A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes

Gurman Gill; Christian Bauer; Reinhard R Beichel

doi:10.1118/1.4894817

Back

A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes

Journal article

Open access

Peer reviewed

A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes

Gurman Gill, Christian Bauer and Reinhard R Beichel

Medical physics (Lancaster), Vol.41(10), pp.101908-n/a

10/2014

DOI: 10.1118/1.4894817

PMCID: PMC4965110

PMID: 25281960

Files and links (1)

url

https://doi.org/10.1118/1.4894817View

Published (Version of record) Open Access

Abstract

The automated correct segmentation of left and right lungs is a nontrivial problem, because the tissue layer between both lungs can be quite thin. In the case of lung segmentation with left and right lung models, overlapping segmentations can occur. In this paper, the authors address this issue and propose a solution for a model-based lung segmentation method. The thin tissue layer between left and right lungs is detected by means of a classification approach and utilized to selectively modify the cost function of the lung segmentation method. The approach was evaluated on a diverse set of 212 CT scans of normal and diseased lungs. Performance was assessed by utilizing an independent reference standard and by means of comparison to the standard segmentation method without overlap avoidance. For cases where the standard approach produced overlapping segmentations, the proposed method significantly (p = 1.65 × 10(-9)) reduced the overlap by 97.13% on average (median: 99.96%). In addition, segmentation accuracy assessed with the Dice coefficient showed a statistically significant improvement (p = 7.5 × 10(-5)) and was 0.9845 ± 0.0111. For cases where the standard approach did not produce an overlap, performance of the proposed method was not found to be significantly different. The proposed method improves the quality of the lung segmentations, which is important for subsequent quantitative analysis steps.

Algorithms

Asthma - diagnostic imaging

Humans

Lung - diagnostic imaging

Models, Biological

Pattern Recognition, Automated - methods

Pulmonary Disease, Chronic Obstructive - diagnostic imaging

Respiration

Tomography, X-Ray Computed - methods

Details

Title: Subtitle: A method for avoiding overlap of left and right lungs in shape model guided segmentation of lungs in CT volumes
Creators: Gurman Gill - University of Iowa
Christian Bauer - University of Iowa
Reinhard R Beichel - University of Iowa
Resource Type: Journal article
Publication Details: Medical physics (Lancaster), Vol.41(10), pp.101908-n/a
DOI: 10.1118/1.4894817
PMID: 25281960
PMCID: PMC4965110
NLM abbreviation: Med Phys
ISSN: 0094-2405
eISSN: 2473-4209
Grant note: R01HL111453 / NHLBI NIH HHS R01 HL111453 / NHLBI NIH HHS
Language: English
Date published: 10/2014
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197073102771

Metrics

31 Record Views

8 Times Cited - Web of Science