Atjaunināt sīkdatņu piekrišanu

E-grāmata: Automated Image Detection of Retinal Pathology [Taylor & Francis e-book]

(University of Waikato, Hamilton, New Zealand), (Medical University of Vienna, Austria)
  • Formāts: 393 pages, 21 Tables, black and white; 22 Illustrations, color; 37 Illustrations, black and white
  • Izdošanas datums: 09-Oct-2009
  • Izdevniecība: CRC Press Inc
  • ISBN-13: 9780429124372
  • Taylor & Francis e-book
  • Cena: 293,49 €*
  • * this price gives unlimited concurrent access for unlimited time
  • Standarta cena: 419,27 €
  • Ietaupiet 30%
  • Formāts: 393 pages, 21 Tables, black and white; 22 Illustrations, color; 37 Illustrations, black and white
  • Izdošanas datums: 09-Oct-2009
  • Izdevniecība: CRC Press Inc
  • ISBN-13: 9780429124372
Discusses the Effect of Automated Assessment Programs on Health Care Provision

Diabetes is approaching pandemic numbers, and as an associated complication, diabetic retinopathy is also on the rise. Much about the computer-based diagnosis of this intricate illness has been discovered and proven effective in research labs. But, unfortunately, many of these advances have subsequently failed during transition from the lab to the clinic. So what is the best way to diagnose and treat retinopathy? Automated Image Detection of Retinal Pathology discusses the epidemiology of the disease, proper screening protocols, algorithm development, image processing, and feature analysis applied to the retina.

Conveys the Need for Widely Implemented Risk-Reduction Programs

Offering an array of informative examples, this book analyzes the use of automated computer techniques, such as pattern recognition, in analyzing retinal images and detecting diabetic retinopathy and its progression as well as other retinal-based diseases. It also addresses the benefits and challenges of automated health care in the field of ophthalmology. The book then details the increasing practice of telemedicine screening and other advanced applications including arteriolar-venous ratio, which has been shown to be an early indicator of cardiovascular, diabetes, and cerebrovascular risk.

Although tremendous advances have been made in this complex field, there are still many questions that remain unanswered. This book is a valuable resource for researchers looking to take retinal pathology to that next level of discovery as well as for clinicians and primary health care professionals that aim to utilize automated diagnostics as part of their health care program.
Preface xiii
Contributors xvii
Introduction
1(26)
H. F. Jelinek
M. J. Cree
Why Automated Image Detection of Retinal Pathology?
1(6)
The general clinical need
2(1)
Diabetes: A global problem
2(1)
Diabetic retinopathy
2(1)
Eye-screening for diabetic retinopathy
3(2)
Other retinal pathologies
5(1)
The retina as an indicator for disease elsewhere
6(1)
Research needs in automated retinopathy detection
6(1)
The engineering opportunity
7(1)
Automated Assessment of Retinal Eye Disease
7(6)
Automated microaneurysm detection in diabetic retinopathy
8(1)
Hemorrhages
9(1)
White lesion segmentation
9(1)
Localization of important markers
10(1)
Retinal vessel diameter changes in disease
11(1)
Retinal blood vessel segmentation
11(1)
Mathematical analysis of vessel patterns
12(1)
The Contribution of This Book
13(14)
Diabetic Retinopathy and Public Health
27(40)
D. Worsley
D. Simmons
Introduction
27(1)
The Pandemic of Diabetes and Its Complications
28(1)
Retinal Structure and Function
29(6)
Definition and Description
35(5)
Classification of Diabetic Retinopathy
40(1)
Differential Diagnosis of Diabetic Retinopathy
40(2)
Systemic Associations of Diabetic Retinopathy
42(1)
Duration of diabetes
42(1)
Type of diabetes
42(1)
Blood glucose control
42(1)
Blood pressure
42(1)
Serum lipids
43(1)
Renal disease
43(1)
Anemia
43(1)
Pregnancy
43(1)
Smoking
43(1)
Pathogenesis
43(2)
Hyperglycemia
43(1)
Hematological abnormalities
44(1)
Leukostasis and inflammation
44(1)
Growth factors
44(1)
Neurodegeneration
45(1)
Treatment
45(3)
Management of systemic associations
45(1)
Ocular treatments
45(1)
Investigational treatments
46(2)
Screening
48(7)
Methods of screening
48(6)
Frequency of screening
54(1)
Cost effectiveness of screening
54(1)
Access to care and screening
54(1)
Conclusion
55(12)
Detecting Retinal Pathology Automatically with Special Emphasis on Diabetic Retinopathy
67(12)
M. D. Abramoff
M. Niemeijer
Historical Aside
67(1)
Approaches to Computer (Aided) Diagnosis
68(2)
Detection of Diabetic Retinopathy Lesions
70(1)
Detection of Lesions and Segmentation of Retinal Anatomy
71(1)
Detection and Staging of Diabetic Retinopathy: Pixel to Patient
71(1)
Directions for Research
72(7)
Finding a Role for Computer-Aided Early Diagnosis of Diabetic Retinopathy
79(42)
L. B. Backlund
Mass Examinations of Eyes in Diabetes
79(3)
Motive for accurate early diagnosis of retinopathy
80(1)
Definition of screening
81(1)
Practical importance of the concept of screening
81(1)
Coverage and timely re-examination
81(1)
Developing and Defending a Risk Reduction Program
82(2)
Explaining why retinopathy is suitable for screening
82(1)
Understanding reasons for possible criticism
83(1)
Fulfilling criteria for screening tests
83(1)
Setting quality assurance standards
84(1)
Training and assessment
84(1)
Assessing Accuracy of a Diagnostic Test
84(6)
Predictive value, estimation, power
85(2)
Receiver operating characteristic curve
87(2)
Area under curve
89(1)
Covariates
90(1)
Improving Detection of Diabetic Retinopathy
90(3)
Improving work environment
91(1)
Going digital
91(1)
Obtaining clear images
91(1)
Avoiding loss of information
92(1)
Viewing images
92(1)
Ensuring accurate grading
93(1)
Organizing for success
93(1)
Measuring Outcomes of Risk Reduction Programs
93(3)
Reducing new blindness and visual impairment
94(1)
Counting people who lost vision
94(1)
Understanding the importance of visual impairment
95(1)
User Experiences of Computer-Aided Diagnosis
96(7)
Perceived accuracy of lesion detection
97(4)
Finding and reading evaluations of software for retinopathy diagnosis
101(1)
Opportunities and challenges for programmers
102(1)
Planning a Study to Evaluate Accuracy
103(7)
Getting help from a statistician
103(1)
Choosing a measurement scale
103(1)
Optimizing design
104(4)
Carrying out different phases of research
108(1)
An example from another field
109(1)
Conclusion
110(10)
Measures of Binary Test Performance
120(1)
Retinal Markers for Early Detection of Eye Disease
121(34)
A. Osareh
Abstract
121(1)
Introduction
122(1)
Nonproliferative Diabetic Retinopathy
123(1)
Chapter Overview
124(4)
Related Works on Identification of Retinal Exudates and the Optic Disc
128(4)
Exudate identification and classification
128(2)
Optic disc detection
130(2)
Preprocessing
132(2)
Pixel-Level Exudate Recognition
134(3)
Application of Pixel-Level Exudate Recognition on the Whole Retinal Image
137(2)
Locating the Optic Disc in Retinal Images
139(9)
Template matching
141(1)
Color morphology preprocessing
141(3)
Accurate localization of the optic disc-based snakes
144(2)
Optic disc localization results
146(2)
Conclusion
148(7)
Automated Microaneurysm Detection for Screening
155(30)
M. J. Cree
Characteristics of Microaneurysms and Dot-Hemorrhages
155(1)
History of Automated Microaneurysm Detection
156(9)
Early morphological approaches
156(1)
The ``standard approach'' to automated microaneurysm detection
157(2)
Extensions of the standard approach
159(3)
Other approaches
162(2)
General red lesion detection
164(1)
Microaneurysm Detection in Color Retinal Images
165(2)
The Waikato Automated Microaneurysm Detector
167(5)
Further comments on the use of color
171(1)
Issues for Microaneurysm Detection
172(5)
Image quality assessment
172(1)
Image compression implications
173(2)
Optic disc detection
175(1)
Meaningful comparisons of implementations
175(2)
Research Application of Microaneurysm Detection
177(1)
Conclusion
178(7)
Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases
185(36)
N. Cheung
T. Y. Wong
L. Hodgson
Introduction
185(1)
Early Description of Retinal Vascular Changes
186(1)
Retinal Vascular Imaging
187(2)
Assessment of retinal vascular signs from retinal photographs
187(1)
Limitations in current retinal vascular imaging techniques
187(2)
Retinal Vascular Changes and Cardiovascular Disease
189(5)
Hypertension
189(2)
Stroke and cerebrovascular disease
191(2)
Coronary heart disease and congestive heart failure
193(1)
Retinal Vascular Changes and Metabolic Diseases
194(3)
Diabetes mellitus
196(1)
The metabolic syndrome
196(1)
Overweight and obesity
197(1)
Retinal Vascular Changes and Other Systemic Diseases
197(3)
Renal disease
197(1)
Atherosclerosis
198(1)
Inflammation and endothelial dysfunction
198(2)
Subclinical cardiac morphology
200(1)
Genetic Associations of Retinal Vascular Changes
200(1)
Conclusion
201(1)
Retinal Vessel Caliber Grading Protocol
201(20)
Grading an image
202(2)
Example of the grading process
204(1)
Obtaining results
205(1)
Saving data
206(15)
Segmentation of Retinal Vasculature Using Wavelets and Supervised Classification: Theory and Implementation
221(48)
J. V. B. Soares
R. M. Cesar Jr.
Introduction
221(3)
Theoretical Background
224(11)
The 1-D CWT
224(1)
The 2-D CWT
225(3)
The 2-D Gabor wavelet
228(1)
Supervised classification
229(2)
Bayesian decision theory
231(1)
Bayesian Gaussian mixture model classifier
231(2)
k-nearest neighbor classifier
233(1)
Linear minimum squared error classifier
234(1)
Segmentation Using the 2-D Gabor Wavelet and Supervised Classification
235(10)
Preprocessing
235(2)
2-D Gabor wavelet features
237(1)
Feature normalization
238(1)
Supervised pixel classification
239(1)
Public image databases
240(1)
Experiments and settings
241(1)
ROC analysis
242(3)
Implementation and Graphical User Interface
245(4)
Overview
245(1)
Installation
246(1)
Command line interface
246(1)
Graphical user interface
247(2)
Experimental Results
249(9)
Conclusion
258(11)
Summary
258(1)
Future work
258(11)
Determining Retinal Vessel Widths and Detection of Width Changes
269(36)
K. H. Fritzsche
C. V. Stewart
B. Roysam
Identifying Blood Vessels
270(1)
Vessel Models
270(1)
Vessel Extraction Methods
271(1)
Can's Vessel Extraction Algorithm
271(5)
Improving Can's algorithm
272(3)
Limitations of the modified Can algorithm
275(1)
Measuring Vessel Width
276(2)
Precise Boundary Detection
278(1)
Continuous Vessel Models with Spline-Based Ribbons
279(9)
Spline representation of vessels
279(5)
B-spline ribbons
284(4)
Estimation of Vessel Boundaries Using Snakes
288(6)
Snakes
288(1)
Ribbon snakes
289(1)
B-spline ribbon snake
289(3)
Cross section-based B-spline snakes
292(1)
B-spline ribbon snakes comparison
293(1)
Vessel Width Change Detection
294(4)
Methodology
294(2)
Change detection via hypothesis test
296(2)
Summary
298(1)
Conclusion
298(7)
Geometrical and Topological Analysis of Vascular Branches from Fundus Retinal Images
305(34)
N. W. Witt
M. E. Martinez-Perez
K. H. Parker
S. A. Thom
A. D. Hughes
Introduction
305(1)
Geometry of Vessel Segments and Bifurcations
306(6)
Arterial to venous diameter ratio
306(2)
Bifurcation geometry
308(3)
Vessel length to diameter ratios
311(1)
Tortuosity
312(1)
Vessel Diameter Measurements from Retinal Images
312(3)
The half-height method
313(1)
Double Gaussian fitting
314(1)
The sliding linear regression filter (SLRF)
314(1)
Clinical Findings from Retinal Vascular Geometry
315(3)
Topology of the Vascular Tree
318(5)
Strahler branching ratio
321(1)
Path length
321(1)
Number of edges
321(1)
Tree asymmetry index
322(1)
Automated Segmentation and Analysis of Retinal Fundus Images
323(5)
Feature extraction
324(2)
Region growing
326(1)
Analysis of binary images
327(1)
Clinical Findings from Retinal Vascular Topology
328(1)
Conclusion
329(10)
Tele-Diabetic Retinopathy Screening and Image-Based Clinical Decision Support
339(12)
K. Yogesan
F. Reinholz
I. J. Constable
Introduction
339(1)
Telemedicine
339(5)
Image capture
340(1)
Image resolution
341(1)
Image transmission
342(1)
Image compression
342(2)
Telemedicine Screening for Diabetic Retinopathy
344(2)
Image-Based Clinical Decision Support Systems
346(1)
Conclusion
347(4)
Index 351
Herbert Jelinek, Charles Stuart University, Albury, New South Wales, Australia

Michael J. Cree, University of Waikato, Hamilton, New Zealand