WO2010030159A2 - A non invasive method for analysing the retina for ocular manifested diseases - Google Patents
A non invasive method for analysing the retina for ocular manifested diseases Download PDFInfo
- Publication number
- WO2010030159A2 WO2010030159A2 PCT/MY2009/000025 MY2009000025W WO2010030159A2 WO 2010030159 A2 WO2010030159 A2 WO 2010030159A2 MY 2009000025 W MY2009000025 W MY 2009000025W WO 2010030159 A2 WO2010030159 A2 WO 2010030159A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- retina
- analyzing
- ocular
- invasive method
- diseases
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 120
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims description 58
- 201000010099 disease Diseases 0.000 title claims description 57
- 210000001525 retina Anatomy 0.000 title claims description 50
- 206010012689 Diabetic retinopathy Diseases 0.000 claims description 73
- 206010012601 diabetes mellitus Diseases 0.000 claims description 36
- 208000035719 Maculopathy Diseases 0.000 claims description 29
- 208000002780 macular degeneration Diseases 0.000 claims description 29
- 230000002708 enhancing effect Effects 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 16
- 201000007914 proliferative diabetic retinopathy Diseases 0.000 claims description 16
- 210000001210 retinal vessel Anatomy 0.000 claims description 16
- 238000003745 diagnosis Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000002250 progressing effect Effects 0.000 claims description 9
- 238000012880 independent component analysis Methods 0.000 claims description 8
- 230000002792 vascular Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 201000007917 background diabetic retinopathy Diseases 0.000 claims description 5
- 206010020772 Hypertension Diseases 0.000 claims description 2
- 201000003772 severe nonproliferative diabetic retinopathy Diseases 0.000 claims description 2
- 230000007170 pathology Effects 0.000 description 25
- 230000004233 retinal vasculature Effects 0.000 description 15
- 206010025421 Macule Diseases 0.000 description 10
- 210000000416 exudates and transudate Anatomy 0.000 description 10
- 238000012216 screening Methods 0.000 description 10
- 238000011282 treatment Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 201000004569 Blindness Diseases 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- RTUHEKLMDKJAQG-UHFFFAOYSA-N 8-acetamido-n-(2-chlorophenyl)-n-methyl-4,5-dihydrothieno[3,2-d][1]benzoxepine-2-carboxamide Chemical compound C=1C=2CCOC3=CC(NC(C)=O)=CC=C3C=2SC=1C(=O)N(C)C1=CC=CC=C1Cl RTUHEKLMDKJAQG-UHFFFAOYSA-N 0.000 description 7
- 230000002207 retinal effect Effects 0.000 description 7
- 206010002329 Aneurysm Diseases 0.000 description 6
- 208000009857 Microaneurysm Diseases 0.000 description 6
- 206010030113 Oedema Diseases 0.000 description 6
- 208000037111 Retinal Hemorrhage Diseases 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 208000017442 Retinal disease Diseases 0.000 description 5
- 210000004204 blood vessel Anatomy 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 238000010191 image analysis Methods 0.000 description 5
- 230000003902 lesion Effects 0.000 description 5
- 230000004256 retinal image Effects 0.000 description 5
- 208000032843 Hemorrhage Diseases 0.000 description 4
- 206010038923 Retinopathy Diseases 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004268 retinal thickening Effects 0.000 description 4
- 230000004393 visual impairment Effects 0.000 description 4
- 208000001344 Macular Edema Diseases 0.000 description 3
- 206010038862 Retinal exudates Diseases 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000010412 perfusion Effects 0.000 description 3
- 239000000790 retinal pigment Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 210000005166 vasculature Anatomy 0.000 description 3
- 206010012688 Diabetic retinal oedema Diseases 0.000 description 2
- 206010025415 Macular oedema Diseases 0.000 description 2
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 description 2
- 201000010183 Papilledema Diseases 0.000 description 2
- 206010038886 Retinal oedema Diseases 0.000 description 2
- 206010053648 Vascular occlusion Diseases 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 201000011190 diabetic macular edema Diseases 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000302 ischemic effect Effects 0.000 description 2
- 150000002632 lipids Chemical class 0.000 description 2
- 201000010230 macular retinal edema Diseases 0.000 description 2
- 230000006740 morphological transformation Effects 0.000 description 2
- 238000002577 ophthalmoscopy Methods 0.000 description 2
- 239000000049 pigment Substances 0.000 description 2
- 230000002062 proliferating effect Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 201000011195 retinal edema Diseases 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 210000003462 vein Anatomy 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000032544 Cicatrix Diseases 0.000 description 1
- 206010058202 Cystoid macular oedema Diseases 0.000 description 1
- 208000002249 Diabetes Complications Diseases 0.000 description 1
- 206010029113 Neovascularisation Diseases 0.000 description 1
- 206010047513 Vision blurred Diseases 0.000 description 1
- 208000034698 Vitreous haemorrhage Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 235000019646 color tone Nutrition 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 201000010206 cystoid macular edema Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000004452 decreased vision Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000004313 glare Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000001435 haemodynamic effect Effects 0.000 description 1
- 238000002430 laser surgery Methods 0.000 description 1
- 208000018769 loss of vision Diseases 0.000 description 1
- 231100000864 loss of vision Toxicity 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000004088 microvessel Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 230000004286 retinal pathology Effects 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037390 scarring Effects 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 208000021331 vascular occlusion disease Diseases 0.000 description 1
- 230000003074 vasoproliferative effect Effects 0.000 description 1
- 230000004304 visual acuity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/14—Arrangements specially adapted for eye photography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/94—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Definitions
- the present invention relates generally to a method of analyzing the retina for ocular manifested diseases by ascertaining the area of foveal avascular zone of the retina.
- Diabetic retinopathy can be classified into 3 main forms; background (non-proliferative) diabetic retinopathy (hereinafter referred to as "NPDR”), pre-proliferative diabetic retinopathy (hereinafter referred to as "PPDR”) and maculopathy and proliferative diabetic retinopathy (hereinafter referred to as "PDR”) based on the presence of pathologies.
- NPDR non-proliferative diabetic retinopathy
- PPDR pre-proliferative diabetic retinopathy
- PDR maculopathy and proliferative diabetic retinopathy
- NPDR is a form of Diabetic Retinopathy caused by micro- vascular leakage away from the macula.
- the occurrence of NPDR is indicated by the presence of sacculations from the capillary walls (microaneurysms), blood (retinal haemorrhages), lipid exudates (hard exudates) and retinal edema.
- microaneurysms sacculations from the capillary walls
- blood retinal haemorrhages
- lipid exudates hard exudates
- retinal edema The rupture of these microaneurysms results in haemorrhages.
- there are often no obvious warning signs and patients suffering from the disease are unaware until it has advanced into more severe levels. Treatment of the disease at this stage may prevent future complications and towards blindness.
- NPDR Moderate to severe NPDR is also known as PPDR where lesion features namely cotton wool spots, venous beading and intra-retinal micro-vascular abnormalities (IRMA) can be found. These changes are found in areas of retinal capillary non-perfusion and indicate the severity of the non-proliferative changes.
- EDRS Early Treatment Diabetic Retinopathy Study
- PDR proliferative diabetic retinopathy
- Diabetic Maculopathy can be in both background and proliferative diabetic retinopathy and is a leading cause of legal blindness in diabetics.
- macular edema is commonly the cause of decreased vision.
- Diabetic Maculopathy can be classified into focal, diffuse, ischaemic and mixed types.
- Focal maculopathy characterized by microaneurysms, haemorrhages, macular edema and hard exudates are usually arranged in a circular pattern.
- Diffuse maculopathy caused by leakage from the retinal capillaries results in diffuse edema. This may also result in cystoid macular edema.
- Ischaemic maculopathy is diagnosed when there is disruption of foveal capillaries resulting in enlargement of foveal avascular zone (hereinafter referred to as "FAZ").
- Diabetic Retinopathy is a common complication of diabetes mellitus and is the leading cause of blindness in the working-age population. It is a silent disease and the patient realises this only when the changes in the retina have progressed to a level where treatment is complicated and nearly impossible.
- Diabetic Retinopathy has increased with increase of life expectancy of diabetics. Roughly, about 50 percent of diabetic patients develop Diabetic Retinopathy after 10 years, 70 percent after 20 years and 90 percent after 30 years of onset of the diabetes. As the disease progresses, clinically evident retinopathy (pathology) appears namely microanerysms, dot and blot haemorrhages, cotton wool spots, venous caliber changes and retinal capillary non-perfusion. However, changes at haemodynamic (physical aspects of the blood circulation) and cellular levels already take place even when there is no clinically detectable retinopathy.
- Diabetic Retinopathy It is believed that visual loss occurring from Diabetic Retinopathy can be prevented by a periodic follow-up that is very important for a timely intervention to reduce the risk of blindness in diabetic patients.
- Diabetic patients with no Diabetic Retinopathy or mild Diabetic Retinopathy should have their eyes checked by an ophthalmologist at least once a year. Proper screening for retinopathy followed by laser surgery treatment can significantly reduce the incidence of blindness. Screening in Diabetic Retinopathy is a non-diagnostic test or identification of individuals who may be at risk of developing Diabetic Retinopathy performed not only by ophthalmologists but also by highly trained clinicians or medical staff. Early treatment of the disease can yield significant cost savings compared with the direct costs for those disabled by vision loss.
- Diabetic Retinopathy is by means of manually comparing a patient's fundus photograph (produced by a fundus camera which is a specialized camera capable of producing fundus images in film or digital form) with a set of standard photographs by ophthalmologists for diagnosis purposes.
- the states of Diabetic Retinopathy are identified by reference to pathologies and symptoms shown on the fundus photographs or images. Therefore, the ophthalmologist will have to carefully study the photographs and diagnose the severity of retinal pathologies.
- This conventional method of making diagnosis requires a high degree of skill and experience and is very costly in both time and money.
- an automated system that can decide whether or not any suspicious signs of Diabetic Retinopathy are present in a fundus image can improve efficiency as only those images deemed suspect by the system would be referred for a more thorough examination by the ophthalmologist was introduced.
- computing techniques By using computing techniques to aid the analysis, the amount of time spent, the number of staff required and the inevitable human error due to performing repetitive tasks in screening of Diabetic Retinopathy is reduced. In this way, individuals who are diagnosed by the automatic digital system (automated diagnosis) as having early retinal lesions would directly be referred to an ophthalmologist for further evaluation.
- NPDR neurodegenerative disease progression into its various stages
- NPDR is indicated by the presence of microaneurysms, retinal haemorrhages, hard exudates and retinal edema
- PPDR by lesion features namely cotton wool spots
- IRMA intra-retinal micro-vascular abnormalities
- PDR microvascular occlusion (blockage of capillary network) extensively throughout the retina.
- This means one type of pathology may be used in the diagnosis of each stage of Diabetic Retinopathy or a few types of pathology depending on the images of the pathologies studied.
- the various stages of diabetic retinopathy progression can be graded using only one single type of structure present in the retinal images such as by means of using the digital map of retinal vasculature to assist in detection of early signs of Diabetic Retinopathy, and the grading of diabetic retinopathy progression by means of determining the degree of enlargement of foveal avascular zone since it has been found there is a correlation between the size of the FAZ and Diabetic Retinopathy progression.
- FAZ is therefore the fovea where there is no blood vessels and is normally located in the very centre of the macula.
- the present invention overcomes the above shortcomings by providing a method of ascertaining the area of FAZ of the retina to effectively analyse and thereafter grade various stages of Diabetic Retinopathy progression.
- the primary aim of the present invention to provide a noninvasive method for analyzing the retina for ocular manifested diseases based on the sole criteria of ascertaining the size of the FAZ instead of changes in the various pathologies in the retina.
- Diabetic Maculopathy It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases wherein the initial task of analyzing the retinal images is automated thereby dispensing with highly trained medical personnel during initial screening of patients thereby saving cost.
- a non-invasive method of analyzing the retina for ocular manifested diseases comprising,
- said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels for ascertainment of the area of the foveal avascular zone (22)
- said analyzing is based on the relative area of the foveal avascular zone
- the present invention provides,
- a non-invasive method of analyzing the retina for ocular manifested diseases comprising, capturing digital images of the retina vascular structure using a photographic device (12),
- said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels and thereafter reconstructing the enhanced extracted retinal vessels for ascertainment of the area of foveal avascular zone (22)
- said analyzing is based on the relative area of the foveal avascular zone (22) to diagnose or grade the disease by means of computerized techniques.
- FIG. 1 is a digital fundus image showing several structures present in the retina.
- FIG. 2 is a flow chart showing a block diagram outlining the general steps of one of the method of the present invention.
- FIGS. 3-A shows an input image being partitioned into small regions or blocks before histogram equalization is applied.
- FIG. 3-B shows a histogram of an image after application of Contrast Limited Adaptive Histogram Equalization before clipping
- FIG. 3-C shows the histogram after being clipped off and redistributed.
- FIG. 4-A and 4-B shows a fundus image prior to employment of image enhancement technique and after employment of image enhancement technique using Contrast Limited Adaptive Histogram Equalization.
- FIG. 4-C and 4-D shows a fundus image prior to employment of image enhancement technique and after employment of image enhancement using Independent Component Analysis.
- FIG. 5 shows the foveal avascular zone delineated after extraction and reconstruction of the vessels.
- FIG. 6 is a flow chart showing block diagram outlining the general steps of another method of the present invention.
- FIGS. 7- A and 7-B show seed-based region growing (SRG) utilizing five and ten seed pixel respectively.
- FIGS. 8 shows gradient-based region growing (GRG) utilizing seven seed pixel.
- a fundus image is a digital retinal image captured using specialized camera such as the fundus camera with Eye
- Fundus images are presented as arrays of pixels having discrete intensity values. Analyzing and interpreting fundus images have become a necessary and important diagnostic procedure in ophthalmology.
- the vasculature in retina layer referred to hereafter as the retinal vasculature can be viewed non-invasively using the fundus camera.
- the bright round structure in FIG. 1 is known as the optic disc (4).
- Retinal vessels (6) comprising arteries and veins are seen as dark red curvature lined structure.
- the darker region at tile right side of the image is known as the macular (8).
- the macular (8) has been delineated as shown in FIG. 1, it is to be understood that the said delineation is not the exact size but is delineated for easy reference.
- the centre of the macular (8) with no vessels is the most accurate vision zone and is known as the fovea (10).
- the structure of retinal vasculature plays an important role in fundus image analysis for several reasons.
- the length, diameter and path, and the changes of the vascular tree induced by the progression of Diabetic Retinopathy, one of the ocular manifested diseases, can become valuable diagnostic indices of the disease.
- the effects of clinical treatments can also be analyzed. It is also the only part of the central circulation that can be viewed non-invasively and studied in detail.
- the retinal vasculature map can also assist in detection and analysis of capillary free zone and enlargement of FAZ.
- Maculopathy are conventionally performed based on the pathologies present in the retina and below are the International Clinical Diabetic Retinopathy Disease Severity Scale and the International Clinical Diabetic Macula Edema [Diabetic Macula Edema is a specific type of Diabetic Maculopathy] Disease , Severity Scale respectively tabulated based on the pathologies present in the retina vasculature: -
- PDR One or both of the following:
- retinal vasculature As is known, the dimensions and the changes of the vascular tree induced by the progression of Diabetic Retinopathy can become valuable diagnostic indices of the disease and therefore, the morphological changes in the retinal vasculature are of great interest to ophthalmologists.
- image analysis of the retinal vasculature is a complicated task particularly because of the variability of the fundus images in terms of the colour or gray levels, the diverse morphology of the retinal anatomical pathological structures and the existence of particular features in different patients that may lead to an erroneous interpretation.
- retinal vessels extraction There are several challenges of retinal vessels extraction that may be outlined as follows:-
- lesion features A variety of non-vessel structures appearing in the surroundings, including the border of the camera's aperture, the optic disc, and pathologies (lesion features).
- the lesion features may appear as a series of bright spots, sometimes with narrow darker gaps in between which are a challenge for automatic vessel extraction.
- Maculopathy In semi-automated means human intervention is employed to select the extremities or terminal points of the capillary of the extracted vessel prior to automated plotting and delineating of the area of FAZ (22) is carried out. In fully automated means selection of the extremities or terminal points of the capillary, plotting and delineating of the area of FAZ (22) are carried out using computerized techniques without any human intervention.
- FIG. 2 there is shown a flow chart outlining the general steps of one of the method of the present invention.
- the flow chart illustrates the general steps of a preferred method to extract vessels (6) of the retinal vasculature from the fundus image taken using a photographic device preferably a fundus camera comprising an image input step, a pre-processing step, an image enhancing step, a vessel extracting step, an FAZ area determining step and an analyzing step.
- the first step is to input digital fundus image to be studied as indicated by the first block (12).
- an image pre-processing step as indicated by the second block (14) comprising a preliminary processing technique is applied to enhance the vessels (6) and reduce background noise including border of the aperture of the photographic device.
- the green channel shows the best contrast of vessels (6) to their surrounding, the green band of the input image is amongst the first to be extracted in the pre-processing step (14).
- Geometric operation such as scaling up the image to preferably two times larger than its original size is applied prior to median filtering to preserve one-pixel width vessels. This is done so that one-pixel width vessel will not be eliminated during median filtering that will be performed to smooth out the image. Median filtering is chosen due to its smoothing while preserving edges effect. After median filtering, the image will be scaled down to its original size resulting in a pre-processed image. Due to poor illumination, lack of dynamic range in the imaging sensor or even wrong settings of lens during image acquisition, low-contrast images may result.
- the pre-processed image has to undergo an image enhancing step [third block (16)] comprising an enhancement technique suitable for low and varying contrast images where the lowest and highest occupied bins are close to the minimum and the maximum of the full range of pixel values that the image type concerned allows.
- This technique is different from the global contrast stretching technique normally used in enhancing vessels located in both dark and bright regions where the said contrast stretching only attempts to increase the dynamic range of the gray levels in the image being processed and works by stretching the range of intensity values it contains to span a desired range of values (that is the full range of pixel values that the image type concerned allows).
- the image enhancement technique employed in this invention is a window (tiles) based enhancement technique called contrast limited adaptive histogram equalization (hereinafter referred to as "CLAHE").
- CLAHE contrast limited adaptive histogram equalization
- An adaptive histogram equalization (AHE) algorithm partitions an input image into small regions or blocks as indicated by the reference letters (A), (B), (C) and (D) as shown in Figure 3-A and applies histogram equalization to each one resulting in small histogram equalized regions or blocks as indicated by the reference letters (A'), (B'), (C) and (D').
- 3-A shows the image input is partitioned into four small blocks (A), (B), (C) and (D) it is to be understood that the said image may be partitioned into more than four.
- CLAHE operates on small data regions (tiles), rather than the entire image. Each tile's contrast is enhanced, so that the histogram of the output region approximately matches the specified histogram. This evens out the distribution of used grey values and thus makes hidden features of the image more visible.
- the new gray level allocation of pixels within the small block is calculated by using bilinear interpolation. This is done to reduce or eliminate artificially induced boundaries.
- the contrast especially in uniform areas is limited by clipping the height of histogram in each contextual region to avoid amplifying any noise that might be present in the image.
- FIG. 3-B When the histogram is clipped as shown by shaded box as indicated by FIG. 3-B, the number of excess pixels is counted and then they are redistributed across the whole histogram as shown in FIG. 3-C.
- FIGS. 4-A and 4-B illustrates two fundus images one prior to employment of CLAHE image enhancement technique and the other after employment of CLAHE image enhancement technique. It will be seen that the one after employment of image enhancement technique (FIG. 4-B) has a well-contrasted image.
- ICA Independent Component Analysis
- the ICA method of enhancing images involves the determination of retinal pigments namely haemoglobin, melanin and macular pigment from the fundus images based on the distribution of the retinal pigments.
- This method of enhancing contrast by determining the said retinal pigments from macular images does not create artefacts in its enhanced state and has been found to perform better than CLAHE.
- the haemoglobin and macular pigment are used to reveal retinal blood vessels and the macular region for studies to be conducted and can be used for image enhancement in particular to visualise very fine vessels that are poorly contrasted without the need of injecting any contrasting agent.
- vessel extraction process as indicated by the fourth block (18), morphological transformation, preferably using the Bottom-hat technique, is performed to extract the enhanced retinal vasculature.
- the Bottom-hat technique is used to isolate dark objects on light surroundings that are convex.
- SE structuring element
- the size of SE is preferably set to be 15, however it is to be understood that the size of SE selected is dependent on the width of the primary vessels and the intersection points.
- the SE is posed in different orientations using a rotating angle from 0 to 180 degrees.
- the Bottom-hat technique with twelve line structuring elements, SEs (but it is to be understood that any number of SE can be used) of size 15 pixels and able to orientate from 0 to 180 degrees (at incremental of 15 degrees) is carried out to ensure all blood vessels are extracted.
- Background noise removal preferably using the averaging filter technique is then carried out to reduce background noise and non-vessel features at the background that are being enhanced as well while undergoing the Bottom-hat technique. Further enhancement of extracted vessels may then be carried out using normal contrast stretching technique.
- FIG. 5 An illustration of the FAZ area (22) which is plotted and delineated using the semi-automated means is shown in FIG. 5. From the FAZ (22) distribution, it is found that there is overlapping of FAZ (22) between two stages of the disease. The overlapping ranges are highlighted to indicate progression of the disease to another stage. The area of FAZ (22) that overlaps the later stage is used as the upper bound of the ranges while the minimum FAZ area (22) of the later stage is used as the lower bound of the ranges. The FAZ area ranges that show progressions of the disease stage by stage are analyzed.
- the lower bounds may indicate the maximum FAZ area (22) for the previous stage and thus will be the indicator of progression to the next stage while the upper bounds may indicate the maximum FAZ area (22) for progression to the next stage. Area within the progression range shows that the disease is in high risk of progressing to the next stage.
- the severity of Diabetic Retinopathy and Diabetic Maculopathy can be easily graded.
- five ranges of FAZ area (22) for Diabetic Retinopathy grading are obtained namely Normal, Mild nonproliferative diabetic retinopathy, Moderate non-proliferative diabetic retinopathy, Severe non-proliferative diabetic retinopathy and proliferative diabetic retinopathy.
- NPDR range 3400 pixels - 6500 pixels
- Progression from NPDR to severe NPDR/ PDR range 6500 pixels - 6600 pixels
- the above method of determining the FAZ area (22) can also be used to grade Diabetic Maculopathy (DM).
- DM Diabetic Maculopathy
- the maximum value for FAZ area (22) for each stage is investigated and used to mark the border of progression of the disease.
- three ranges of FAZ area (22) for Diabetic Maculopathy grading and its progressing stages are obtained namely Normal, Diabetic Maculopathy (Observable) and Severe Diabetic Maculopathy (Referable). If a set of 584 x 565 pixel sized digital fundus images is being considered, the grading for Diabetic Maculopathy based on the size of FAZ is as follows:
- morphological transformation has certain limitations such as the inability to highlight bifurcation and intersection points effectively where the profiles are larger than the Structuring Element. It is observed that the intersection point mostly at primary vessels can only be weakly or partially extracted. In order to achieve a better result a morphology reconstruction process is performed based on region growing on the extracted vessels.
- FIG. 6 is a flow chart outlining the general steps of another method of the present invention having an additional vessel reconstruction process.
- the flow chart illustrates the general steps of a second method to extract vessels (6) of the retinal vasculature from the fundus image comprising an image input step, a pre-processing step, an image enhancing step, a vessel extracting step, a vessel reconstruction step and an FAZ area (22) determining step and an analysing step.
- the steps in the second method are similar to the preferred method described and illustrated by FIG. 2 (and are thus indicated with the same reference numerals) except for an additional vessel reconstruction step as indicated by the fifth block (19) in FIG. 6.
- a region growing technique is employed such as seed-based region growing (SRG) or based on first-order Gaussian derivative known as gradient-based region growing (GRG) is performed on the extracted retinal vasculature.
- the seed- based region growing (SRG) starts with selecting a set of seed pixels and grows from these seeds by merging neighbouring pixels whose properties are most similar to the pre-merged region.
- FIGS. 7- A and 7-B show seed-based region growing (SRG) technique using five and ten seed pixels to reconstruct the extracted vessels prior to ascertaining the area of FAZ (22).
- the arrows illustrated in FIGS. 7-A and 7-B indicate the placements of seed pixels.
- the region growing is restricted to the selected window of suspected area centred on the selected seed.
- the decision of adding a pixel to a formed region is based on homogeneity criteria specified which reflects the similarity between the region and the candidate pixel by comparing the seed pixel's gray level with the statistics (e.g. mean, variance etc.) of its neighbouring pixels. If some growing conditions are fulfilled from the comparison, the seed pixel will grow towards its neighbours.
- SRG seed-based region growing
- FIG. 8 shows gradient- based region growing (GRG) technique using seven seed pixel to reconstruct the extracted vessels prior to ascertaining the area of FAZ (22).
- the arrows illustrated in FIGS. 8 indicate the placements of seed pixels.
- GRG incorporates both gradient magnitude change and average intensity as the homogeneity criteria that enable the process to adapt to intensity changes and intensity spread over the vasculature region.
- GRG thus reduces the required number of seeds to near optimal for the region growing process in reconstructing retinal vasculature.
- the gradient magnitude change in GRG is also used to identify ambiguous boundary between homogeneous regions and resolve the partial- volume effect (over segmentation) problem on the boundary.
- seed pixels may also placed in the pathology regions, which are near or at the periphery of foveal capillary network. This will increase the number of vessel ends as pathologies usually originated from the vessel ends.
- Vessel and pathology end points are extracted from this image using morphological operations such as thinning and spurring.
- the selection of terminal or end points near or at the perifoveal capillary network may be carried out either by manually or automatically. Thereafter the selection, construction of the FAZ area (22) is done by an automated process. It is found that the FAZ area (22) obtained by the developed method achieved a higher degree of reliability and accuracy as compared to manual analysis using coloured fundus image that is usually practiced by the ophthalmologist for most early Diabetic Retinopathy and Diabetic Maculopathy cases.
- the said invention has disclosed a new approach for determination of the FAZ area (22) for grading the severity of Diabetic Retinopathy or Diabetic Maculopathy based on the digital map of retinal vasculature obtained from extraction (and optionally reconstruction) of retinal vasculature to enable the vessel ends and pathologies surrounding FAZ area (22) to be derived for reliable determination of the FAZ area (22).
- the algorithms utilized in the image enhancing technique has been described and illustrated in some detail as being CLAHE and ICA, other image enhancing algorithms may also be applicable as what is advantageous in accordance with the present invention is the fact that the image enhancing technique specifically caters for low and varying contrast image to enhance the retinal vessels from its background.
- the seed growing image segmentation technique utilized in the reconstruction of vessels has been described and illustrated in some detail as being SRG and GRG, other image segmentation techniques may also be applicable such as thresholding and edge-based segmentation as what is advantageous in accordance with the present invention is the fact that the image segmentation technique is able to permit reconstruction of the extracted vessels with high accuracy to allow reliable ascertainment of the FAZ (22).
- the new technique has been described and illustrated as for use in diagnosing and grading Diabetic Retinopathy and Diabetic Maculopathy, the extracted and reconstructed vessels can also be used to assist in diagnosis of hypertension based on the turtuosity of the retinal vessels.
Description
A NON INVASIVE METHOD FOR ANALYSING THE RETINA FOR OCULAR MANIFESTED DISEASES
1. TECHNICAL HELD OF INVENTION
The present invention relates generally to a method of analyzing the retina for ocular manifested diseases by ascertaining the area of foveal avascular zone of the retina.
2. BACKGROUND OF THE INVENTION
The finest blood vessels linking arteries to veins, which are called retinal capillaries (very thin or micro vessels), tend to be damaged due to complications of diabetes mellitus. This progressive damage called diabetic retinopathy occurs due to a combination of micro-vascular leakage and micro-vascular occlusion. Diabetic retinopathy (DR) can be classified into 3 main forms; background (non-proliferative) diabetic retinopathy (hereinafter referred to as "NPDR"), pre-proliferative diabetic retinopathy (hereinafter referred to as "PPDR") and maculopathy and proliferative diabetic retinopathy (hereinafter referred to as "PDR") based on the presence of pathologies. NPDR is a form of Diabetic Retinopathy caused by micro-
vascular leakage away from the macula. The occurrence of NPDR is indicated by the presence of sacculations from the capillary walls (microaneurysms), blood (retinal haemorrhages), lipid exudates (hard exudates) and retinal edema. The rupture of these microaneurysms results in haemorrhages. At this stage, there are often no obvious warning signs and patients suffering from the disease are unaware until it has advanced into more severe levels. Treatment of the disease at this stage may prevent future complications and towards blindness. Moderate to severe NPDR is also known as PPDR where lesion features namely cotton wool spots, venous beading and intra-retinal micro-vascular abnormalities (IRMA) can be found. These changes are found in areas of retinal capillary non-perfusion and indicate the severity of the non-proliferative changes. The Early Treatment Diabetic Retinopathy Study (ETDRS) identified multiple retinal haemorrhages, venous caliber (width) changes and IRMA as main indicator of risk of advancement to proliferative diabetic retinopathy (PDR). Sometimes, there are extensive areas of microvascular occlusion (blockage of capillary network) throughout the retina. When vessel occlusions occur, the retinal tissues that lack of nutrition and oxygen release a vasoproliferative factor that stimulates the growth of new abnormal blood vessels at locations where the normal capillaries are occluded. This form of diabetic retinopathy called PDR may cause bleeding into the cavity of the eye and produce scars (scarring) with loss of vision.
When microvascular leakage of edema, blood and lipid occurs in the central region of the retina (the macula), it results in blurred vision and is called diabetic maculopathy. Diabetic Maculopathy can be in both background and proliferative diabetic retinopathy and is a leading cause of legal blindness in diabetics. Among NPDR patients, macular edema is commonly the cause of decreased vision. Diabetic Maculopathy can be classified into focal, diffuse, ischaemic and mixed types. Focal maculopathy characterized by microaneurysms, haemorrhages, macular edema and hard exudates are usually arranged in a circular pattern. Diffuse maculopathy caused by leakage from the retinal capillaries results in diffuse edema. This may also result in cystoid macular edema. Ischaemic maculopathy is diagnosed when there is disruption of foveal capillaries resulting in enlargement of foveal avascular zone (hereinafter referred to as "FAZ").
Diabetic Retinopathy is a common complication of diabetes mellitus and is the leading cause of blindness in the working-age population. It is a silent disease and the patient realises this only when the changes in the retina have progressed to a level where treatment is complicated and nearly impossible.
The incidence of Diabetic Retinopathy has increased with increase of life expectancy of diabetics. Roughly, about 50 percent of diabetic patients develop Diabetic Retinopathy after 10 years, 70 percent after 20 years and 90 percent after 30 years of onset of the diabetes. As the disease progresses,
clinically evident retinopathy (pathology) appears namely microanerysms, dot and blot haemorrhages, cotton wool spots, venous caliber changes and retinal capillary non-perfusion. However, changes at haemodynamic (physical aspects of the blood circulation) and cellular levels already take place even when there is no clinically detectable retinopathy. It is believed that visual loss occurring from Diabetic Retinopathy can be prevented by a periodic follow-up that is very important for a timely intervention to reduce the risk of blindness in diabetic patients. Diabetic patients with no Diabetic Retinopathy or mild Diabetic Retinopathy should have their eyes checked by an ophthalmologist at least once a year. Proper screening for retinopathy followed by laser surgery treatment can significantly reduce the incidence of blindness. Screening in Diabetic Retinopathy is a non-diagnostic test or identification of individuals who may be at risk of developing Diabetic Retinopathy performed not only by ophthalmologists but also by highly trained clinicians or medical staff. Early treatment of the disease can yield significant cost savings compared with the direct costs for those disabled by vision loss.
Known methods of screening Diabetic Retinopathy is by means of manually comparing a patient's fundus photograph (produced by a fundus camera which is a specialized camera capable of producing fundus images in film or digital form) with a set of standard photographs by ophthalmologists for
diagnosis purposes. The states of Diabetic Retinopathy are identified by reference to pathologies and symptoms shown on the fundus photographs or images. Therefore, the ophthalmologist will have to carefully study the photographs and diagnose the severity of retinal pathologies. This conventional method of making diagnosis requires a high degree of skill and experience and is very costly in both time and money. The high cost of examination and the shortage of ophthalmologists or highly trained clinicians, particularly in undeveloped or rural areas in developing countries, are prominent factors that hamper patients from obtaining regular examinations. Further mass screening of a large number of diabetic patients annually poses a huge workload for the ophthalmologists or highly trained clinicians as they are required to examine a prohibitively large number of fundus images and the number of images produced without any sign of Diabetic Retinopathy, is extremely large compared to the ones having signs. Potential of inconsistent judgment can occur due to varying degrees of experience of ophthalmologists and highly trained clinicians and so the diagnosis is therefore subjective. Errors due to susceptibility of the observer are inevitable. Such errors will either result in the delay of patients being referred to ophthalmologist for further examination and treatment or false alarm being raised. The degree of severity varies over the retina (fundus) and therefore assessment of the complete fundus is necessary. The optimal time for treatment is before the patient experiences visual symptoms. Therefore,
early detection of the disease through regular screening and timely treatment is very crucial to prevent virtual loss and blindness. It is also very important to recognize the stages in which treatment may be beneficial.
To address the costly, time consuming and subjectiveness of manual screening, which is further bogged down by inconsistent images of pathologies taken under differing coloured tones and conditions, an automated system that can decide whether or not any suspicious signs of Diabetic Retinopathy are present in a fundus image can improve efficiency as only those images deemed suspect by the system would be referred for a more thorough examination by the ophthalmologist was introduced. By using computing techniques to aid the analysis, the amount of time spent, the number of staff required and the inevitable human error due to performing repetitive tasks in screening of Diabetic Retinopathy is reduced. In this way, individuals who are diagnosed by the automatic digital system (automated diagnosis) as having early retinal lesions would directly be referred to an ophthalmologist for further evaluation. This would allow more patients to be screened per year and the ophthalmologists will be able to spend more time on those patients who are actually in need of their expertise. Computer aided analysis of digitized images also offers the possibility of more quantitative and repeatable measurements, reducing the variability in the grades
assigned. Therefore, automated diagnosis could improve the analysis of progression of the disease and make screening more efficient and fast.
However, typical diagnosis for grading Diabetic Retinopathy progression into its various stages is based on the several pathologies present in the retina individually or in combination. For example, NPDR is indicated by the presence of microaneurysms, retinal haemorrhages, hard exudates and retinal edema, PPDR by lesion features namely cotton wool spots, venous beading and intra-retinal micro-vascular abnormalities (IRMA) and PDR by microvascular occlusion (blockage of capillary network) extensively throughout the retina. This means one type of pathology may be used in the diagnosis of each stage of Diabetic Retinopathy or a few types of pathology depending on the images of the pathologies studied. In short, there is no one single type of pathology that can be used in determining all the grades of Diabetic Retinopathy progression. The same goes for diagnosing diabetic maculopathy that is based on the pathologies found in the retina mostly at the macular area. Further, due to the study of various types of pathologies present in the retinal vasculature, the person analyzing the retinal images must be one who is a highly trained medical personnel and experienced so as to be able to detect changes, indicating different stages of diabetic retinopathy progression, in each and every type of pathology. The skilled person must therefore be one who has studied in detail the characteristics and changing
patterns of each and every type of pathology, who is none other than an ophthalmologist or his trained staff. And because it involves so many types of pathologies the skilled person being human may make errors leading to inaccurate or wrong diagnosis due to the quality of images obtained as a result of inherent images produced by the photographic device. Although analysis of the various types of pathologies and their changes can be automated, such automation would require use of several different software to cater for the different types of pathology studied, their inconsistent images under variable colour tones (due to differing makes and quality of digital cameras used) and detection of their characteristics and changes that is costly.
It is therefore advantageous if the various stages of diabetic retinopathy progression can be graded using only one single type of structure present in the retinal images such as by means of using the digital map of retinal vasculature to assist in detection of early signs of Diabetic Retinopathy, and the grading of diabetic retinopathy progression by means of determining the degree of enlargement of foveal avascular zone since it has been found there is a correlation between the size of the FAZ and Diabetic Retinopathy progression. In a normal healthy person, there is a region in the macula where there are no vessels in the entire fovea namely FAZ. FAZ is therefore the fovea where there is no blood vessels and is normally located in the very centre of the macula. However, an enlargement of FAZ is usually found in
eyes of patients with diabetic retinopathy resulting from a loss of capillaries in the perifoveal capillary network. This is often observed in early Diabetic Retinopathy such as NPDR and also in PDR. The capillaries surrounding an FAZ region may possibly tend to be blocked or damaged as a result of diabetes. It is found that the FAZ dimensions were strongly and positively correlated with the severity of capillary. non-perfusion (blockage of capillary) and the presence of proliferative diabetic retinopathy. Early detection of FAZ enlargement at NPDR stage may prevent the progress of the disease to PDR stage and towards visual loss.
However, one is not able to currently determine the area of FAZ and its enlargement over time accurately and reliably based on merely studying coloured fundus images and comparing fundus images of a patient taken at different intervals. Fundus image analysis presents several challenges such as image variability (due to pathologies of different patients and due to differing imaging conditions for the same patient), low image contrast of blood vessels against the macular region, improper illumination, glare, fadeout, loss of focus and artefacts arising from reflection, refraction and dispersion. Therefore, a suitable image processing technique is needed to provide reliable fundus image analysis of the FAZ.
The present invention overcomes the above shortcomings by providing a method of ascertaining the area of FAZ of the retina to effectively analyse and thereafter grade various stages of Diabetic Retinopathy progression.
3. SUMMARY OF THE INVENTION
Accordingly, it is the primary aim of the present invention to provide a noninvasive method for analyzing the retina for ocular manifested diseases based on the sole criteria of ascertaining the size of the FAZ instead of changes in the various pathologies in the retina.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases that has enabled the determination of FAZ that is bordered by capillary ends in the macular region with good accuracy.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases which is able to provide a comprehensive grading for severity of Diabetic Retinopathy and
Diabetic Maculopathy.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases wherein the initial task of analyzing the retinal images is automated thereby dispensing with highly trained medical personnel during initial screening of patients thereby saving cost.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases which is capable of overcoming the huge workload of professional ophthalmologists thus freeing them from performing repetitive tasks in initial screening of Diabetic Retinopathy and permitting them to concentrate on patients that require their expertise.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases which is efficient and reliable thereby allowing detection of Diabetic Retinopathy progression to be taken early enabling prevention of progress of the disease by directly referring the patient to a professional.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases capable of
allowing tiny vessels to be detected, extracted and reconstructed for further study.
It is yet another object of the present invention to provide a non-invasive method for analyzing the retina for ocular manifested diseases which is safe as it does not require any contrasting agent to be injected into the patient for a better image production.
Other and further objects of the invention will become apparent with an understanding of the following detailed description of the invention or upon employment of the invention in practice.
According to a preferred embodiment of the present invention there is provided,
A non-invasive method of analyzing the retina for ocular manifested diseases comprising,
capturing digital images of the retina vascular structure using a photographic device (12),
undergoing image pre-processing technique (14),
undergoing image enhancement technique (16),
analyzing processed images for purposes of diagnosis (18)
characterized in that
said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels for ascertainment of the area of the foveal avascular zone (22)
further characterized in that
said analyzing is based on the relative area of the foveal avascular zone
(22) to diagnose or grade the disease by means of computerized techniques.
In another embodiment, the present invention provides,
A non-invasive method of analyzing the retina for ocular manifested diseases comprising,
capturing digital images of the retina vascular structure using a photographic device (12),
undergoing image pre-processing technique (14),
undergoing image enhancement technique (16),
analyzing processed images for purposes of diagnosis (18)
characterized in that
said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels and thereafter reconstructing the enhanced extracted retinal vessels for ascertainment of the area of foveal avascular zone (22)
further characterized in that
said analyzing is based on the relative area of the foveal avascular zone (22) to diagnose or grade the disease by means of computerized techniques.
4. BRIEF DESCRIPTION OF THE DRAWINGS
Other aspects of the present invention and their advantages will be discerned after studying the Detailed Description in conjunction with the accompanying drawings in which:
FIG. 1 is a digital fundus image showing several structures present in the retina.
FIG. 2 is a flow chart showing a block diagram outlining the general steps of one of the method of the present invention.
FIGS. 3-A shows an input image being partitioned into small regions or blocks before histogram equalization is applied.
FIG. 3-B shows a histogram of an image after application of Contrast Limited Adaptive Histogram Equalization before clipping
FIG. 3-C shows the histogram after being clipped off and redistributed.
FIG. 4-A and 4-B shows a fundus image prior to employment of image enhancement technique and after employment of image enhancement technique using Contrast Limited Adaptive Histogram Equalization.
FIG. 4-C and 4-D shows a fundus image prior to employment of image enhancement technique and after employment of image enhancement using Independent Component Analysis.
FIG. 5 shows the foveal avascular zone delineated after extraction and reconstruction of the vessels.
FIG. 6 is a flow chart showing block diagram outlining the general steps of another method of the present invention.
FIGS. 7- A and 7-B show seed-based region growing (SRG) utilizing five and ten seed pixel respectively.
FIGS. 8 shows gradient-based region growing (GRG) utilizing seven seed pixel.
5. DETAILED DESCRIPTION OF THE DRAWINGS
In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those or ordinary skill in the art that the invention may be practised without these specific details. In other instances, well known
methods, procedures and/ or components have not been described in detail so as not to obscure the invention.
The invention will be more clearly understood from the following description of the methods thereof, given by way of example only with reference to the accompanying drawings. In the descriptions that follow, like numerals represent like elements in all figures. For example, where the numeral (2) is used to refer to a particular element in one figure, the numeral (2) appearing in any other figure refers to the same element.
Referring now to FIG. 1, there is shown a digital fundus image showing several structures present in the retina (2). A fundus image is a digital retinal image captured using specialized camera such as the fundus camera with Eye
Cap Retina Software. Many retinal diseases and systematic diseases will lead to evident fundus changes that can be observed by fundus photographs.
Fundus images are presented as arrays of pixels having discrete intensity values. Analyzing and interpreting fundus images have become a necessary and important diagnostic procedure in ophthalmology. The vasculature in retina layer, referred to hereafter as the retinal vasculature can be viewed non-invasively using the fundus camera. The bright round structure in FIG. 1 is known as the optic disc (4). Retinal vessels (6) comprising arteries and veins are seen as dark red curvature lined structure. The darker region at tile right
side of the image is known as the macular (8). Although the macular (8) has been delineated as shown in FIG. 1, it is to be understood that the said delineation is not the exact size but is delineated for easy reference. The centre of the macular (8) with no vessels is the most accurate vision zone and is known as the fovea (10).
Among the features in ocular fundus image, the structure of retinal vasculature plays an important role in fundus image analysis for several reasons. The length, diameter and path, and the changes of the vascular tree induced by the progression of Diabetic Retinopathy, one of the ocular manifested diseases, can become valuable diagnostic indices of the disease.
The effects of clinical treatments can also be analyzed. It is also the only part of the central circulation that can be viewed non-invasively and studied in detail. The retinal vasculature map can also assist in detection and analysis of capillary free zone and enlargement of FAZ.
As described above, the grading for Diabetic Retinopathy and Diabetic
Maculopathy are conventionally performed based on the pathologies present in the retina and below are the International Clinical Diabetic Retinopathy Disease Severity Scale and the International Clinical Diabetic Macula Edema [Diabetic Macula Edema is a specific type of Diabetic Maculopathy] Disease ,
Severity Scale respectively tabulated based on the pathologies present in the retina vasculature: -
Proposed Disease Severity Findings Observable upon Dilated Level for Diabetic Retinopathy Ophthalmoscopy
No apparent retinopathy No abnormalities Mild NPDR Microaneurysms (MA) only Moderate NPDR More than just MAs but less than severe
NPDR
Severe NPDR Any of the following:
(a) More than 20 intra-retinal haemorrhages in each of four quadrants
(b) Definite venous beading in two or more quadrants
(c) Prominent IRMA in one or more quadrants
And no signs of PDR
PDR One or both of the following:
(a) Neovascularization
(b) Vitreous / Pre-retinal haemorrhage
Proposed Disease Severity Findings Observable upon Dilated
Level for Diabetic Macular Edema Ophthalmoscopy
Mild diabetic macular edema Some retinal thickening or hard exudates in posterior pole but distant from the centre of macula
Moderate diabetic macular Retinal thickening or hard exudates edema approaching the centre of the macula but not involving the centre
Severe diabetic macular Retinal thickening or hard exudates edema involving the centre of the macula
Generally the criteria used in grading Diabetic Maculopathy is as stated below:
(a) Exudate within 1 disc diameter of centre of fovea
(b) Exudate or group of exudates within macula
(c) Any mcroaneurysms or haemorrhage within 1 disc diameter of centre of fovea and only if best corrected visual acuity less than 6/12 (d) Retinal thickening less than 1 disc diameter of centre of fovea (if stereoscopic photos are available).
Depending on the above criteria, grading for Diabetic Maculopathy is as below:-
As is known, the dimensions and the changes of the vascular tree induced by the progression of Diabetic Retinopathy can become valuable diagnostic indices of the disease and therefore, the morphological changes in the retinal vasculature are of great interest to ophthalmologists. However, image analysis of the retinal vasculature is a complicated task particularly because of the variability of the fundus images in terms of the colour or gray levels, the diverse morphology of the retinal anatomical pathological structures and the existence of particular features in different patients that may lead to an erroneous interpretation. There are several challenges of retinal vessels extraction that may be outlined as follows:-
(a) A wide range of vessel widths - from a pixel to 12 pixels wide
(b) Low contrast of vessels to its surrounding areas. Narrow vessels often have the lowest contrast.
(c) A variety of non-vessel structures appearing in the surroundings, including the border of the camera's aperture, the optic disc, and pathologies (lesion features). The lesion features may appear as a series of bright spots, sometimes with narrow darker gaps in between which are a challenge for automatic vessel extraction.
(d) Some wider vessels have a bright strip along the centre called the "central reflex", causing a complicated intensity cross-section. This may be hard to be distinguished locally from two side-by-side vessels.
Therefore, to enable an accurate study of the retinal vasculature to determine and analyse the area of FAZ (22), to reliably and accurately diagnose stages of ocular manifested diseases, digital images need to first undergo an image processing technique automatically by intelligent computerized analysis systems whereby a technique is employed to manipulate digital images to preferably perform image enhancement, image noise removal, image segmentation or extraction, image reconstruction and image statistical extraction and finally determining the area of FAZ (22) based on the extracted vessel; either by semi-automated or by fully automated means; before diagnosing differing severity of Diabetic Retinopathy or Diabetic
Maculopathy. In semi-automated means human intervention is employed to
select the extremities or terminal points of the capillary of the extracted vessel prior to automated plotting and delineating of the area of FAZ (22) is carried out. In fully automated means selection of the extremities or terminal points of the capillary, plotting and delineating of the area of FAZ (22) are carried out using computerized techniques without any human intervention.
Referring to FIG. 2 there is shown a flow chart outlining the general steps of one of the method of the present invention. The flow chart illustrates the general steps of a preferred method to extract vessels (6) of the retinal vasculature from the fundus image taken using a photographic device preferably a fundus camera comprising an image input step, a pre-processing step, an image enhancing step, a vessel extracting step, an FAZ area determining step and an analyzing step. From the said flow chart, it can be seen that the first step is to input digital fundus image to be studied as indicated by the first block (12). Prior to actual vessel extraction, an image pre-processing step as indicated by the second block (14) comprising a preliminary processing technique is applied to enhance the vessels (6) and reduce background noise including border of the aperture of the photographic device. As the green channel shows the best contrast of vessels (6) to their surrounding, the green band of the input image is amongst the first to be extracted in the pre-processing step (14). In this pre-processing step
(14) which is prior to image enhancing step as indicated by the third block
(16), a combination of geometric operation and median filtering is performed on the green band image. Geometric operation such as scaling up the image to preferably two times larger than its original size is applied prior to median filtering to preserve one-pixel width vessels. This is done so that one-pixel width vessel will not be eliminated during median filtering that will be performed to smooth out the image. Median filtering is chosen due to its smoothing while preserving edges effect. After median filtering, the image will be scaled down to its original size resulting in a pre-processed image. Due to poor illumination, lack of dynamic range in the imaging sensor or even wrong settings of lens during image acquisition, low-contrast images may result. Thus the pre-processed image has to undergo an image enhancing step [third block (16)] comprising an enhancement technique suitable for low and varying contrast images where the lowest and highest occupied bins are close to the minimum and the maximum of the full range of pixel values that the image type concerned allows. This technique is different from the global contrast stretching technique normally used in enhancing vessels located in both dark and bright regions where the said contrast stretching only attempts to increase the dynamic range of the gray levels in the image being processed and works by stretching the range of intensity values it contains to span a desired range of values (that is the full range of pixel values that the image type concerned allows). Preferably the image enhancement technique employed in this invention is a window (tiles) based
enhancement technique called contrast limited adaptive histogram equalization (hereinafter referred to as "CLAHE"). To further increase the contrast produced by histogram equalization, local properties of an image can be considered. An adaptive histogram equalization (AHE) algorithm partitions an input image into small regions or blocks as indicated by the reference letters (A), (B), (C) and (D) as shown in Figure 3-A and applies histogram equalization to each one resulting in small histogram equalized regions or blocks as indicated by the reference letters (A'), (B'), (C) and (D'). Although FIG. 3-A shows the image input is partitioned into four small blocks (A), (B), (C) and (D) it is to be understood that the said image may be partitioned into more than four. Unlike contrast stretching, CLAHE operates on small data regions (tiles), rather than the entire image. Each tile's contrast is enhanced, so that the histogram of the output region approximately matches the specified histogram. This evens out the distribution of used grey values and thus makes hidden features of the image more visible. The new gray level allocation of pixels within the small block is calculated by using bilinear interpolation. This is done to reduce or eliminate artificially induced boundaries. In CLAHE, the contrast especially in uniform areas is limited by clipping the height of histogram in each contextual region to avoid amplifying any noise that might be present in the image. When the histogram is clipped as shown by shaded box as indicated by FIG. 3-B, the number of excess pixels is counted and then they are redistributed across the whole
histogram as shown in FIG. 3-C. By using CLAHE vessels in both bright region (optic disc) and dark regions are evenly enhanced and can be distinguished as shown in FIGS. 4-A and 4-B which illustrates two fundus images one prior to employment of CLAHE image enhancement technique and the other after employment of CLAHE image enhancement technique. It will be seen that the one after employment of image enhancement technique (FIG. 4-B) has a well-contrasted image.
Alternatively, an algorithm known as Independent Component Analysis (hereinafter referred to as "ICA") may be employed in image enhancing during processing of the digital fundus images. The ICA method of enhancing images involves the determination of retinal pigments namely haemoglobin, melanin and macular pigment from the fundus images based on the distribution of the retinal pigments. This method of enhancing contrast by determining the said retinal pigments from macular images does not create artefacts in its enhanced state and has been found to perform better than CLAHE. The haemoglobin and macular pigment are used to reveal retinal blood vessels and the macular region for studies to be conducted and can be used for image enhancement in particular to visualise very fine vessels that are poorly contrasted without the need of injecting any contrasting agent. As vessels are the predominant and most reliable structures in the fundus images, reliable vessel extraction is a requirement for subsequent retinal
image analysis. Vessel enhancement as achieved by CLAHE or ICA described above increases the contrast of vessels to the background and this makes the task to extract vessel from the background less difficult. In vessel extraction process as indicated by the fourth block (18), morphological transformation, preferably using the Bottom-hat technique, is performed to extract the enhanced retinal vasculature. The Bottom-hat technique is used to isolate dark objects on light surroundings that are convex. Preferably the structuring element (hereinafter referred to as "SE") used is of line type as the vessels are mainly linear in form. The size of the element is critical because portions of vessels with profiles larger than the SE will be excluded. However, using larger SE can cause more objects representing unwanted vessels to be extracted. To ensure that we are able to extract the primary vessels (that are normally 10 to 12 pixel wide according to a 584 x 565 pixel digital fundus camera) including their branching and intersection points, the size of SE is preferably set to be 15, however it is to be understood that the size of SE selected is dependent on the width of the primary vessels and the intersection points. The SE is posed in different orientations using a rotating angle from 0 to 180 degrees. A Bottom-hat technique using the said line structuring element, SE, allow vessels even in low local contrast regions to be extracted regardless of their sizes and directions. Advantageously the Bottom-hat technique with twelve line structuring elements, SEs, (but it is to be understood that any number of SE can be used) of size 15 pixels and able to
orientate from 0 to 180 degrees (at incremental of 15 degrees) is carried out to ensure all blood vessels are extracted. Background noise removal preferably using the averaging filter technique is then carried out to reduce background noise and non-vessel features at the background that are being enhanced as well while undergoing the Bottom-hat technique. Further enhancement of extracted vessels may then be carried out using normal contrast stretching technique.
After extraction of the said vessels (6), ascertainment of the area of FAZ as indicated by the fifth block (20) in FIG. 2 is carried out. As stated earlier the said ascertainment is done either by semi-automated or fully automated means to plot and delineate the area of FAZ (22) based on selected extremities (or terminal points) of the extracted capillaries. Subsequently an analyzing step as indicated by the sixth block (21) in FIG. 2 employing an automated computerized technique will follow for purposes of Diabetic Retinopathy and also Diabetic Maculopathy grading based on the relative area of the FAZ
(22). An illustration of the FAZ area (22) which is plotted and delineated using the semi-automated means is shown in FIG. 5. From the FAZ (22) distribution, it is found that there is overlapping of FAZ (22) between two stages of the disease. The overlapping ranges are highlighted to indicate progression of the disease to another stage. The area of FAZ (22) that overlaps the later stage is used as the upper bound of the ranges while the minimum
FAZ area (22) of the later stage is used as the lower bound of the ranges. The FAZ area ranges that show progressions of the disease stage by stage are analyzed. The lower bounds may indicate the maximum FAZ area (22) for the previous stage and thus will be the indicator of progression to the next stage while the upper bounds may indicate the maximum FAZ area (22) for progression to the next stage. Area within the progression range shows that the disease is in high risk of progressing to the next stage. Using the above method, the severity of Diabetic Retinopathy and Diabetic Maculopathy can be easily graded. Using the above method preferably five ranges of FAZ area (22) for Diabetic Retinopathy grading are obtained namely Normal, Mild nonproliferative diabetic retinopathy, Moderate non-proliferative diabetic retinopathy, Severe non-proliferative diabetic retinopathy and proliferative diabetic retinopathy.
In the event, a set of 584 x 565 pixel (picture element) sized digital fundus images are being considered for the grading of Diabetic Retinopathy and its progressing stages based on the size of FAZ as follows:
(a) Normal range: less than 3300 pixels
(b) Progression from normal to NPDR range: 3300 pixels- 3400 pixels
(c) NPDR range: 3400 pixels - 6500 pixels
(d) Progression from NPDR to severe NPDR/ PDR range: 6500 pixels - 6600 pixels
(e) Severe NPDR / PDR range: more than 6600 pixels
Although the above grading is tabulated in pixels, it is to be understood that the number of pixels is dependent on the megapixels of a camera used in capturing digital images. The above result is just one example using 584 x 565 pixel sized images. While the grading of Diabetic Retinopathy has been described and illustrated in some detail as being in five ranges as stated above, ranges below or above five may also be applicable as what is advantageous in accordance with the present invention is the fact that the present invention allows accurate and reliable ascertainment of the FAZ area
(22) to aid grading of Diabetic Retinopathy and its progressing stages.
The above method of determining the FAZ area (22) can also be used to grade Diabetic Maculopathy (DM). For severity grading of Diabetic Maculopathy, the maximum value for FAZ area (22) for each stage is investigated and used to mark the border of progression of the disease. Using the above method, preferably three ranges of FAZ area (22) for Diabetic Maculopathy grading and its progressing stages are obtained namely Normal, Diabetic Maculopathy (Observable) and Severe Diabetic Maculopathy (Referable).
If a set of 584 x 565 pixel sized digital fundus images is being considered, the grading for Diabetic Maculopathy based on the size of FAZ is as follows:
(a) Normal : less than 3900 pixels
(b) DM (Observable): more than 3900 pixels but less than 9870 pixels
(c) Severe DM (Referable): more than 9870 pixels
Although the above grading is tabulated in pixels, it is to be understood that the number of pixels is dependent on the megapixels of a camera used in capturing digital images. The above result is just one example using 584 x 565 pixel sized images. While the grading of Diabetic Maculopathy has been described and illustrated in some detail as being in three ranges as stated above, ranges below or above three may also be applicable as what is advantageous in accordance with the present invention is the fact that the present invention allows accurate and reliable ascertainment of the area of FAZ (22) to aid grading of Diabetic Maculopathy and its progressing stages.
It is observed that morphological transformation has certain limitations such as the inability to highlight bifurcation and intersection points effectively where the profiles are larger than the Structuring Element. It is observed that the intersection point mostly at primary vessels can only be weakly or
partially extracted. In order to achieve a better result a morphology reconstruction process is performed based on region growing on the extracted vessels.
FIG. 6 is a flow chart outlining the general steps of another method of the present invention having an additional vessel reconstruction process. The flow chart illustrates the general steps of a second method to extract vessels (6) of the retinal vasculature from the fundus image comprising an image input step, a pre-processing step, an image enhancing step, a vessel extracting step, a vessel reconstruction step and an FAZ area (22) determining step and an analysing step. The steps in the second method are similar to the preferred method described and illustrated by FIG. 2 (and are thus indicated with the same reference numerals) except for an additional vessel reconstruction step as indicated by the fifth block (19) in FIG. 6. In vessel reconstruction, a region growing technique is employed such as seed-based region growing (SRG) or based on first-order Gaussian derivative known as gradient-based region growing (GRG) is performed on the extracted retinal vasculature. The seed- based region growing (SRG) starts with selecting a set of seed pixels and grows from these seeds by merging neighbouring pixels whose properties are most similar to the pre-merged region. FIGS. 7- A and 7-B show seed-based region growing (SRG) technique using five and ten seed pixels to reconstruct the extracted vessels prior to ascertaining the area of FAZ (22). The arrows
illustrated in FIGS. 7-A and 7-B indicate the placements of seed pixels. The region growing is restricted to the selected window of suspected area centred on the selected seed. The decision of adding a pixel to a formed region is based on homogeneity criteria specified which reflects the similarity between the region and the candidate pixel by comparing the seed pixel's gray level with the statistics (e.g. mean, variance etc.) of its neighbouring pixels. If some growing conditions are fulfilled from the comparison, the seed pixel will grow towards its neighbours. In the seed-based region growing (SRG) process, when the growth of one-region stops, another seed pixel which does not yet belong to any region is chosen and the step is repeated. This whole process is repeated until all pixels belonging to same region are considered.
Preferably a GRG technique is employed in reconstructing vessels to overcome limitations of SRG as in SRG more seed-pixels are needed to increase the ability of the region growing process to adapt to intensity changes and intensity spread over an image and the placement of more seed- pixels is found to be time consuming and could produce inconsistent result and even over segmentation mainly at vessel borders. FIG. 8 shows gradient- based region growing (GRG) technique using seven seed pixel to reconstruct the extracted vessels prior to ascertaining the area of FAZ (22). The arrows illustrated in FIGS. 8 indicate the placements of seed pixels. GRG incorporates both gradient magnitude change and average intensity as the homogeneity
criteria that enable the process to adapt to intensity changes and intensity spread over the vasculature region. GRG thus reduces the required number of seeds to near optimal for the region growing process in reconstructing retinal vasculature. The gradient magnitude change in GRG is also used to identify ambiguous boundary between homogeneous regions and resolve the partial- volume effect (over segmentation) problem on the boundary.
Apart from placing seed pixels in the vessel regions for determination of the FAZ area (22), seed pixels may also placed in the pathology regions, which are near or at the periphery of foveal capillary network. This will increase the number of vessel ends as pathologies usually originated from the vessel ends.
Vessel and pathology end points are extracted from this image using morphological operations such as thinning and spurring. The selection of terminal or end points near or at the perifoveal capillary network may be carried out either by manually or automatically. Thereafter the selection, construction of the FAZ area (22) is done by an automated process. It is found that the FAZ area (22) obtained by the developed method achieved a higher degree of reliability and accuracy as compared to manual analysis using coloured fundus image that is usually practiced by the ophthalmologist for most early Diabetic Retinopathy and Diabetic Maculopathy cases.
The said invention has disclosed a new approach for determination of the FAZ area (22) for grading the severity of Diabetic Retinopathy or Diabetic Maculopathy based on the digital map of retinal vasculature obtained from extraction (and optionally reconstruction) of retinal vasculature to enable the vessel ends and pathologies surrounding FAZ area (22) to be derived for reliable determination of the FAZ area (22).
Although the algorithms utilized in the image enhancing technique has been described and illustrated in some detail as being CLAHE and ICA, other image enhancing algorithms may also be applicable as what is advantageous in accordance with the present invention is the fact that the image enhancing technique specifically caters for low and varying contrast image to enhance the retinal vessels from its background.
While the seed growing image segmentation technique utilized in the reconstruction of vessels has been described and illustrated in some detail as being SRG and GRG, other image segmentation techniques may also be applicable such as thresholding and edge-based segmentation as what is advantageous in accordance with the present invention is the fact that the image segmentation technique is able to permit reconstruction of the extracted vessels with high accuracy to allow reliable ascertainment of the FAZ (22).
Although the new technique has been described and illustrated as for use in diagnosing and grading Diabetic Retinopathy and Diabetic Maculopathy, the extracted and reconstructed vessels can also be used to assist in diagnosis of hypertension based on the turtuosity of the retinal vessels.
It will be understood by those skilled in the art that changes and modifications may be made to the invention without departing from the spirit and scope of the invention. Therefore it is intended that the foregoing description merely for illustrative purposes and not intended to limit the spirit and scope of the invention in any way but only by the spirit and scope of the appended claim.
Claims
1. A non-invasive method of analyzing the retina (2) for ocular manifested diseases comprising:-
capturing digital images of the retina vascular structure using a photographic device (12)
undergoing image pre-processing technique (14),
undergoing image enhancement technique (16),
analyzing processed images for purposes of diagnosis (18),
characterized in that
said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels for ascertainment of the area of foveal avascular zone (22)
further characterized in that said analyzing is based on the relative area of the foveal avascular zone (22) to diagnose and grade the disease and its progressing stages by means of computerized techniques.
2. A non-invasive method of analyzing the retina (2) for ocular manifested diseases comprising:-
capturing digital images of the retina vascular structure using a photographic device (12),
undergoing image pre-processing technique (14),
undergoing image enhancement technique (16),
analyzing processed images for purposes of diagnosis (18),
characterized in that
said image enhancing technique specifically caters for low and varying contrast image employing a pre-determined algorithm to enhance the retinal vessels (6) from its background prior to extraction of the enhanced retinal vessels and thereafter reconstructing the enhanced extracted retinal vessels for ascertainment of the area of foveal avascular zone (22)
further characterized in that
said analyzing is based on the relative area of the foveal avascular zone (22) to grade the disease and its progressing stages by means of computerized techniques.
3. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 wherein the said method is used to grade severity of diabetic retinopathy.
4. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 wherein the said method is used to grade severity of diabetic maculopathy.
5. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 3 wherein the said method allows grading of diabetic retinopathy and its progressing stages based on the relative area of the foveal avascular zone (22) into the following: - Normal Mild non-proliferative diabetic retinopathy Moderate non-proliferative diabetic retinopathy Severe non-proliferative diabetic retinopathy Proliferative diabetic retinopathy
6. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 4 wherein the said method allows grading of diabetic maculopathy and its progressing stages based on the relative area of the foveal avascular zone (22) into the following: -
Normal DM (Observable)
Severe DM (Referable)
7. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 wherein said ascertainment of the foveal avascular zone (22) is semi-automated or fully automated.
8. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 wherein said enhancing technique employs an image enhancing algorithm.
9. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1, 2 or 8 wherein said enhancing technique is a technique employing the algorithm known as Contrast Limited Adaptive Histogram Equalization (CLAHE).
10. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1, 2 or 8 wherein said image enhancing technique is a technique employing the algorithm known as Independent
Component Analysis (ICA).
11. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 wherein extraction of the enhanced retinal vessels is by means of a technique to isolate dark objects on light surroundings that are convex known as bottom-hat technique.
12. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 11 wherein the structuring element used during vessel extraction is a line type.
13. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 12 wherein the size of the structuring element ranges from ten to fifteen pixels.
14. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 12 wherein the optimum number of structuring elements employed is twelve.
15. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 14 wherein the said structuring element is able to pose in twelve orientations with each orientation increasing by 15 degrees starting from 0 degree to 180 degrees.
16. A non-invasive method of analyzing the retina (2) for ocular manifested of diseases as claimed in Claim 2 wherein said vessel reconstruction by seed- based region growing using manual or automated computerized placement of seeds to guide vessel growth enables neighbouring vessels having similar properties to merge to facilitate selection of terminal points of capillaries of the extracted vessels.
17. A non-invasive method of analyzing the retina (2) for ocular manifested of diseases as claimed in Claim 2 wherein said vessel reconstruction by gradient-based region using manual or automated computerized placement of seeds to guide vessel growth enables neighbouring vessels to merge to facilitate selection of terminal points of capillaries of the extracted vessels.
18. A non-invasive method of analyzing the retina (2) for ocular manifested diseases as claimed in Claim 1 or 2 which is capable of diagnosing hypertension.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
MYPI20083503 | 2008-09-10 | ||
MYPI20083503A MY142859A (en) | 2008-09-10 | 2008-09-10 | A non-invasive method for analysing the retina for ocular manifested diseases |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010030159A2 true WO2010030159A2 (en) | 2010-03-18 |
Family
ID=40940235
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/MY2009/000025 WO2010030159A2 (en) | 2008-09-10 | 2009-02-10 | A non invasive method for analysing the retina for ocular manifested diseases |
Country Status (2)
Country | Link |
---|---|
MY (1) | MY142859A (en) |
WO (1) | WO2010030159A2 (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013070300A1 (en) * | 2011-11-07 | 2013-05-16 | Alcon Research, Ltd. | Retinal laser surgery |
US20140079296A1 (en) * | 2012-07-13 | 2014-03-20 | Retina Biometrix, Llc | Biometric identification via retina scanning |
US9107609B2 (en) | 2011-07-07 | 2015-08-18 | Carl Zeiss Meditec, Inc. | Inter-frame complex OCT data analysis techniques |
WO2015085130A3 (en) * | 2013-12-07 | 2015-11-05 | Razzor Technologies Inc. | Adaptive contrast in image processing and display |
US9357916B2 (en) | 2012-05-10 | 2016-06-07 | Carl Zeiss Meditec, Inc. | Analysis and visualization of OCT angiography data |
US10264963B2 (en) | 2015-09-24 | 2019-04-23 | Carl Zeiss Meditec, Inc. | Methods for high sensitivity flow visualization |
CN109886938A (en) * | 2019-01-29 | 2019-06-14 | 深圳市科曼医疗设备有限公司 | A kind of ultrasound image blood vessel diameter method for automatic measurement |
US10398302B2 (en) | 2014-05-02 | 2019-09-03 | Carl Zeiss Meditec, Inc. | Enhanced vessel characterization in optical coherence tomograogphy angiography |
CN110211136A (en) * | 2019-06-05 | 2019-09-06 | 深圳大学 | Construction method, image partition method, device and the medium of Image Segmentation Model |
CN111862121A (en) * | 2020-07-24 | 2020-10-30 | 汕头大学·香港中文大学联合汕头国际眼科中心 | Level Sets algorithm-based foveal avascular zone segmentation method and measurement method |
RU2794220C1 (en) * | 2021-12-01 | 2023-04-12 | федеральное государственное автономное учреждение "Национальный медицинский исследовательский центр "Межотраслевой научно-технический комплекс "Микрохирургия глаза" имени академика С.Н. Федорова" Министерства здравоохранения Российской Федерации | Method for diagnosing diabetic retinopathy in patients with type 2 diabetes mellitus based on the results of nail bed capillaroscopy |
-
2008
- 2008-09-10 MY MYPI20083503A patent/MY142859A/en unknown
-
2009
- 2009-02-10 WO PCT/MY2009/000025 patent/WO2010030159A2/en active Application Filing
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9107609B2 (en) | 2011-07-07 | 2015-08-18 | Carl Zeiss Meditec, Inc. | Inter-frame complex OCT data analysis techniques |
US9849034B2 (en) | 2011-11-07 | 2017-12-26 | Alcon Research, Ltd. | Retinal laser surgery |
WO2013070300A1 (en) * | 2011-11-07 | 2013-05-16 | Alcon Research, Ltd. | Retinal laser surgery |
US9357916B2 (en) | 2012-05-10 | 2016-06-07 | Carl Zeiss Meditec, Inc. | Analysis and visualization of OCT angiography data |
US20140079296A1 (en) * | 2012-07-13 | 2014-03-20 | Retina Biometrix, Llc | Biometric identification via retina scanning |
WO2014012102A3 (en) * | 2012-07-13 | 2015-07-16 | Retina Biometrix, Llc | Biometric identification via retina scanning |
WO2015085130A3 (en) * | 2013-12-07 | 2015-11-05 | Razzor Technologies Inc. | Adaptive contrast in image processing and display |
US10398302B2 (en) | 2014-05-02 | 2019-09-03 | Carl Zeiss Meditec, Inc. | Enhanced vessel characterization in optical coherence tomograogphy angiography |
US10264963B2 (en) | 2015-09-24 | 2019-04-23 | Carl Zeiss Meditec, Inc. | Methods for high sensitivity flow visualization |
CN109886938A (en) * | 2019-01-29 | 2019-06-14 | 深圳市科曼医疗设备有限公司 | A kind of ultrasound image blood vessel diameter method for automatic measurement |
CN109886938B (en) * | 2019-01-29 | 2023-07-18 | 深圳市科曼医疗设备有限公司 | Automatic measuring method for blood vessel diameter of ultrasonic image |
CN110211136A (en) * | 2019-06-05 | 2019-09-06 | 深圳大学 | Construction method, image partition method, device and the medium of Image Segmentation Model |
CN111862121A (en) * | 2020-07-24 | 2020-10-30 | 汕头大学·香港中文大学联合汕头国际眼科中心 | Level Sets algorithm-based foveal avascular zone segmentation method and measurement method |
CN111862121B (en) * | 2020-07-24 | 2023-09-26 | 汕头大学·香港中文大学联合汕头国际眼科中心 | Level set algorithm-based segmentation method and measurement method for foveal avascular region |
RU2794220C1 (en) * | 2021-12-01 | 2023-04-12 | федеральное государственное автономное учреждение "Национальный медицинский исследовательский центр "Межотраслевой научно-технический комплекс "Микрохирургия глаза" имени академика С.Н. Федорова" Министерства здравоохранения Российской Федерации | Method for diagnosing diabetic retinopathy in patients with type 2 diabetes mellitus based on the results of nail bed capillaroscopy |
RU2794220C9 (en) * | 2021-12-01 | 2023-07-11 | федеральное государственное автономное учреждение "Национальный медицинский исследовательский центр "Межотраслевой научно-технический комплекс "Микрохирургия глаза" имени академика С.Н. Федорова" Министерства здравоохранения Российской Федерации | Method for diagnosing diabetic retinopathy in patients with type 2 diabetes mellitus based on the results of nail bed capillaroscopy |
Also Published As
Publication number | Publication date |
---|---|
MY142859A (en) | 2011-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2010030159A2 (en) | A non invasive method for analysing the retina for ocular manifested diseases | |
Haleem et al. | Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: a review | |
Sekhar et al. | Automated localisation of retinal optic disk using Hough transform | |
SujithKumar et al. | Automatic detection of diabetic retinopathy in non-dilated RGB retinal fundus images | |
EP1444635B1 (en) | Assessment of lesions in an image | |
Welikala et al. | Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification | |
Akram et al. | Automated detection of dark and bright lesions in retinal images for early detection of diabetic retinopathy | |
Sekhar et al. | Automated localisation of optic disk and fovea in retinal fundus images | |
Sopharak et al. | Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods | |
Medhi et al. | An effective fovea detection and automatic assessment of diabetic maculopathy in color fundus images | |
Siddalingaswamy et al. | Automatic grading of diabetic maculopathy severity levels | |
Raman et al. | Proposed retinal abnormality detection and classification approach: Computer aided detection for diabetic retinopathy by machine learning approaches | |
WO2010131944A2 (en) | Apparatus for monitoring and grading diabetic retinopathy | |
Maher et al. | Automated diagnosis non-proliferative diabetic retinopathy in fundus images using support vector machine | |
Win et al. | Automated detection of exudates using histogram analysis for digital retinal images | |
Tobin Jr et al. | Characterization of the optic disc in retinal imagery using a probabilistic approach | |
Medhi et al. | Automatic grading of macular degeneration from color fundus images | |
Zhang et al. | Hierarchical detection of red lesions in retinal images by multiscale correlation filtering | |
Giancardo | Automated fundus images analysis techniques to screen retinal diseases in diabetic patients | |
Lu et al. | Quantification of parapapillary atrophy and optic disc | |
Lazar et al. | A novel approach for the automatic detection of microaneurysms in retinal images | |
WO2011108995A1 (en) | Automatic analysis of images of the anterior chamber of an eye | |
Samawi et al. | Optic disc segmentation in retinal fundus images using morphological techniques and intensity thresholding | |
Maher et al. | Automatic Detection of Microaneurysms in digital fundus images using LRE | |
Siddalingaswamy et al. | Automatic detection and grading of severity level in exudative maculopathy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09788109 Country of ref document: EP Kind code of ref document: A2 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 09788109 Country of ref document: EP Kind code of ref document: A2 |