PRIOR KNOWLEDGE FOR TARGETED OBJECTS SEGMENTATION IN MEDICAL IMAGES
Medical image segmentation (MIS), partitioning an image into meaningful parts, is an important step toward automating medical image analysis and is at the crux of a variety of medical imaging applications, such as computer aided diagnosis, therapy planning and delivery, and computer aided interventions. However, existence of noise, low contrast and objects' complexity in medical images are important barriers that keep us away from an ideal segmentation system. Incorporating prior knowledge into image segmentation algorithms has proven useful for obtaining more accurate and plausible results on targeted objects segmentation.
This report surveys different types of prior knowledge that are utilized in different segmentation frameworks for targeted object segmentation. Here, we mostly focus on optimization-based methods that incorporate prior information into their framework. We review and compare these methods in terms of types of utilized prior, domain of action (continuous vs. discrete) and optimization techniques (convex vs. non-convex).
Ph.D. Examining Committee:
Dr. Ghassan Hamarneh, Senior Supervisor
Dr. Greg Mori, Co-Sr. Supervisor
Dr. Brian Funt, Examiner