Multiscale Opening of Conjoined Fuzzy Objects: Theory and Applications

Punam K Saha; Subhadip Basu; Eric A Hoffman

doi:10.1109/TFUZZ.2015.2502278

Back

Multiscale Opening of Conjoined Fuzzy Objects: Theory and Applications

Journal article

Peer reviewed

Multiscale Opening of Conjoined Fuzzy Objects: Theory and Applications

Punam K Saha, Subhadip Basu and Eric A Hoffman

IEEE transactions on fuzzy systems, Vol.24(5), pp.1121-1133

10/2016

DOI: 10.1109/TFUZZ.2015.2502278

PMCID: PMC5116813

PMID: 27885318

Files and links (1)

url

http://doi.org/10.1109/TFUZZ.2015.2502278View

Open Access

Abstract

Theoretical properties of a multiscale opening algorithm for two conjoined fuzzy objects are established, and its extension to separating two conjoined fuzzy objects with different intensity properties is introduced. In addition, its applications to artery/vein separation in pulmonary CT imaging and carotid vessel segmentation in CT angiograms (CTAs) of patients with intracranial aneurysms are presented. The new algorithm accounts for distinct intensity properties of individual conjoined objects by combining fuzzy distance transform, a morphologic feature, with fuzzy connectivity, a topologic feature. The algorithm iteratively opens the two conjoined objects starting at large scales and progressing toward finer scales. Results of application of the method in separating arteries and veins in a physical cast phantom of a pig lung are presented. Accuracy of the algorithm is quantitatively evaluated in terms of sensitivity and specificity on patients' CTA datasets, and its performance is compared with existing methods. Reproducibility of the algorithm is examined in terms of volumetric agreement between two users' carotid vessel segmentation results. Experimental results using this algorithm on patients' CTA data demonstrate a high average accuracy of 96.3% with 95.1% sensitivity and 97.5% specificity and a high reproducibility of 94.2% average agreement between segmentation results from two mutually independent users. Approximately, 25-35 user-specified seeds/separators are needed for each CTA data through a custom-designed graphical interface requiring an average of 30 min to complete carotid vascular segmentation in a patient's CTA dataset.

Algorithm design and analysis

carotid vasculature

fuzzy connectivity

Heuristic algorithms

morphology

Aneurysm

pulmonary vasculature

CT angiogram (CTA)

Arteries

Image segmentation

Computed tomography

multiscale opening (MSO)

fuzzy distance transform (FDT)

Details

Title: Subtitle: Multiscale Opening of Conjoined Fuzzy Objects: Theory and Applications
Creators: Punam K Saha - Department of Electrical and Computer Engineering and the Department of Radiology, University of Iowa, Iowa City, IA, USA
Subhadip Basu - University of Iowa, Iowa City, IA, USA
Eric A Hoffman - Department of Radiology and the Department of Biomedical Engineering, University of Iowa, Iowa City, IA, USA
Resource Type: Journal article
Publication Details: IEEE transactions on fuzzy systems, Vol.24(5), pp.1121-1133
DOI: 10.1109/TFUZZ.2015.2502278
PMID: 27885318
PMCID: PMC5116813
NLM abbreviation: IEEE Trans Fuzzy Syst
ISSN: 1063-6706
eISSN: 1941-0034
Publisher: IEEE
Grant note: Government of India R01-AR054439; R01-HL112986 / National Institutes of Health (10.13039/100000002) SR/BY/E-15/09 / BOYSCAST SR/FTP/ETA-04/2012 / FASTTRACK Department of Science and Technology (10.13039/501100006143)
Language: English
Date published: 10/2016
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Internal Medicine
Record Identifier: 9984051516902771

Metrics

19 Record Views

15 Times Cited - Web of Science