A directional distance aided method for medical image segmentation

Medical Physics
Feng ZhugeSandy Napel

Abstract

A challenging problem in image segmentation is preventing boundary leakage through poorly resolved edges because not enough local information can be provided along them. In this article, we propose a new directional distance aided image segmentation method, formulated under the level set framework, to prevent the leakage. At each evolution step, the zero level set is extracted and smoothed. For each point on the zero level set, a new directional distance (DD) term, defined as the vector starting from itself and pointing to its counterpart on the smoothed version of the zero level set, is calculated to measure its "degree of protrusion." The evolution speed of the points that are considered to be protruding out will be penalized. Other terms, e.g., curvature and gradient terms and user specified constraints, are used along with the DD term to influence the level set evolution. Our smoothing technique augments traditional Gaussian smoothing with a new antishrinkage operation. The novelty of our method is that the DD term does not depend on intensity or gradient boundaries to regulate the regional shape and, therefore, help prevent leakage and the method incorporates vertex-based curve/surface smoothing into curve evolution under ...Continue Reading

References

Jul 18, 1995·Proceedings of the National Academy of Sciences of the United States of America·R Malladi, J A Sethian
Sep 3, 1996·Proceedings of the National Academy of Sciences of the United States of America·R Malladi, J A Sethian
Apr 1, 1997·IEEE Transactions on Medical Imaging·A YezziA Tannenbaum
Jan 11, 2000·IEEE Transactions on Medical Imaging·X ZengJ S Duncan
Aug 10, 2001·IEEE Engineering in Medicine and Biology Magazine : the Quarterly Magazine of the Engineering in Medicine & Biology Society·J S Suri
Aug 29, 2001·Medical Image Analysis·C BaillardC Barillot
Aug 29, 2001·Medical Image Analysis·L M LorigoC F Westin
Apr 9, 2002·IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society·Jasjit S SuriLaura Reden
Sep 21, 2004·IEEE Transactions on Pattern Analysis and Machine Intelligence·Nikos ParagiosVisvanathan Ramesh
Sep 21, 2004·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·Ulrich ClarenzMartin Rumpf
Nov 16, 2004·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·Debora Gil, Petia Radeva
Feb 6, 2008·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·T F Chan, L A Vese
Feb 16, 2008·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·C Xu, J L Prince
Feb 16, 2008·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·K SiddiqiS W Zucker
Jan 1, 1986·IEEE Transactions on Pattern Analysis and Machine Intelligence·J BabaudR O Duda
May 1, 1986·IEEE Transactions on Pattern Analysis and Machine Intelligence·B K Horn, E J Weldon

❮ Previous
Next ❯

Citations

Nov 4, 2008·Medical Physics·Samuel G Armato, Bram van Ginneken

❮ Previous
Next ❯

Related Concepts

Related Feeds

Aneurysm

Aneurysms are outward distensions or bulges that occurs in a weakened wall of blood vessels. Discover the latest research on aneurysms here.

Aortic Aneurysm

An aortic aneurysm is the weakening and bulging of the blood vessel wall in the aorta. This causes dilatation of the aorta, which is usually asymptomatic but carries the risk of rupture and hemorrhage. Find the latest research on aortic aneurysms here.

Cardiac Aneurysm

Aneurysm refers to a bulge of the wall or lining of a vessel commonly occurring in the blood vessels at the base of the septum or within the aorta. In the heart, it usually arises from a patch of weakened tissue in a ventricular wall, which swells into a bubble filled with blood. Discover the latest research on cardiac aneurysm here.