3D Morphometric Assessment of Temporal Changes in Lung Nodules
1) To evaluate and compare CAD volumetric measurement methods on phantoms and selected test-set clinical CT scans. (Hypothesis: No significant variability in accuracy and reproducibility between different CAD methods in measuring lung nodule volumes.) 2) To measure temporal volumetric changes in nodules using CAD and compare them with semi-quantitative measurements by radiologists. (Hypothesis: The CAD measurements are significantly more reproducible than the 2D manual semi-quantitative measurements.) 3) To evaluate and compare the probability of malignancy based on the nodule growth rate estimated by the CAD and manual semi-quantitative measurements. Histology and clinical follow-up data from the NLST will be used as the gold standard. Hypothesis: The CAD method can estimate the probability of malignancy of a nodule more accurately and more time-efficiently than the manual method.
Computer-aided nodule detection and volumetry to reduce variability between radiologists in the interpretation of lung nodules at low-dose screening computed tomography.
Jeon KN, Goo JM, Lee CH, Lee Y, Choo JY, Lee NK, Shim MS, Lee IS, Kim KG, Gierada DS, Bae KT
Invest Radiol. 2012 Aug; Volume 47 (Issue 8): Pages 457-61 PUBMED
Automated matching of pulmonary nodules: evaluation in serial screening chest CT.
Tao C, Gierada DS, Zhu F, Pilgram TK, Wang JH, Bae KT
AJR Am J Roentgenol. 2009 Mar; Volume 192 (Issue 3): Pages 624-8 PUBMED