Optimal surface segmentation in volumetric images--a graph-theoretic approach

Kang Li; Xiaodong Wu; Danny Z Chen; Milan Sonka

doi:10.1109/TPAMI.2006.19

Back

Optimal surface segmentation in volumetric images--a graph-theoretic approach

Journal article

Open access

Optimal surface segmentation in volumetric images--a graph-theoretic approach

Kang Li, Xiaodong Wu, Danny Z Chen and Milan Sonka

IEEE transactions on pattern analysis and machine intelligence, Vol.28(1), pp.119-134

01/2006

DOI: 10.1109/TPAMI.2006.19

PMCID: PMC2646122

PMID: 16402624

Files and links (1)

url

http://doi.org/10.1109/TPAMI.2006.19View

Open Access

Abstract

Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s-t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.

Algorithms

Reproducibility of Results

Artificial Intelligence

Humans

Sensitivity and Specificity

Imaging, Three-Dimensional - methods

Radiographic Image Enhancement - methods

Tomography, X-Ray Computed - methods

Lung - diagnostic imaging

Pattern Recognition, Automated - methods

Details

Title: Subtitle: Optimal surface segmentation in volumetric images--a graph-theoretic approach
Creators: Kang Li - Department of Electrical and Computer Engineering, Carnegie Mellon University, 4106 NSH, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. kangl@cmu.edu
Xiaodong Wu
Danny Z Chen
Milan Sonka
Resource Type: Journal article
Publication Details: IEEE transactions on pattern analysis and machine intelligence, Vol.28(1), pp.119-134
DOI: 10.1109/TPAMI.2006.19
PMID: 16402624
PMCID: PMC2646122
NLM abbreviation: IEEE Trans Pattern Anal Mach Intell
ISSN: 0162-8828
eISSN: 1939-3539
Publisher: United States
Grant note: R01 EB004640 / NIBIB NIH HHS R01 HL064368-03 / NHLBI NIH HHS R01 HL063373-02 / NHLBI NIH HHS R01 HL071809-04 / NHLBI NIH HHS R01-HL64368 / NHLBI NIH HHS R01 HL064368-05 / NHLBI NIH HHS R01 EB004640-01A2 / NIBIB NIH HHS R01 HL063373-07 / NHLBI NIH HHS R01 HL064368-06A1 / NHLBI NIH HHS R01 HL064368-08 / NHLBI NIH HHS R01 HL064368-02 / NHLBI NIH HHS R01 HL063373-05A1 / NHLBI NIH HHS R01 HL071809 / NHLBI NIH HHS R01 HL064368-07 / NHLBI NIH HHS R01 HL064368-04 / NHLBI NIH HHS R01 HL064368-03S1 / NHLBI NIH HHS R01 HL063373-04 / NHLBI NIH HHS R01 HL071809-02 / NHLBI NIH HHS R01 EB004640-03 / NIBIB NIH HHS R01 HL063373 / NHLBI NIH HHS R01 HL063373-01 / NHLBI NIH HHS R01 HL064368 / NHLBI NIH HHS R01 HL064368-09 / NHLBI NIH HHS R01 HL063373-03 / NHLBI NIH HHS R01 EB004640-02 / NIBIB NIH HHS R01 HL064368-01 / NHLBI NIH HHS R01 HL071809-01A1 / NHLBI NIH HHS R01 HL071809-03 / NHLBI NIH HHS R01 HL063373-06 / NHLBI NIH HHS
Language: English
Date published: 01/2006
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984046800902771

Metrics

21 Record Views

542 Times Cited - Web of Science