with atherosclerosis, ischemic heart disease, or cardiovascular mortality, but when reliably quantified, retinal microvascular abnormalities may be useful as risk indicators for cerebrovascular diseases.
IEEE Transactions on Pattern Analysis and Machine IntelligenceEvent detection and analysis from video streams
402 Citations2001Gérard Medioni, I. Cohen +3 more
A system which takes as input a video stream obtained from an airborne moving platform and produces an analysis of the behavior of the moving objects in the scene and relies on two modular blocks to achieve this functionality.
IEEE Transactions on Pattern Analysis and Machine IntelligenceProbabilistic data association methods for tracking complex visual objects
376 Citations2001Christopher Rasmussen, G Hager
A randomized tracking algorithm adapted from an existing probabilistic data association filter (PDAF) that is resistant to clutter and follows agile motion is introduced and a related technique that allows mixed tracker modalities and handles object overlaps robustly is derived.
American Journal of EpidemiologyRetinal Arteriolar Diameters and Elevated Blood Pressure: The Atherosclerosis Risk in Communities Study
353 Citations1999A. Richey Sharrett, Larry D. Hubbard +6 more
The patterns of association suggested that these signs reflect both transient and persisting structural effects of elevated blood pressure, in agreement with the scant pathologic literature available.
IEEE Transactions on Biomedical EngineeringDetection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter
295 Citations2002L. Gang, O. Chutatape +1 more
The experiment shows that the inclusion of the width measurement in the detection process can improve the performance of matched filter and result in a significant increase in success rate of detection.
IEEE Transactions on Medical ImagingThe detection and quantification of retinopathy using digital angiograms
289 Citations1994Liang Yan, Mark S. Rzeszotarski +2 more
An algorithm is presented for the analysis and quantification of the vascular structures of the human retina that relies on a matched filtering approach coupled with a priori knowledge about retinal vessel properties to automatically detect the vessel boundaries, track the midline of the vessel, and extract useful parameters of clinical interest.
Pattern RecognitionA computer method of understanding ocular fundus images
186 Citations1982Koichiro Akita, Hideki Kuga
A computer method is proposed for the extraction of blood vessels from the retinal background; the recognition of arteries and veins; the detection and analysis of peculiar regions such as hemorrhages, exudates, optic discs and arterio-venous crossings.
Application of the self-organising map to trajectory classification
141 Citations2002JD Owens, Andrew Hunter
It is shown that analysis of trajectories may be carried out in a model-free fashion, using self-organising feature map neutral networks to learn the characteristics of normal trajectories, and to detect novel ones.
British Journal of OphthalmologyComputer algorithms for the automated measurement of retinal arteriolar diameters
123 Citations2001N Chapman
Of the three automated methods compared, the SLRF method was the most consistent and the most repeatable in measurements of retinal arteriolar diameter and the Gaussian method less so.
IEEE Transactions on Circuits and Systems for Video TechnologyA real-time system for video surveillance of unattended outdoor environments
122 Citations1998Gian Luca Foresti
A visual surveillance system for remote monitoring of unattended outdoor environments that is able to detect, localize, track, and classify multiple objects moving in a surveilled area based on a statistical morphological operator, the statistical pecstrum.
Clinical SciencePeripheral vascular disease is associated with abnormal arteriolar diameter relationships at bifurcations in the human retina
88 Citations2002Neil Chapman, Giacomo Dell’Omo +5 more
In healthy men, retinal arterial diameters at bifurcations conformed to predicted optimal values but in men with peripheral vascular disease, junction exponents deviated significantly from the optimum, suggesting a generalized abnormality of endothelial function in atherosclerosis.
CentAUR (University of Reading)An integrated traffic and pedestrian model-based vision system
88 Citations1997Paolo Remagnino, Adam Baumberg +5 more
A novel integrated vision system in which two autonomous visual modules are combined to interpret a dynamic scene and a novel method for handling occlusion between objects within the context of this hybrid tracking system is described.
Computers and Biomedical ResearchAutomated Grading of Venous Beading
81 Citations1995Peter H. Gregson, Zixu Shen +2 more
An algorithm for automated grading of venous beading in digitized ocular fundus images is described and is compared to the currently accepted clinical practice of manual grading in a pilot clinical study of 51 subjects.
IEEE Transactions on Medical ImagingSemi-automatic segmentation of vascular network images using a rotating structuring element (ROSE) with mathematical morphology and dual feature thresholding
78 Citations1993Brett D. Thackray, Alan C. Nelson
It is shown that a combination of the mathematical morphology operation, opening, with a linear rotating structuring element (ROSE) and dual feature thresholding can semi-automatically segment categories of vessels in a vascular network.
Computer Methods and Programs in BiomedicineQuantification and characterisation of arteries in retinal images
73 Citations2000Xiaohong Gao, Anil A. Bharath +4 more
In general an acceptable degree of accuracy and precision was seen for all measurements, although the system had difficulty dealing with very noisy images and small or especially tortuous blood vessels.
Multimedia Video-Based Surveillance Systems: Requirements, Issues and Solutions
64 Citations2000Gian Luca Foresti, Petri Mähönen +1 more
Pattern Recognition LettersQuantitative measurement of changes in retinal vessel diameter in ocular fundus images
63 Citations2000L. Pedersen, Michael Grunkin +5 more
The aim of this work is to develop methods to provide quantitative information about the FAN status of retinal arteriolar vessel segments using a ‘‘normalised accumulated gradient’’ (NAG) and the coeAcient of variance (CV) to estimate the F AN in a vessel segment.
British Journal of OphthalmologyAccurate vessel width measurement from fundus photographs: a new concept.
61 Citations1994Sal Rassam, Vinod Patel +3 more
The kick point method may provide the most accurate measurement of vessel width possible from these profiles, and the characteristics of the kick points and their practicality have been discussed.
Acta OphthalmologicaTheoretical relations between light streak characteristics and optical properties of retinal vessels
58 Citations1986O Brinchmann-Hansen, Halvor Heier
It is shown that variations in thickness of the wall or changes in its refractive index do not influence the final image of the width of the central light reflex, however, the intensity is affected by density changes in overlying structures.
Acta OphthalmologicaMicrophotometry of the blood column and the light streak on retinal vessels in fundus photographs
54 Citations1986O Brinchmann-Hansen, O. Engvold
A scanning microdensitometric technique to be applied directly on negatives of fundus photographs is presented, and preliminary results of various light streak parameters are discussed and related to previous ophthalmoscopic observations.
Comparison of background extraction based intrusion detection algorithms
45 Citations2002Aleksej Makarov
The overall performance of the presented motion detection algorithms is shown to depend on the type of the pelwise temporal filter, and on the image features applied to it.
PubMedSigns in the fundus oculi and arterial hypertension: unconventional assessment and significance.
38 Citations1967Aubrey Kagan, Elizabeth Aurell +1 more
Unconventional ways of assessing diminution of vascularity in a population sample of men aged 50 and also in a group of hospital patients are described, showing that a method simple enough to be learnt by a schoolboy in 20 minutes gives information that is more precise and less biased than data obtained by more conventional means.
Robotics and Autonomous SystemsVisual surveillance using deformable models of vehicles
17 Citations1997James Ferryman, A. D. Worrall +2 more
A new pose refinement technique using “active” models is described, able to recover both the pose of a rigid object, and the structure of a deformable model; an assessment of its performance is examined in comparison with previously reported “passive” model-based techniques in the context of traffic surveillance.
Measurement and ControlImage Processing System for Pedestrian Monitoring Using Neural Classification of Normal Motion Patterns
14 Citations1999B. Boghossian, Sergio A. Velastín
Motion is adopted as the main cue for abnormal incident detection and the neural network model is described, the run-time techniques employed to detect the abnormal agents, a typical example of implementation, and results and conclusions are presented.
Image and Vision ComputingA statistically-based Newton method for pose refinement
14 Citations1998Arthur E.C. Pece, A. D. Worrall
By projecting this gradient of the ‘line energy’ onto parameter space, Newton's method can be applied to recovering the pose parameters of 3D models that minimize the probability of an accidental match between instantiated model and image.
Acta OphthalmologicaThe apparent and true width of the blood column in retinal vessels
13 Citations1986O Brinchmann-Hansen, Halvor Heier
Numerical experiments show that variations in the index of refraction and in the thickness of the vessel wall have negligible influence on the apparent width of the blood column, which might implicate that an early differentiation between vessel constriction caused by increased tonus of systemic‐hypertension versus irreversible arteriosclerosis is probably not within physical and optical reach, using ophthalmoscopy.
Lecture notes in computer scienceNovelty Detection in Video Surveillance Using Hierarchical Neural Networks
13 Citations2002JD Owens, Andrew Hunter +1 more
A hierarchical self-organising neural network is described for the detection of unusual pedestrian behaviour in video-based surveillance systems, trained on a normal data set, with no prior information about the scene under surveillance, thereby requiring minimal user input.
Real-Time ImagingReal-Time Vision-based Detection of Waiting Pedestrians
11 Citations1997Nasser Kehtarnavaz, Farida Rajkotwala
A real-time digital signal processing system to detect the presence of pedestrians waiting to cross an intersection using a Texas Instruments TMS320C40 digital signal processor chip and results obtained indicate that this DSP implementation provides an acceptable detection rate for this traffic management problem.
Learning and Classification of Suspicious Events for Advanced Visual-Based Surveillance
11 Citations2000Gian Luca Foresti, Fabio Roli
The main goal of an AVS system is to generate automatically focus-of-attention messages in order to help the human operator to concentrate his decision capabilities on possible danger situations.