Multi-scale Opening of Conjoined Structures with Shared Intensities: Methods and Applications

S Basu; M. L Raghavan; E. A Hoffman; P. K Saha

doi:10.1109/ICBMI.2011.69

Back

Conference proceeding

Multi-scale Opening of Conjoined Structures with Shared Intensities: Methods and Applications

S Basu, M. L Raghavan, E. A Hoffman and P. K Saha

2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation, pp.128-131

12/2011

DOI: 10.1109/ICBMI.2011.69

View Online

Abstract

We describe a new theory and algorithm for separating two structures sharing a common intensity band and conjoined at different unknown locations and scales. The method is applied for segmenting vasculature in patients with intracranial aneurysms via CT angiography (CTA). Major challenges in segmenting vasculature are related to separation of vessels and aneurysms from bone in the shared intensity space, especially, at regions with mutual tight coupling. The segmentation for bone and vessels combines fuzzy distance transform (FDT), a morphologic function with a topologic fuzzy connectivity to iteratively open two objects starting at large scales and progressing toward smaller scales. The accuracy of the method has been examined both qualitatively and quantitatively on (1) mathematically generated phantoms, (2) CT images of a pig pulmonary vessel cast phantom, and (3) cerebral CT angiography images of human subjects.

Algorithm design and analysis

Aneurysm

Angiography

Bones

Computed tomography

Computed Tomography Angiography (CTA)

fuzzy connectivity

Fuzzy Distance Transform (FDT)

Image segmentation

Imaging phantoms

morphology

multi-scale opening

Details

Title: Subtitle: Multi-scale Opening of Conjoined Structures with Shared Intensities: Methods and Applications
Creators: S Basu - Jadavpur University
M. L Raghavan - University of Iowa
E. A Hoffman - University of Iowa
P. K Saha - University of Iowa
Resource Type: Conference proceeding
Publication Details: 2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation, pp.128-131
DOI: 10.1109/ICBMI.2011.69
Publisher: IEEE
Language: English
Date published: 12/2011
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Internal Medicine
Record Identifier: 9984196982102771

Metrics

33 Record Views