Research Articles

Download PDF (929.32 KB)

TOMOGRAPHY, December 2016, Volume 2, Issue 4: 430-437
DOI: 10.18383/j.tom.2016.00235

Radiomics of Lung Nodules: A Multi- Institutional Study of Robustness and Agreement of Quantitative Imaging Features

Jayashree Kalpathy-Cramer1, Artem Mamomov1, Binsheng Zhao2, Lin Lu2, Dmitry Cherezov3, Sandy Napel4, Sebastian Echegaray4, Daniel Rubin4, Michael McNitt-Gray5, Pechin Lo5, Jessica C. Sieren6, Johanna Uthoff6, Samantha K. N. Dilger6, Brandan Driscoll7, Ivan Yeung7, Lubomir Hadjiiski8, Kenny Cha8, Yoganand Balagurunathan9, Robert Gillies9, and Dmitry Goldgof3

1Massachusetts General Hospital, Boston, Massachusetts; 2Columbia University Medical Center, New York, New York; 3University of South Florida, Tampa, Florida; 4Stanford University, Stanford, California; 5University of California Los Angeles, Los Angeles, California; 6University of Iowa, Iowa City, Iowa; 7Princess Margaret Cancer Center, Toronto, Ontario, Canada; 8University of Michigan, Ann Arbor, Michigan; and 9Moffitt Cancer Center, Tampa, Florida

Abstract

Radiomics is to provide quantitative descriptors of normal and abnormal tissues during classification and prediction tasks in radiology and oncology. Quantitative Imaging Network members are developing radiomic “feature” sets to characterize tumors, in general, the size, shape, texture, intensity, margin, and other aspects of the imaging features of nodules and lesions. Efforts are ongoing for developing an ontology to describe radiomic features for lung nodules, with the main classes consisting of size, local and global shape descriptors, margin, intensity, and texture-based features, which are based on wavelets, Laplacian of Gaussians, Law’s features, gray-level cooccurrence matrices, and run-length features. The purpose of this study is to investigate the sensitivity of quantitative descriptors of pulmonary nodules to segmentations and to illustrate comparisons across different feature types and features computed by different implementations of feature extraction algorithms. We calculated the concordance correlation coefficients of the features as a measure of their stability with the underlying segmentation; 68% of the 830 features in this study had a concordance CC of ≥0.75. Pairwise correlation coefficients between pairs of features were used to uncover associations between features, particularly as measured by different participants. A graphical model approach was used to enumerate the number of uncorrelated feature groups at given thresholds of correlation. At a threshold of 0.75 and 0.95, there were 75 and 246 subgroups, respectively, providing a measure for the features’ redundancy.

Supplemental Media

PDF

Download the article PDF (929.32 KB)

Download the full issue PDF (200.5 MB)

Mobile-ready Flipbook

View the full issue as a flipbook (Desktop and Mobile-ready)