Automated retinal image analysis for glaucoma screening and vessel evaluation:
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Berlin
Logos-Verl.
2006
|
| Series: | Studien zur Mustererkennung
21 |
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Item Description: | Zugl.: Erlangen-Nürnberg, Univ., Diss., 2005 |
| Physical Description: | III, 216 S. Ill., graph. Darst. 210 mm x 145 mm |
| ISBN: | 3832511911 |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV021567971 | ||
| 003 | DE-604 | ||
| 005 | 20060504 | ||
| 007 | t | ||
| 008 | 060503s2006 gw ad|| m||| 00||| eng d | ||
| 015 | |a 06,N15,0620 |2 dnb | ||
| 016 | 7 | |a 978974255 |2 DE-101 | |
| 020 | |a 3832511911 |c Pb. : EUR 40.50, EUR 41.60 (AT), sfr 72.10 |9 3-8325-1191-1 | ||
| 024 | 3 | |a 9783832511913 | |
| 035 | |a (OCoLC)254711465 | ||
| 035 | |a (DE-599)BVBBV021567971 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 044 | |a gw |c XA-DE-BE | ||
| 049 | |a DE-29 |a DE-29T |a DE-91 | ||
| 084 | |a 610 |2 sdnb | ||
| 100 | 1 | |a Chrástek, Radim |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Automated retinal image analysis for glaucoma screening and vessel evaluation |c from Radim Chrástek |
| 264 | 1 | |a Berlin |b Logos-Verl. |c 2006 | |
| 300 | |a III, 216 S. |b Ill., graph. Darst. |c 210 mm x 145 mm | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Studien zur Mustererkennung |v 21 | |
| 500 | |a Zugl.: Erlangen-Nürnberg, Univ., Diss., 2005 | ||
| 650 | 4 | |a Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse | |
| 650 | 0 | 7 | |a Reihenuntersuchung |0 (DE-588)4277596-6 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Bildanalyse |0 (DE-588)4145391-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Netzhaut |0 (DE-588)4171512-3 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Glaukom |0 (DE-588)4021210-5 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Glaukom |0 (DE-588)4021210-5 |D s |
| 689 | 0 | 1 | |a Reihenuntersuchung |0 (DE-588)4277596-6 |D s |
| 689 | 0 | 2 | |a Netzhaut |0 (DE-588)4171512-3 |D s |
| 689 | 0 | 3 | |a Bildanalyse |0 (DE-588)4145391-8 |D s |
| 689 | 0 | |5 DE-604 | |
| 830 | 0 | |a Studien zur Mustererkennung |v 21 |w (DE-604)BV013645858 |9 21 | |
| 856 | 4 | 2 | |m HBZ Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=014783827&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-014783827 | ||
Record in the Search Index
| _version_ | 1804135332726177792 |
|---|---|
| adam_text | Titel: Automated retinal image analysis for glaucoma screening and vessel evaluation
Autor: Chrástek, Radim
Jahr: 2006
Contents
1 Introduction 1
1.1 Motivation 1
1.1.1 Glaucoma 1
1.1.2 Association between cardiovascular diseases and retinal microvascu-
lar abnormalities 3
1.2 Contribution to progress in science 5
1.3 Overview 6
2 Medical background and image data 9
2.1 Medical basics 9
2.1.1 Anatoray and physiology of the visual System 9
2.1.2 Methods of retina imaging 14
2.2 Glaucoma and its diagnostic methods 16
2.2.1 Types of glaucoma 17
2.2.2 Diagnostic methods 18
2.3 Retinal vessel evaluation 20
2.3.1 Method for evaluation of retinal vasculature 21
2.4 Scanning laser tomography (SLT) 23
2.5 Fundus photography 29
3 State-of-the-art 35
3.1 Automated approaches to the evaluation of the optic nerve head in glaucoma
diagnosis 35
3.2 General fundus image processing 38
3.2.1 Automatic image quality assessment 39
3.2.2 Correction of nonuniform illumination and contrast enhancement . 40
3.2.3 Processing of color Information 40
3.3 Optic nerve head localization and segmentation 41
3.3.1 Optic nerve head segmentation and localization in scanning laser
imaging 41
3.3.2 Optic nerve head localization in fundus photographs 42
3.3.3 Optic nerve head segmentation in fundus photographs 44
3.4 Methods of vessel segmentation 47
3.4.1 Retinal vessel segmentation 47
i
CONTENTS
ii
3.4.2 Calculation of retinal vessel width ^
3.4.3 Artery and vein classification ^
3.5 Concluding Remarks
53
4 optic nerve head segmentation in SLT images ^
4.1 Preprocessing: correction of nonuniform illumination ^
4 2 Rough localization of the optic nerve head ^
4 3 Constraining the search space for the potential contours
4.3.1 Estimation of the position and size of the neuroretinal rim ^
4 3.2 Detection of the neuroretinal rim
4.3.3 Detection of the Elschnig s scleral ring
4.3.4 Determination of border of the search space
4 4 Fine segmentation of the optic nerve head by anchored snakes
4.4.1 Active contour formulation
4.4.2 Numerical formulation
ol
4.4.3 Numerical solution .
4.4.4 Determination of anchor candidates
4.4.5 Final segmentation .
4.5 Multimodal approach
4.5.1 Registration
4.5.2 Optic nerve head segmentation in registered fundus photographs . .
9o
4.5.3 Multimodal segmentation
5 Results of optic nerve head segmentation
5.1 Optic nerve head segmentation ¦
5.2 Evaluation . . ¦ 10
j^ 5.2.1 Data sets for evaluation . • ¦
B 5.2.2 Comparison of overlapping areas . • •
¦ 5.2.3 Reproducibility of algorithm
f 5.2.4 Automated segmentation compared to interobserver variability of
manual segmentation
5.2.5 Radial distances between contours . • ¦
5.2.6 Error rates of registration and segmentation in fundus photographs
5.2.7 Comparing classification error rates
6 Calculation of artery-to-vein diameter ratio in fundus photographs 12
6.1 Preprocessing
125
6.2 Determination of parameters of measurement zones
125
6.2.1 Optic nerve head localization
197
6.2.2 Filtering region-of-interest and detecting significant edges
6.2.3 Determining zone parameters with Hough transform
6.3 Vessel segmentation ¦ *
6.3.1 Thresholding and correcting binary image
CONTENTS iii
6.3.2 Masking out macula and optic nerve head 138
6.3.3 Extracting vessel centerlines and characteristic points 139
6.3.4 Finding corresponding vessel borders 142
6.3.5 Vessel tree reconstruction 143
6.4 Vessel classification as arteries or veins 146
6.5 Calculation of artery-to-vein diameter ratio 147
7 Results of calculation of artery-to-vein diameter ratio 151
7.1 Calculation of artery-to-vein diameter ratio 151
7.2 Evaluation 151
7.2.1 Data sets for evaluation 151
7.2.2 Rough segmentation of the optic nerve head and macula 152
7.2.3 Evaluation of calculation of artery-to-vein diameter ratio 152
8 Discussion 157
8.1 Discussion on results of optic nerve head segmentation 157
8.2 Discussion on results of calculation of artery-to-vein diameter ratio .... 160
9 Summary and Outlook 163
9.1 Summary 163
9.2 Outlook 166
Bibliography 169
A Notation 189
B Layout of structure charts 193
C Inhaltsverzeichnis 195
D Einleitung 199
D.I Motivation 200
D.I.I Glaukom 200
D. 1.2 Zusammenhang zwischen kardiovaskularen Erkrankungen und retina-
len mikrovaskularen Abnormalitaten 202
D.2 Beitrag zum Fortschritt der Forschung 203
D.3 Obersicht 205
E Zusammenfassung 207
Index 213
List of Figures
1.1 Examination of the optic nerve head in scanning laser tomography 3
1.2 Workflow of computer-assisted retinal vessel evaluation 4
2.1 Basic eye anatomy 9
2.2 Outflow of aqueous humor 10
2.3 Layers and levels of the fundus 11
2.4 The main components of the fundus 12
2.5 Schematic anatomy of the optic nerve head 12
2.6 Optic nerve head structures shown in fundus photograph 13
2.7 Principles of the direct and indirect ophthalmoscope 15
2.8 Open angle glaucoma and angle closure glaucoma 17
2.9 Typical normal and glaucomatous appearance of the optic nerve head ... 19
2.10 Definition of measurement zones 22
2.11 An example of the scanning laser tomograph 24
2.12 Principle of the scanning laser tomography 24
2.13 Principle of computation of the topography of the light reflecting surface . 25
2.14 An example of the series of the 32 tomographic layers of the optic nerve head 25
2.15 Typical Heidelberg Retina Tomograph topographies and reflectivity images 26
2.16 The definition of the reference plane 26
2.17 Obtaining parameters with Heidelberg Retina Tomograph 27
2.18 An example of the fundus camera: NonMyd Alpha (Kowa) 29
2.19 Illumination system of the fundus camera 30
2.20 Detail of illumination system of the fundus camera 30
2.21 Observation system of the fundus camera 31
2.22 Illustrating the field of view for 45° and 20° 31
2.23 Example of the fundus photographs 32
2.24 Typical artifacts 32
4.1 Workflow in the scanning laser tomography 53
4.2 Flowchart of monomodal segmentation 55
4.3 Typical histograms of HRT(2) images 56
4.4 Binarization of unpreprocessed HRT image 56
4.5 Binarization of unpreprocessed HRT and HRT2 image 57
4.6 Binarization of HRT and HRT2 image preprocessed by histogram equalization 58
i
LIST OF FIGURES
ii
4.7 Binarization of HRT and HRT2 image preprocessed by adaptive histogram ^
equalization 60
4.8 Correction of nonuniform illumination gl
4.9 Correction of nonuniform illumination: results g2
4.10 Influence of the correction of nonuniform illumination on image histogram. ^
4.11 Calculation of the Euclidean distance map ^
4.12 Optic nerve head localization g5
4.13 Estimation of the position and size of the optic nerve head border ^
4.14 Selection of valid regions • ¦ ¦ ¦ ^
4.15 Circle detection by Hough transform
4.16 Constraining the search space for the potential contours by detecting ana- ^
totnical structures. . ¦ • •
4.1? Removing bright pixels inside the optic nerve head . ¦ •
4.18 Determination of border of the search space . . • ¦
4.19 Border of the search space for two constraints • • •
4.20 Search for pair of constraining circles with best concentricity ...••¦¦•
4.21 Meaning of indices used with anchored snakes • • ¦
4.22 Determination of anchor candidates • • •
4.23 Removing pixels outside the search space • • •
4.24 Anchored snakes . • •
4.25 Fine segmentation of the optic nerve head in an image with a very well
visible border ...•¦¦¦
4.26 Fine segmentation of the optic nerve head with a hardly identifiable border.
4.27 Difficulties with monomodal optic nerve head segmentation ..•••¦•¦
4.28 Registration of SLT images and fundus photographs ¦ ¦ •
4.29 Verification of registration • ¦ • •
4.30 Constraining the search space for segmentation of the optic nerve head m
fundus photograph. ...•¦••
4.31 Optic nerve head segmentation in fundus photograph ....••¦
4.32 Segmented contour from fundus photograph superimposed on SLT image .
4.33 Multimodal segmentation of the optic nerve head with elimination of blood
vessels . ....•¦• ^
4.34 Multiniodal segmentation of the optic nerve head with simplified determi¬
nation of anchor candidates ¦ • •
5.1 Examples of monomodftl segmentation for images of the field of view 10° x 10° 102
5.2 Examples of monomodal segmentation for images of the field of view 20° x 20°. 102
5.3 Examples of monomodal and multimodal segmentation • • •
5.4 Illustration to the comparison criterion • • • 1(^
5.5 Calculating number of overlapping and non-overlapping pixels ....¦¦• 107
5.6 Ex»mple of evaluation of reproducibility for one image group • ¦ ¦ 109
5.7 The angle dependent relative segmentation errors for the Augsburg study . I13
5.8 The angle dependent relative segmentation errors for the A4 study ll3
LIST OF FIGURES iii
5.9 The angle dependent relative segmentation errors for the variability study . 115
5.10 The angle dependent standard deviation of relative segmentation errors for
the variability study 116
5.11 Examples of failed registration and successful automatic check 117
5.12 Examples of failed segmentation in registered fundus photographs 118
5.13 Predefined sectors of the Heidelberg Retina Tomograph 118
5.14 Example of global and sector dependent parameters of the Heidelberg Retina
Tomograph 119
6.1 Cropping relevant parts of image 124
6.2 Optic nerve head localization by detecting maximum gray values 126
6.3 Localization of the optic nerve head 127
6.4 Nonlinear image filtering with mean field annealing optimization 132
6.5 Filtering region-of-interest and refining localization 133
6.6 Computing edge image and applying Hough transform 134
6.7 Determination of measurement zone parameters 135
6.8 Correcting nonuniform illumination 137
6.9 Thresholding and correcting binary image 138
6.10 Correction of central light reflex 138
6.11 Constraining the search space for macula detection 140
6.12 Macula detection 140
6.13 Masking out the macula and the optic nerve head 141
6.14 Extracting vessel centerlines and characteristic points 141
6.15 Principle of finding corresponding vessel borders 143
6.16 Corresponding vessel borders 143
6.17 Corresponding vessel borders in detail 144
6.18 Reconstruction of a vessel tree: detail 145
6.19 Reconstruction of a vessel tree 146
6.20 Segmenting veins in red channel 146
6.21 Identification of veins in red channel 147
6.22 Vessel classification 148
6.23 Classified vessels as arteries or veins superimposed on green channel .... 148
6.24 Calculation of artery-to-vein diameter ratio 149
7.1 Example of a very good automated suggestions of the vessel classification. . 155
7.2 Example of a wrong vessel classification 156
D.I Untersuchung des optischen Sehnervenkopfes in der ScanningLaserTomo-
graphie 201
D.2 Ablauf der rechnergestiitzten Evaluation der retinalen Gefafce 203
1
List of Tables
2.1 Technical specifications of the Heidelberg Retina Tomograph 28
2.2 Technical specifications of the fundus cameras CR6-45NM and NonMyd Alpha. 31
4.1 Parameters of the anchored snakes 87
5.1 Data sets for evaluation 104
5.2 Results of comparison of overlapping areas 108
5.3 Results of evaluation of reproducibility 109
5.4 Mean true positive for variability study 110
5.5 Mean false positive for variability study 110
5.6 Mean segmentation rate for variability study 110
5.7 The mean absolute and relative errors and their deviations for the Augsburg
and A4 studies 114
5.8 The mean absolute and relative errors and their deviations for the variability
study 114
5.9 Influence of registration and segmentation in fundus photographs on final
results 116
5.10 Classification error rates: .632+ estimator for LDA, SLDA, CTREE and
BAGGING 120
5.11 Meaning of terms connected to sensitivity and specificity 121
5.12 Estimated classification rates for LDA, CTREE and bagging 121
6.1 Parameters of weak membrane model and mean field annealing optimization 131
7.1 Optic nerve head and macula segmentation error rate 152
7.2 Absolute and relative errors and standard deviations of AVR calculation . 153
7.3 Statistical evaluation of manual corrections 154
7.4 Vessel characteristics 154
i
|
| adam_txt |
Titel: Automated retinal image analysis for glaucoma screening and vessel evaluation
Autor: Chrástek, Radim
Jahr: 2006
Contents
1 Introduction 1
1.1 Motivation 1
1.1.1 Glaucoma 1
1.1.2 Association between cardiovascular diseases and retinal microvascu-
lar abnormalities 3
1.2 Contribution to progress in science 5
1.3 Overview 6
2 Medical background and image data 9
2.1 Medical basics 9
2.1.1 Anatoray and physiology of the visual System 9
2.1.2 Methods of retina imaging 14
2.2 Glaucoma and its diagnostic methods 16
2.2.1 Types of glaucoma 17
2.2.2 Diagnostic methods 18
2.3 Retinal vessel evaluation 20
2.3.1 Method for evaluation of retinal vasculature 21
2.4 Scanning laser tomography (SLT) 23
2.5 Fundus photography 29
3 State-of-the-art 35
3.1 Automated approaches to the evaluation of the optic nerve head in glaucoma
diagnosis 35
3.2 General fundus image processing 38
3.2.1 Automatic image quality assessment 39
3.2.2 Correction of nonuniform illumination and contrast enhancement . 40
3.2.3 Processing of color Information 40
3.3 Optic nerve head localization and segmentation 41
3.3.1 Optic nerve head segmentation and localization in scanning laser
imaging 41
3.3.2 Optic nerve head localization in fundus photographs 42
3.3.3 Optic nerve head segmentation in fundus photographs 44
3.4 Methods of vessel segmentation 47
3.4.1 Retinal vessel segmentation 47
i
CONTENTS
ii
3.4.2 Calculation of retinal vessel width ^
3.4.3 Artery and vein classification ^
3.5 Concluding Remarks
53
4 optic nerve head segmentation in SLT images ^
4.1 Preprocessing: correction of nonuniform illumination ^
4 2 Rough localization of the optic nerve head ^
4 3 Constraining the search space for the potential contours
4.3.1 Estimation of the position and size of the neuroretinal rim ^
4 3.2 Detection of the neuroretinal rim
4.3.3 Detection of the Elschnig's scleral ring
4.3.4 Determination of border of the search space
4 4 Fine segmentation of the optic nerve head by anchored snakes
4.4.1 Active contour formulation
4.4.2 Numerical formulation
ol
4.4.3 Numerical solution .
4.4.4 Determination of anchor candidates
4.4.5 Final segmentation .
4.5 Multimodal approach
4.5.1 Registration
4.5.2 Optic nerve head segmentation in registered fundus photographs . .
9o
4.5.3 Multimodal segmentation
5 Results of optic nerve head segmentation
5.1 Optic nerve head segmentation ¦
5.2 Evaluation . . ¦ 10
j^ 5.2.1 Data sets for evaluation . • ¦
B 5.2.2 Comparison of overlapping areas . • •
¦ 5.2.3 Reproducibility of algorithm
f 5.2.4 Automated segmentation compared to interobserver variability of
manual segmentation
5.2.5 Radial distances between contours . • ¦
5.2.6 Error rates of registration and segmentation in fundus photographs
5.2.7 Comparing classification error rates
6 Calculation of artery-to-vein diameter ratio in fundus photographs 12
6.1 Preprocessing
125
6.2 Determination of parameters of measurement zones
125
6.2.1 Optic nerve head localization
197
6.2.2 Filtering region-of-interest and detecting significant edges
6.2.3 Determining zone parameters with Hough transform
6.3 Vessel segmentation ¦ *
6.3.1 Thresholding and correcting binary image
CONTENTS iii
6.3.2 Masking out macula and optic nerve head 138
6.3.3 Extracting vessel centerlines and characteristic points 139
6.3.4 Finding corresponding vessel borders 142
6.3.5 Vessel tree reconstruction 143
6.4 Vessel classification as arteries or veins 146
6.5 Calculation of artery-to-vein diameter ratio 147
7 Results of calculation of artery-to-vein diameter ratio 151
7.1 Calculation of artery-to-vein diameter ratio 151
7.2 Evaluation 151
7.2.1 Data sets for evaluation 151
7.2.2 Rough segmentation of the optic nerve head and macula 152
7.2.3 Evaluation of calculation of artery-to-vein diameter ratio 152
8 Discussion 157
8.1 Discussion on results of optic nerve head segmentation 157
8.2 Discussion on results of calculation of artery-to-vein diameter ratio . 160
9 Summary and Outlook 163
9.1 Summary 163
9.2 Outlook 166
Bibliography 169
A Notation 189
B Layout of structure charts 193
C Inhaltsverzeichnis 195
D Einleitung 199
D.I Motivation 200
D.I.I Glaukom 200
D. 1.2 Zusammenhang zwischen kardiovaskularen Erkrankungen und retina-
len mikrovaskularen Abnormalitaten 202
D.2 Beitrag zum Fortschritt der Forschung 203
D.3 Obersicht 205
E Zusammenfassung 207
Index 213
List of Figures
1.1 Examination of the optic nerve head in scanning laser tomography 3
1.2 Workflow of computer-assisted retinal vessel evaluation 4
2.1 Basic eye anatomy 9
2.2 Outflow of aqueous humor 10
2.3 Layers and levels of the fundus 11
2.4 The main components of the fundus 12
2.5 Schematic anatomy of the optic nerve head 12
2.6 Optic nerve head structures shown in fundus photograph 13
2.7 Principles of the direct and indirect ophthalmoscope 15
2.8 Open angle glaucoma and angle closure glaucoma 17
2.9 Typical normal and glaucomatous appearance of the optic nerve head . 19
2.10 Definition of measurement zones 22
2.11 An example of the scanning laser tomograph 24
2.12 Principle of the scanning laser tomography 24
2.13 Principle of computation of the topography of the light reflecting surface . 25
2.14 An example of the series of the 32 tomographic layers of the optic nerve head 25
2.15 Typical Heidelberg Retina Tomograph topographies and reflectivity images 26
2.16 The definition of the reference plane 26
2.17 Obtaining parameters with Heidelberg Retina Tomograph 27
2.18 An example of the fundus camera: NonMyd Alpha (Kowa) 29
2.19 Illumination system of the fundus camera 30
2.20 Detail of illumination system of the fundus camera 30
2.21 Observation system of the fundus camera 31
2.22 Illustrating the field of view for 45° and 20° 31
2.23 Example of the fundus photographs 32
2.24 Typical artifacts 32
4.1 Workflow in the scanning laser tomography 53
4.2 Flowchart of monomodal segmentation 55
4.3 Typical histograms of HRT(2) images 56
4.4 Binarization of unpreprocessed HRT image 56
4.5 Binarization of unpreprocessed HRT and HRT2 image 57
4.6 Binarization of HRT and HRT2 image preprocessed by histogram equalization 58
i
LIST OF FIGURES
ii
4.7 Binarization of HRT and HRT2 image preprocessed by adaptive histogram ^
equalization 60
4.8 Correction of nonuniform illumination gl
4.9 Correction of nonuniform illumination: results g2
4.10 Influence of the correction of nonuniform illumination on image histogram. ^
4.11 Calculation of the Euclidean distance map ^
4.12 Optic nerve head localization g5
4.13 Estimation of the position and size of the optic nerve head border ^
4.14 Selection of valid regions • ¦ ¦ ¦ ^
4.15 Circle detection by Hough transform
4.16 Constraining the search space for the potential contours by detecting ana- ^
totnical structures. . ¦ • •
4.1? Removing bright pixels inside the optic nerve head . ¦ •
4.18 Determination of border of the search space . . • ¦
4.19 Border of the search space for two constraints • • •
4.20 Search for pair of constraining circles with best concentricity .••¦¦•
4.21 Meaning of indices used with anchored snakes • • ¦
4.22 Determination of anchor candidates • • •
4.23 Removing pixels outside the search space • • •
4.24 Anchored snakes . • •
4.25 Fine segmentation of the optic nerve head in an image with a very well
visible border .•¦¦¦
4.26 Fine segmentation of the optic nerve head with a hardly identifiable border.
4.27 Difficulties with monomodal optic nerve head segmentation .•••¦•¦'
4.28 Registration of SLT images and fundus photographs ¦ ¦ • '
4.29 Verification of registration • ¦ • •
4.30 Constraining the search space for segmentation of the optic nerve head m
fundus photograph. .•¦••
4.31 Optic nerve head segmentation in fundus photograph .••¦
4.32 Segmented contour from fundus photograph superimposed on SLT image .
4.33 Multimodal segmentation of the optic nerve head with elimination of blood
vessels . .•¦• ^
4.34 Multiniodal segmentation of the optic nerve head with simplified determi¬
nation of anchor candidates ¦ • •
5.1 Examples of monomodftl segmentation for images of the field of view 10° x 10° 102
5.2 Examples of monomodal segmentation for images of the field of view 20° x 20°. 102
5.3 Examples of monomodal and multimodal segmentation • • •
5.4 Illustration to the comparison criterion • • • 1(^
5.5 Calculating number of overlapping and non-overlapping pixels .¦¦• 107
5.6 Ex»mple of evaluation of reproducibility for one image group • ¦ ¦ 109
5.7 The angle dependent relative segmentation errors for the Augsburg study . I13
5.8 The angle dependent relative segmentation errors for the A4 study ll3
LIST OF FIGURES iii
5.9 The angle dependent relative segmentation errors for the variability study . 115
5.10 The angle dependent standard deviation of relative segmentation errors for
the variability study 116
5.11 Examples of failed registration and successful automatic check 117
5.12 Examples of failed segmentation in registered fundus photographs 118
5.13 Predefined sectors of the Heidelberg Retina Tomograph 118
5.14 Example of global and sector dependent parameters of the Heidelberg Retina
Tomograph 119
6.1 Cropping relevant parts of image 124
6.2 Optic nerve head localization by detecting maximum gray values 126
6.3 Localization of the optic nerve head 127
6.4 Nonlinear image filtering with mean field annealing optimization 132
6.5 Filtering region-of-interest and refining localization 133
6.6 Computing edge image and applying Hough transform 134
6.7 Determination of measurement zone parameters 135
6.8 Correcting nonuniform illumination 137
6.9 Thresholding and correcting binary image 138
6.10 Correction of central light reflex 138
6.11 Constraining the search space for macula detection 140
6.12 Macula detection 140
6.13 Masking out the macula and the optic nerve head 141
6.14 Extracting vessel centerlines and characteristic points 141
6.15 Principle of finding corresponding vessel borders 143
6.16 Corresponding vessel borders 143
6.17 Corresponding vessel borders in detail 144
6.18 Reconstruction of a vessel tree: detail 145
6.19 Reconstruction of a vessel tree 146
6.20 Segmenting veins in red channel 146
6.21 Identification of veins in red channel 147
6.22 Vessel classification 148
6.23 Classified vessels as arteries or veins superimposed on green channel . 148
6.24 Calculation of artery-to-vein diameter ratio 149
7.1 Example of a very good automated suggestions of the vessel classification. . 155
7.2 Example of a wrong vessel classification 156
D.I Untersuchung des optischen Sehnervenkopfes in der ScanningLaserTomo-
graphie 201
D.2 Ablauf der rechnergestiitzten Evaluation der retinalen Gefafce 203
1
List of Tables
2.1 Technical specifications of the Heidelberg Retina Tomograph 28
2.2 Technical specifications of the fundus cameras CR6-45NM and NonMyd Alpha. 31
4.1 Parameters of the anchored snakes 87
5.1 Data sets for evaluation 104
5.2 Results of comparison of overlapping areas 108
5.3 Results of evaluation of reproducibility 109
5.4 Mean true positive for variability study 110
5.5 Mean false positive for variability study 110
5.6 Mean segmentation rate for variability study 110
5.7 The mean absolute and relative errors and their deviations for the Augsburg
and A4 studies 114
5.8 The mean absolute and relative errors and their deviations for the variability
study 114
5.9 Influence of registration and segmentation in fundus photographs on final
results 116
5.10 Classification error rates: .632+ estimator for LDA, SLDA, CTREE and
BAGGING 120
5.11 Meaning of terms connected to sensitivity and specificity 121
5.12 Estimated classification rates for LDA, CTREE and bagging 121
6.1 Parameters of weak membrane model and mean field annealing optimization 131
7.1 Optic nerve head and macula segmentation error rate 152
7.2 Absolute and relative errors and standard deviations of AVR calculation . 153
7.3 Statistical evaluation of manual corrections 154
7.4 Vessel characteristics 154
i |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Chrástek, Radim |
| author_facet | Chrástek, Radim |
| author_role | aut |
| author_sort | Chrástek, Radim |
| author_variant | r c rc |
| building | Verbundindex |
| bvnumber | BV021567971 |
| ctrlnum | (OCoLC)254711465 (DE-599)BVBBV021567971 |
| discipline | Medizin |
| discipline_str_mv | Medizin |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02019nam a2200493 cb4500</leader><controlfield tag="001">BV021567971</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20060504 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">060503s2006 gw ad|| m||| 00||| eng d</controlfield><datafield tag="015" ind1=" " ind2=" "><subfield code="a">06,N15,0620</subfield><subfield code="2">dnb</subfield></datafield><datafield tag="016" ind1="7" ind2=" "><subfield code="a">978974255</subfield><subfield code="2">DE-101</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">3832511911</subfield><subfield code="c">Pb. : EUR 40.50, EUR 41.60 (AT), sfr 72.10</subfield><subfield code="9">3-8325-1191-1</subfield></datafield><datafield tag="024" ind1="3" ind2=" "><subfield code="a">9783832511913</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)254711465</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV021567971</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">gw</subfield><subfield code="c">XA-DE-BE</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-29</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-91</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">610</subfield><subfield code="2">sdnb</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chrástek, Radim</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automated retinal image analysis for glaucoma screening and vessel evaluation</subfield><subfield code="c">from Radim Chrástek</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Berlin</subfield><subfield code="b">Logos-Verl.</subfield><subfield code="c">2006</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">III, 216 S.</subfield><subfield code="b">Ill., graph. Darst.</subfield><subfield code="c">210 mm x 145 mm</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Studien zur Mustererkennung</subfield><subfield code="v">21</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Zugl.: Erlangen-Nürnberg, Univ., Diss., 2005</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Reihenuntersuchung</subfield><subfield code="0">(DE-588)4277596-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Bildanalyse</subfield><subfield code="0">(DE-588)4145391-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Netzhaut</subfield><subfield code="0">(DE-588)4171512-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Glaukom</subfield><subfield code="0">(DE-588)4021210-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Glaukom</subfield><subfield code="0">(DE-588)4021210-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Reihenuntersuchung</subfield><subfield code="0">(DE-588)4277596-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Netzhaut</subfield><subfield code="0">(DE-588)4171512-3</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="3"><subfield code="a">Bildanalyse</subfield><subfield code="0">(DE-588)4145391-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Studien zur Mustererkennung</subfield><subfield code="v">21</subfield><subfield code="w">(DE-604)BV013645858</subfield><subfield code="9">21</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">HBZ Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=014783827&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-014783827</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV021567971 |
| illustrated | Illustrated |
| index_date | 2024-07-02T14:37:14Z |
| indexdate | 2024-07-09T20:38:50Z |
| institution | BVB |
| isbn | 3832511911 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-014783827 |
| oclc_num | 254711465 |
| open_access_boolean | |
| owner | DE-29 DE-29T DE-91 DE-BY-TUM |
| owner_facet | DE-29 DE-29T DE-91 DE-BY-TUM |
| physical | III, 216 S. Ill., graph. Darst. 210 mm x 145 mm |
| publishDate | 2006 |
| publishDateSearch | 2006 |
| publishDateSort | 2006 |
| publisher | Logos-Verl. |
| record_format | marc |
| series | Studien zur Mustererkennung |
| series2 | Studien zur Mustererkennung |
| spelling | Chrástek, Radim Verfasser aut Automated retinal image analysis for glaucoma screening and vessel evaluation from Radim Chrástek Berlin Logos-Verl. 2006 III, 216 S. Ill., graph. Darst. 210 mm x 145 mm txt rdacontent n rdamedia nc rdacarrier Studien zur Mustererkennung 21 Zugl.: Erlangen-Nürnberg, Univ., Diss., 2005 Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse Reihenuntersuchung (DE-588)4277596-6 gnd rswk-swf Bildanalyse (DE-588)4145391-8 gnd rswk-swf Netzhaut (DE-588)4171512-3 gnd rswk-swf Glaukom (DE-588)4021210-5 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Glaukom (DE-588)4021210-5 s Reihenuntersuchung (DE-588)4277596-6 s Netzhaut (DE-588)4171512-3 s Bildanalyse (DE-588)4145391-8 s DE-604 Studien zur Mustererkennung 21 (DE-604)BV013645858 21 HBZ Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=014783827&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Chrástek, Radim Automated retinal image analysis for glaucoma screening and vessel evaluation Studien zur Mustererkennung Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse Reihenuntersuchung (DE-588)4277596-6 gnd Bildanalyse (DE-588)4145391-8 gnd Netzhaut (DE-588)4171512-3 gnd Glaukom (DE-588)4021210-5 gnd |
| subject_GND | (DE-588)4277596-6 (DE-588)4145391-8 (DE-588)4171512-3 (DE-588)4021210-5 (DE-588)4113937-9 |
| title | Automated retinal image analysis for glaucoma screening and vessel evaluation |
| title_auth | Automated retinal image analysis for glaucoma screening and vessel evaluation |
| title_exact_search | Automated retinal image analysis for glaucoma screening and vessel evaluation |
| title_exact_search_txtP | Automated retinal image analysis for glaucoma screening and vessel evaluation |
| title_full | Automated retinal image analysis for glaucoma screening and vessel evaluation from Radim Chrástek |
| title_fullStr | Automated retinal image analysis for glaucoma screening and vessel evaluation from Radim Chrástek |
| title_full_unstemmed | Automated retinal image analysis for glaucoma screening and vessel evaluation from Radim Chrástek |
| title_short | Automated retinal image analysis for glaucoma screening and vessel evaluation |
| title_sort | automated retinal image analysis for glaucoma screening and vessel evaluation |
| topic | Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse Reihenuntersuchung (DE-588)4277596-6 gnd Bildanalyse (DE-588)4145391-8 gnd Netzhaut (DE-588)4171512-3 gnd Glaukom (DE-588)4021210-5 gnd |
| topic_facet | Glaukom - Reihenuntersuchung - Netzhaut - Bildanalyse Reihenuntersuchung Bildanalyse Netzhaut Glaukom Hochschulschrift |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=014783827&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| volume_link | (DE-604)BV013645858 |
| work_keys_str_mv | AT chrastekradim automatedretinalimageanalysisforglaucomascreeningandvesselevaluation |