Automatic detection and segmentation of ground glass opacity nodules Conference Paper
| Authors: | Zhou, J.; Chang, S.; Metaxas, D. N.; Zhao, B.; Schwartz, L. H.; Ginsberg, M. S. |
| Title: | Automatic detection and segmentation of ground glass opacity nodules |
| Conference Title: | 9th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2006 |
| Abstract: | Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (nonsolid) 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 inter- or 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-NN whose distance measure is the Euclidean distance between the nonparametric density estimates of two examples. The detected GGO region is then automatically segmented by analyzing the 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 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. © Springer-Verlag Berlin Heidelberg 2006. |
| Keywords: | image analysis; lung cancer; computerized tomography; tumors; lung; blood vessels; image segmentation; statistical methods; pulmonary diseases; ground glass opacity (ggo); edge detection; euclidean distance |
| Journal Title | Lecture Notes in Computer Science |
| Volume: | 4190 |
| Conference Dates: | 2006 Oct 1-6 |
| Conference Location: | Copenhagen, Denmark |
| ISBN: | 0302-9743 |
| Publisher: | Springer |
| Date Published: | 2006-10-01 |
| Start Page: | 784 |
| End Page: | 791 |
| Language: | English |
| PROVIDER: | scopus |
| PUBMED: | 17354962 |
| DOI/URL: | |
| Notes: | Chapter in "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2006" (ISBN: 978-3-540-44707-8) -- "Conference code: 68371" - "Cited By (since 1996): 7" - "Export Date: 4 June 2012" - "Sponsors: AstraZeneca; Center for Clinical and Basic Research; Claron; Elsevier; GE" - "Source: Scopus" |
Citation Impact
Related MSK Work