Deformable Surface Models in Medical Image Analysis

Surface extraction from noisy volumetric images is a common task in medical image analysis. Due to noise, the use of prior information about surface topology and shape is necessary to automate the surface extraction. Deformable surface models can incorporate such geometric knowledge into the extraction process which is restated as an energy minimization problem. A drawback of deformable models is that the formulated minimization problem is difficult to solve because of numerous local minima and a large number of variables. This difficulty may lead to sensitivity to the initialization, complicating the unsupervised use of deformable models. This book offers a concise review on deformable surface methods concentrating on the ways to solve the initialization sensitivity problem. Particularly, global optimization methods to solve the energy minimization problem and applications of these to surface extraction from positron emission tomography images are presented. The book is intended to readers working in the field of medical image analysis. The book includes original publications by the author describing the global optimization approach to deformable surfaces in detail.

Autorentext

Jussi Tohka, PhD, is a senior researcher at the Department of Signal Processing, Tampere University of Technology, Finland. His research interests include image analysis and pattern recognition within brain imaging, particularly using energy minimization based techniques.