Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies

Li Zhang; Ming Fang; David P. Naidich M.D.; Carol L. Novak

doi:10.1117/12.536259

12 May 2004 Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies

Li Zhang, Ming Fang, David P. Naidich M.D., Carol L. Novak

Proceedings Volume 5370, Medical Imaging 2004: Image Processing; (2004) https://doi.org/10.1117/12.536259
Event: Medical Imaging 2004, 2004, San Diego, California, United States

Abstract

Ground glass nodules (GGNs) have proved especially problematic in lung cancer diagnosis, as despite frequently being malignant they characteristically have extremely slow rates of growth. This problem is further magnified by the small size of many of these lesions now being routinely detected following the introduction of multislice CT scanners capable of acquiring contiguous high resolution 1 to 1.25 mm sections throughout the thorax in a single breathhold period. Although segmentation of solid nodules can be used clinically to determine volume doubling times quantitatively, reliable methods for segmentation of pure ground glass nodules have yet to be introduced. Our purpose is to evaluate a newly developed computer-based segmentation method for rapid and reproducible measurements of pure ground glass nodules. 23 pure or mixed ground glass nodules were identified in a total of 8 patients by a radiologist and subsequently segmented by our computer-based method using Markov random field and shape analysis. The computer-based segmentation was initialized by a click point. Methodological consistency was assessed using the overlap ratio between 3 segmentations initialized by 3 different click points for each nodule. The 95% confidence interval on the mean of the overlap ratios proved to be [0.984, 0.998]. The computer-based method failed on two nodules that were difficult to segment even manually either due to especially low contrast or markedly irregular margins. While achieving consistent manual segmentation of ground glass nodules has proven problematic most often due to indistinct boundaries and interobserver variability, our proposed method introduces a powerful new tool for obtaining reproducible quantitative measurements of these lesions. It is our intention to further document the value of this approach with a still larger set of ground glass nodules.

Citation Download Citation

Li Zhang, Ming Fang, David P. Naidich M.D., and Carol L. Novak "Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies", Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); https://doi.org/10.1117/12.536259

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available