Simulation of nodules and diffuse infiltrates in chest radiographs using CT templates
- PMID: 20879340
- DOI: 10.1007/978-3-642-15745-5_49
Simulation of nodules and diffuse infiltrates in chest radiographs using CT templates
Abstract
A method is proposed to simulate nodules and diffuse infiltrates in chest radiographs. This allows creation of large annotated databases for training of both radiologists and computer aided diagnosis systems. Realistic nodules and diffuse infiltrates were generated from three-dimensional templates segmented from CT data. These templates are rescaled, rotated, projected and superimposed on a radiograph. This method was compared, in an observer study, to a previously published method that simulates pulmonary nodules as perfectly spherical objects. Results show that it is hard for human observers to distinguish real and simulated nodules when using templates (AUC-values do not significantly differ from .5, p > .05 for all observers). The method that produced spherical nodules performed slightly worse (AUC of one observer differs significantly from .5, p = .011). Simulation of diffuse infiltrates is challenging but also feasible (AUC = 0.67 for one observer).
Similar articles
-
Computer-assisted detection of infectious lung diseases: a review.Comput Med Imaging Graph. 2012 Jan;36(1):72-84. doi: 10.1016/j.compmedimag.2011.06.002. Epub 2011 Jul 1. Comput Med Imaging Graph. 2012. PMID: 21723090 Free PMC article. Review.
-
Three-dimensional volumetric assessment with thoracic CT: a reliable approach for noncalcified lung nodules?Radiology. 2010 Feb;254(2):634; author reply 635. doi: 10.1148/radiol.091655. Radiology. 2010. PMID: 20093537 No abstract available.
-
Computer-aided diagnosis in chest radiography: beyond nodules.Eur J Radiol. 2009 Nov;72(2):226-30. doi: 10.1016/j.ejrad.2009.05.061. Epub 2009 Jul 14. Eur J Radiol. 2009. PMID: 19604661 Review.
-
Semi-automatic volumetric measurement of lung cancer using multi-detector CT effects of nodule characteristics.Acad Radiol. 2009 Oct;16(10):1179-86. doi: 10.1016/j.acra.2009.04.007. Epub 2009 Jun 12. Acad Radiol. 2009. PMID: 19524456
-
Appearance models for robust segmentation of pulmonary nodules in 3D LDCT chest images.Med Image Comput Comput Assist Interv. 2006;9(Pt 1):662-70. doi: 10.1007/11866565_81. Med Image Comput Comput Assist Interv. 2006. PMID: 17354947
Cited by
-
A systematic approach to deep learning-based nodule detection in chest radiographs.Sci Rep. 2023 Jun 21;13(1):10120. doi: 10.1038/s41598-023-37270-2. Sci Rep. 2023. PMID: 37344565 Free PMC article.
-
Teaching search patterns to medical trainees in an educational laboratory to improve perception of pulmonary nodules.J Med Imaging (Bellingham). 2016 Jan;3(1):011006. doi: 10.1117/1.JMI.3.1.011006. Epub 2015 Nov 6. J Med Imaging (Bellingham). 2016. PMID: 26870749 Free PMC article.
MeSH terms
LinkOut - more resources
Other Literature Sources
Medical