Noninvasive Risk Stratification of Lung Adenocarcinoma using Quantitative Computed Tomography Sushravya Raghunath, PhD, Fabien Maldonado, MD, Srinivasan Rajagopalan, PhD, Ronald A. Karwoski, BA, Zackary S. DePew, MD, Brian J. Bartholmai, MD, Tobias Peikert, MD, Richard A. Robb, PhD Journal of Thoracic Oncology Volume 9, Issue 11, Pages 1698-1703 (November 2014) DOI: 10.1097/JTO.0000000000000319 Copyright © 2014 International Association for the Study of Lung Cancer Terms and Conditions
FIGURE 1 The original CT axial sections, color-coded voxel classification overlay and glyph representations are shown for representative nodules. Journal of Thoracic Oncology 2014 9, 1698-1703DOI: (10.1097/JTO.0000000000000319) Copyright © 2014 International Association for the Study of Lung Cancer Terms and Conditions
FIGURE 2 The raw CT section, pattern overlay and glyph visualization of the three nodule exemplars identified by unsupervised affinity propagation (AP)-based clustering using pair-wise similarity of the parametric signatures. Journal of Thoracic Oncology 2014 9, 1698-1703DOI: (10.1097/JTO.0000000000000319) Copyright © 2014 International Association for the Study of Lung Cancer Terms and Conditions
FIGURE 3 KaplanMeier survival curve of 264 cases categorized into three automatically identified three groups of unique parametric signature. DFS, Disease-free survival. Journal of Thoracic Oncology 2014 9, 1698-1703DOI: (10.1097/JTO.0000000000000319) Copyright © 2014 International Association for the Study of Lung Cancer Terms and Conditions