CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Issue 3 (March 2015)

• Record Type: Journal Article
• Authors: Coroller, Thibaud P.; Grossmann, Patrick; Hou, Ying; Rios Velazquez, Emmanuel; Leijenaar, Ralph T.H.; Hermann, Gretchen; Lambin, Philippe; Haibe-Kains, Benjamin; Mak, Raymond H.; Aerts, Hugo J.W.L.
• Is Part Of: Radiotherapy and oncology. Volume 114:Issue 3(2015:Mar.)
• Page Start: 345
• Page End: 350
• Publication Date: 2015-03
• Subjects: Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2015.02.015
• Languages: English
• ISSNs: 0167-8140

Abstract

<abstract xml:lang="en" abstract-type="author" id="ab005"> <title id="st070">Abstract</title> <sec> <title id="st075">Background and purpose</title> <p id="sp0005">Radiomics provides opportunities to quantify the tumor phenotype non-invasively by applying a large number of quantitative imaging features. This study evaluates computed-tomography (CT) radiomic features for their capability to predict distant metastasis (DM) for lung adenocarcinoma patients.</p> </sec> <sec> <title id="st080">Material and methods</title> <p id="sp0010">We included two datasets: 98 patients for discovery and 84 for validation. The phenotype of the primary tumor was quantified on pre-treatment CT-scans using 635 radiomic features. Univariate and multivariate analysis was performed to evaluate radiomics performance using the concordance index (CI).</p> </sec> <sec> <title id="st085">Results</title> <p id="sp0015">Thirty-five radiomic features were found to be prognostic (CI > 0.60, FDR < 5%) for DM and twelve for survival. It is noteworthy that tumor volume was only moderately prognostic for DM (CI = 0.55, <italic>p</italic>-value = 2.77 × 10<sup>−5</sup>) in the discovery cohort. A radiomic-signature had strong power for predicting DM in the independent validation dataset (CI = 0.61, <italic>p</italic>-value = 1.79 × 10<sup>−17</sup>). Adding this radiomic-signature to a clinical model resulted in a significant improvement of predicting DM in the validation dataset (<italic>p</italic>-value = 1.56 × 10<sup>−11</sup>).</p> </sec> <sec> <title id="st090">Conclusions</title> <p id="sp0020">Although only basic metrics are routinely quantified, this study shows that radiomic features capturing detailed information of the tumor phenotype can be used as a prognostic biomarker for clinically-relevant factors such as DM. Moreover, the radiomic-signature provided additional information to clinical data.</p> </sec> </abstract>