Level Set Method in Medical Imaging Segmentation

Level set methods are numerical techniques which offer remarkably powerful tools for understanding, analyzing, and computing interface motion in a host of settings. When used for medical imaging analysis and segmentation, the function assigns a label to each pixel or voxel and optimality is defined based on desired imaging properties. This often includes a detection step to extract specific objects via segmentation. This allows for the segmentation and analysis problem to be formulated and solved in a principled way based on well-established mathematical theories. Level set method is a great tool for modeling time varying medical images and enhancement of numerical computations.

Ayman El-Baz is a University Scholar and Chair, Bioengineering Department at the University of Louisville, KY. He has over 15 years of hands-on experience in the fields of bio-imaging modeling and non-invasive computer-assisted diagnostic systems. He has developed new techniques for the accurate identification of probability mixtures for segmenting multi-modal images, new probability models, and model-based algorithms for recognizing lung nodules and blood vessels in magnetic resonance and computer tomography imaging systems, as well as new registration techniques based on multiple second-order signal statistics, all of which have been reported at multiple international conferences and journal articles. His work related to novel image analysis techniques for autism, dyslexia, and lung cancer has earned multiple awards including the Walter H. Coulter Foundation Early Career in Biomedical Engineering and a Research Scholar Grant from the American Cancer Society. He has authored or coauthored more than 300 technical articles (87 journals, 9 books, 39 book chapters, 144 refereed-conference papers, 74 abstracts published in proceedings and 12 US patents). Jasjit S. Suri is Chairman of Global Biomedical Technologies, Inc. Roseville, CA. He has spent over 30 years in the fields of biomedical engineering/sciences, software and hardware engineering and its management. He has developed products and worked extensively in the areas of breast, mammography, orthopedics (spine), neurology (brain), angiography, urology and image guided surgery. Dr. Suri has over 100 US/European Patents, 20 Trademarks, 35 books and over 550 peer reviewed articles. He is a Fellow of AIMBE (American Institute of Medical and Biological Engineering).

A Survey on Deformable Models and their Applications to Medical Imaging. Level Set Method for Image Segmentation: A Survey. A Survey for Region-based Level Set Image Segmentation. Deformable Models in Medical Image Analysis. A Fast Level Set Method for Propagating Interfaces. Shape-Specific Adaptations for Level-Set Deformable Model-Based Segmentation. Image Segmentation Using Deformable Models. An Adaptive Level Set Method for Medical Image Segmentation. Level Set Methods and Their Applications in Image Science. Image Segmentation Techniques. A Survey of Digital Image Segmentation Algorithms. State-of-the-Art of Level Set Methods in Segmentation and Registration of Medical Imaging Modalities. Deformable Models in Medical Image Analysis: A Survey. Neighbor-Constrained Segmentation with Level Set 3-D Deformable Models. A Shape Based Approach to the Segmentation of Medical Imagery Using Level Sets. Image Registration via Level Set Motion: Applications to Atlas-Based Segmentation. GIST: An Interactive, GPU-Based Level Set Segmentation Tool for 3D Medical Images. Level Set Based Segmentation using Data-Driven Shape Prior on Feature Histograms. Level Set Based Cerebral Vasculature Segmentation and Diameter Quantification in CT Angiography. A Multiresolution Stochastic Level Set Method for Mumford-Shah Image Segmentation. On the incorporation of Shape Priors into Geometric Active Contours. A Novel NMF Guided Level-Set for DWI Prostate Segmentation. Image Segmentation with a Parametric Deformable Model using Shape and Appearance Priors. Shape Appearance Guided Level Set Deformable Model for Image Segmentation.