Abstract
Tumor phenotypes captured in computed tomography (CT) images can be described qualitatively and quantitatively using radiologist-defined “semantic” and computer-derived “radiomic” features, respectively. While both types of features have shown to be promising predictors of prognosis, the association between these groups of features remains unclear. We investigated the associations between semantic and radiomic features in CT images of 258 non-small cell lung adenocarcinomas. The tumor imaging phenotypes were described using 9 qualitative semantic features that were scored by radiologists, and 57 quantitative radiomic features that were automatically calculated using mathematical algorithms. Of the 9 semantic features, 3 were rated on a binary scale (cavitation, air bronchogram, and calcification) and 6 were rated on a categorical scale (texture, border definition, contour, lobulation, spiculation, and concavity). 32–41 radiomic features were associated with the binary semantic features (AUC = 0.56–0.76). The relationship between all radiomic features and the categorical semantic features ranged from weak to moderate (|Spearmen’s correlation| = 0.002–0.65). There are associations between semantic and radiomic features, however the associations were not strong despite being significant. Our results indicate that radiomic features may capture distinct tumor phenotypes that fail to be perceived by naked eye that semantic features do not describe and vice versa.
Highlights
Our results indicate that radiomic features may capture distinct tumor phenotypes that fail to be perceived by naked eye that semantic features do not describe and vice versa
Our study cohort consisted of 183 early stage (Stage I and II) and 75 advanced stage patients with non-small cell lung adenocarcinoma (Table 1)
296 radiomic features were initially extracted from computed tomography (CT) images, only 57 features (10 unfiltered and 47 filtered features) with |ρ| ≤ 0.85 were included to evaluate their relationship with semantic features
Summary
Tumor phenotypes captured in computed tomography (CT) images can be described qualitatively and quantitatively using radiologist-defined “semantic” and computer-derived “radiomic” features, respectively. While both types of features have shown to be promising predictors of prognosis, the association between these groups of features remains unclear. Several studies have indicated that the identification of unique characteristics of individual lung tumors may provide clinicians with crucial information to personalize treatments for patients[4, 5] These unique characteristics can be qualitative CT-based descriptors, termed semantic features, that describe a tumor’s shape and internal structure that are scored by radiologists to characterize lung lesions[5,6,7,8]. Histology subtype Minimally invasive adenocarcinoma Acinar predominant Lepidic predominant Papillary predominant Micropapillary predominant Solid predominant Variants of invasive adenocarcinomas Tumor grade Low/Intermediate/High CT Scanners Siemens Somatom Sensation 64 GE scanner Lightspeed 16/Discovery CT750 HD Binary semantic features Cavitation (score: 0/1) Air Bronchogram (score: 0/1) Calcification (score: 0/1) Categorical Semantic features Texture (score: 1/2/3)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
