An automatic method for ground glass opacity nodule detection and segmentation from CT studies

Jinghao Zhou, Sukmoon Chang, Dimitris N. Metaxas, Binsheng Zhao, Michelle S. Ginsberg, Lawrence H. Schwartz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (non-solid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and interor intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting K-Nearest Neighbor (K-NN), whose distance measure is the Euclidean distance between the nonparametric density estimates of two regions. The detected GGO region is then automatically segmented by analyzing the 3D texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for automatic GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO.

Original languageEnglish (US)
Title of host publication28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
Pages3062-3065
Number of pages4
DOIs
StatePublished - Dec 1 2006
Event28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 - New York, NY, United States
Duration: Aug 30 2006Sep 3 2006

Publication series

NameAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
ISSN (Print)0589-1019

Other

Other28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06
CountryUnited States
CityNew York, NY
Period8/30/069/3/06

Fingerprint

Opacity
Glass
Thorax
Classifiers
Cone-Beam Computed Tomography
Observer Variation
Lung Neoplasms
Textures
Lung

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Zhou, J., Chang, S., Metaxas, D. N., Zhao, B., Ginsberg, M. S., & Schwartz, L. H. (2006). An automatic method for ground glass opacity nodule detection and segmentation from CT studies. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06 (pp. 3062-3065). [4030078] (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings). https://doi.org/10.1109/IEMBS.2006.260285
Zhou, Jinghao ; Chang, Sukmoon ; Metaxas, Dimitris N. ; Zhao, Binsheng ; Ginsberg, Michelle S. ; Schwartz, Lawrence H. / An automatic method for ground glass opacity nodule detection and segmentation from CT studies. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. pp. 3062-3065 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).
@inproceedings{f0423976d20541d8a2b9bed636808f5d,
title = "An automatic method for ground glass opacity nodule detection and segmentation from CT studies",
abstract = "Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (non-solid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and interor intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting K-Nearest Neighbor (K-NN), whose distance measure is the Euclidean distance between the nonparametric density estimates of two regions. The detected GGO region is then automatically segmented by analyzing the 3D texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for automatic GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO.",
author = "Jinghao Zhou and Sukmoon Chang and Metaxas, {Dimitris N.} and Binsheng Zhao and Ginsberg, {Michelle S.} and Schwartz, {Lawrence H.}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/IEMBS.2006.260285",
language = "English (US)",
isbn = "1424400325",
series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
pages = "3062--3065",
booktitle = "28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06",

}

Zhou, J, Chang, S, Metaxas, DN, Zhao, B, Ginsberg, MS & Schwartz, LH 2006, An automatic method for ground glass opacity nodule detection and segmentation from CT studies. in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06., 4030078, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pp. 3062-3065, 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06, New York, NY, United States, 8/30/06. https://doi.org/10.1109/IEMBS.2006.260285

An automatic method for ground glass opacity nodule detection and segmentation from CT studies. / Zhou, Jinghao; Chang, Sukmoon; Metaxas, Dimitris N.; Zhao, Binsheng; Ginsberg, Michelle S.; Schwartz, Lawrence H.

28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 3062-3065 4030078 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An automatic method for ground glass opacity nodule detection and segmentation from CT studies

AU - Zhou, Jinghao

AU - Chang, Sukmoon

AU - Metaxas, Dimitris N.

AU - Zhao, Binsheng

AU - Ginsberg, Michelle S.

AU - Schwartz, Lawrence H.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (non-solid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and interor intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting K-Nearest Neighbor (K-NN), whose distance measure is the Euclidean distance between the nonparametric density estimates of two regions. The detected GGO region is then automatically segmented by analyzing the 3D texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for automatic GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO.

AB - Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (non-solid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and interor intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting K-Nearest Neighbor (K-NN), whose distance measure is the Euclidean distance between the nonparametric density estimates of two regions. The detected GGO region is then automatically segmented by analyzing the 3D texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for automatic GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO.

UR - http://www.scopus.com/inward/record.url?scp=34047146116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047146116&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2006.260285

DO - 10.1109/IEMBS.2006.260285

M3 - Conference contribution

SN - 1424400325

SN - 9781424400324

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 3062

EP - 3065

BT - 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06

ER -

Zhou J, Chang S, Metaxas DN, Zhao B, Ginsberg MS, Schwartz LH. An automatic method for ground glass opacity nodule detection and segmentation from CT studies. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'06. 2006. p. 3062-3065. 4030078. (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings). https://doi.org/10.1109/IEMBS.2006.260285