Extraction of Medial Tracks via Height Ridges MIDAG - Medical Image Display and Analysis Group
Introduction
Both slabs and tubes can be extracted by locating cores, i.e., height ridges of a graded measure of medial strength that we call "medialness" (Fig. 5). Height ridges are subdimensional maxima and fall into two categories: maximal convexity ridges and optimal parameter ridges, which differ according to the rule used for choosing the subspace in which the medialness maximum is checked for. Subdimensional saddles connect height ridges when they stop, forming "connectors". This work involves singularity theoretic study of height ridges [Damon, Miller, Keller] as well as algorithmic development of height ridge extractors [Fritsch, Aylward, Furst, Fridman]. 
wireframe image of the m-rep model matching the m-rep model against a dataset
Fig. 1. Left: Tree of blood vessels and aneurysm extracted from magnetic resonance angiogram via height ridges (Aylward, Bullitt). Right: Core (red), with connectors (yellow) for a blood vessel in a (2D) x-ray angiogram (Furst, Fridman).
 
Project Links
 
Bibliography

Pizer S, K Siddiqi, G Székely, J Damon, S Zucker (2001). Multiscale Medial Loci and their Properties. IJCV Special UNC-MIDAG issue, to appear.

Furst J and S Pizer (2001). Marching Ridges. IASTED International Conference on Signal and Image Processing, 22-26.

Furst J and S Pizer (2001). Shape Analysis of Objects in 3D Images. 5th World Multiconference on Systemics, Cybernetics and Informatics, SCI 2001, 6:289-292.

Furst J and S Pizer, "Optimal Parameter Ridges." to appear, Journal of Visual Communication and Image Representation.

Furst JD, SM Pizer (1998). Marching optimal-parameter ridges: an algorithm to extract shape loci in 3D images. In WM Wells, A Colchester, S Delp, eds., Medical Image Computing and Computer-Assisted Intervention- MICCAI '98. Lecture Notes in Computer Science 1496: 780-787, Springer, New York.

Pizer SM, Fritsch, DS, Low, KC, Furst, JD (1998). 2D & 3D figural models of anatomic objects from medical images. Mathematical Morphology and Its Applications to Image Processing, HJAM Heijmans, JBTM Roerdink, eds. (invited paper, Proc. ISMM '98), Kluwer Computational Imaging and Vision Series: 139-150. TR#98-005.

Furst J, RS Keller, JE Miller, SM Pizer (1997). Image loci are ridges in geometric spaces. University of North Carolia at Chapel Hill Department of Computer Science technical report number 96-046. Scale-Space Theory in Computer Vision, Lecture Notes in Computer Science. Springer 1252:176-187

Furst JD, SM Pizer, DH Eberly (1996). Marching cores: a method for extracting cores from 3D medical images. University of North Carolina Computer Science Department technical report TR96-003. Proc. Conf. Mathematical Methods in Biomedical Image Analysis, IEEE Catalog #96TB100056:124-130.

Pizer SM, D Eberly, BS Morse, D Fritsch (1995). Zoom-Invariant Vision of Figural Shape: The Mathematics of Cores. University of North Carolina technical report TR96-004. Computer Vision and ImageUnderstanding, 69:55-71, 1998.

Morse, BS, SM Pizer, DT Puff, C Gu (1995). Zoom-invariant vision of figural shape: effects on cores of image disturbances. University of North Carolina technical report TR96-005. Computer Vision and Image Understanding, 69:72-86, 1998.

Fritsch DS, D Eberly, SM Pizer, MJ McAuliffe (1994). Stimulated Cores and their Applications in Medical Imaging. University of North Carolina at Chapel Hill Department of Radiation Oncology technical report. Information Processing in Medical Imaging 1995 (IPMI'95) 365-368.

Furst J and S Pizer. Marching Ridges. IASTED International Conference on Signal and Image Processing, Hawaii, August 2001. 22-26.

Stetten GD, RN Landesman, Pizer SM (1997). "Core-Atoms and the spectra of scale," SPIE Medical Imaging Conference, Feb., 1997, 3034(2):642-652., also Technical Report TR97-006, University of North Carolina, Department of Computer Science.

Liu A, SM Pizer, D Eberly, B Morse, J Rosenman, E Chaney, E Bullitt, V Carrasco (1994). Volume registration using the 3D core.Visualization in Biomedical Computing '94 SPIE 2659:217-226.

Furst JD, SM Pizer, DH Eberly (1996). Marching cores: a method for extracting cores from 3D medical images. University of North Carolina Computer Science Department technical report TR96-003. Proc. Conf. Mathematical Methods in Biomedical Image Analysis, IEEE Catalog #96TB100056:124-130.

McAuliffe M, D Eberly, DS Fritsch, EL Chaney, SM Pizer (1996). Scale-space boundary evolution initialized by cores. Proc. Visualization in Biomedical Computing, KH Höhne, R Kikinis, eds. Lecture Notes in Computer Science, Springer, 1131:173-182.

Fritsch DS, EL Chaney, A Boxwala, MJ McAuliffe, S Raghavan, A Thall, JRD Earnhart (1995). Core-based portal image registration for automatic radiotherapy treatment verification. International Journal of Radiation, Oncology, Biology, Physics.; special issue on Conformal Therapy, 33(5):1287-1300, 1995.

Puff DT, D Eberly, SM Pizer (1994). Object-based interpolation via cores. Medical Imaging '94: Image Processing, SPIE 2167:143-150.

Burbeck CA, SM Pizer (1994). Object representation by cores: identifying and representing primitive spatial regions. University of North Carolina Computer Science Department technical report TR94-048. Vision Research, 35(13):1917-1930, 1995.

Fritsch DS, SM Pizer, EL Chaney, A Liu, S Raghavan, T Shah (1994). Cores for image registration",Proc. SPIE Medical Imaging '94: Image Processing, 2167, 128-142, 1994.

Pizer SM, CA Burbeck (1994). Cores as the basis for object vision in medical images. Proc. SPIE Medical Imaging '94: Image Perception, Modeling the Human Observer, 2166:191-198, 1994.