Case study: an evaluation of user-assisted hierarchical watershed segmentation

Joshua E. Cates, Ross T. Whitaker, Greg M. Jones
2005 Medical Image Analysis  
While level sets have demonstrated a great potential for 3D medical image segmentation, their usefulness has been limited by two problems. First, 3D level sets are relatively slow to compute. Second, their formulation usually entails several free parameters which can be very difficult to correctly tune for specific applications. The second problem is compounded by the first. This paper describes a new tool for 3D segmentation that addresses these problems by computing level-set surface models
more » ... interactive rates. This tool employs two important, novel technologies. First is the mapping of a 3D level-set solver onto a commodity graphics card (GPU). This mapping relies on a novel mechanism for GPU memory management. The interactive rates level-set PDE solver give the user immediate feedback on the parameter settings, and thus users can tune free parameters and control the shape of the model in real time. The second technology is the use of region-based speed functions, which allow a user to quickly and intuitively specify the behavior of the deformable model. We have found that the combination of these interactive tools enables users to produce good, reliable segmentations. To support this observation, this paper presents qualitative results from several different datasets as well as a quantitative evaluation from a study of brain tumor segmentations. Abstract. This paper evaluates the effectiveness of an interactive, three-dimensional image segmentation technique that relies on watersheds. This paper presents two user-based case studies, which include two different groups of domain experts. Subjects manipulate a graphics-based front end to a hierarchy of segmented regions generated from a watershed segmentation algorithm, which is implemented in the Insight Toolkit. In the first study, medical students segment several different anatomical structures from the Visible Human Female head and neck color cryosection data. In the second study, radiologists use the interactive tool to produce models of brain tumors from MRI data. This paper presents a quantitative and qualitative comparison against hand contouring and another semi-automatic technique based on deformable models. To quantify accuracy, we estimate ground truth from the hand-contouring data using the Simultaneous Truth and Performance Estimation algorithm. We also apply metrics from the literature to estimate precision and efficiency. The watershed segmentation technique showed improved subject interaction times and increased intersubject precision over hand contouring, with quality that is visually and statistically comparable. The watershed results also compare favorably to results using the deformable models. The analysis also identifies some failures in the watershed technique, where edges were poorly defined in the data, and noted a trend in the hand-contouring results toward systematically larger segmentations, which raises questions about the wisdom of using expert segmentations to define ground truth.
doi:10.1016/j.media.2005.04.007 pmid:15919233 fatcat:lso2xh7qwrewnohk3jomp5nodm