ABSTRACT
Kenneth H. Fritzsche, Ali Can, Hong Shen, Chia-Ling Tsai, James N. Turner, Howard L. Tanenbaum, Charles V. Stewart, and Badrinath Roysam
CONTENTS 6.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .225 6.2 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .226 6.3 Retinal Imaging Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .233 6.4 Models for Detecting Retinal Vasculature in Digital Imagery . . . . . .235 6.5 Vessel Extraction Approaches . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .246 6.6 RPI-Trace . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .256 6.7 Algorithm Design Considerations for Real-Time Tracing . . . . . . . . . .261 6.8 Accurate Extraction of Vessel Bifurcations and Crossovers . . . . . . . .267 6.9 Applications of Vessel Segmentation Data . . . . . . . . . . . . . . . . . . . . . . . . . .275 6.10 Implementation Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .275 6.11 Experimental Validation Using Ground Truth Data . . . . . . . . . . . . . . . .277 6.12 Experimental Analysis of Model and Settings for RPI-Trace . . . . . . .284 6.13 Experimental Assessment of the Impact of Landmark
Refinement with the ERPR Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .286 6.14 Chapter Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .288 Acknowledgments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .289 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .290
Quantitative morphometry of the retinal vasculature is of widespread interest, directly for ophthalmology and indirectly for diseases involving structural and/or functional changes of the body vasculature. Key points such as bifurcations and crossovers are of special interest to developmental biologists
and clinicians examining conditions such as hypertension and diabetes. Segmentation/tracings of the retinal vasculature and the key points, such as bifurcations and crossovers, are also important as spatial landmarks for image registration. Image registration, in turn, has direct applications to change detection, mosaic synthesis, real-time tracking, and real-time spatial referencing. Change detection is important for supporting a variety of clinical trials, high-volume reading centers, and for large-scale screening applications.
