The predictive value of CT-based radiomics in differentiating indolent from invasive lung adenocarcinoma in patients with pulmonary nodules
- 693 Downloads
Adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) are assumed to be indolent lung adenocarcinoma with excellent prognosis. We aim to identify these lesions from invasive adenocarcinoma (IA) by a radiomics approach.
This retrospective study was approved by institutional review board with a waiver of informed consent. Pathologically confirmed lung adenocarcinomas manifested as lung nodules less than 3 cm were retrospectively identified. In-house software was used to quantitatively extract 60 CT-based radiomics features quantifying nodule’s volume, intensity and texture property through manual segmentation. In order to differentiate AIS/MIA from IA, least absolute shrinkage and selection operator (LASSO) logistic regression was used for feature selection and developing radiomics signatures. The predictive performance of the signature was evaluated via receiver operating curve (ROC) and calibration curve, and validated using an independent cohort.
402 eligible patients were included and divided into the primary cohort (n = 207) and the validation cohort (n = 195). Using the primary cohort, we developed a radiomics signature based on five radiomics features. The signature showed good discrimination between MIA/AIS and IA in both the primary and validation cohort, with AUCs of 0.95 (95% CI, 0.91–0.98) and 0.89 (95% CI, 0.84–0.93), respectively. Multivariate logistic analysis revealed that the signature (OR, 13.3; 95% CI, 6.2–28.5; p < 0.001) and gender (OR, 3.5; 95% CI, 1.2–10.9; p = 0.03) were independent predictors of indolent lung adenocarcinoma.
The signature based on radiomics features helps to differentiate indolent from invasive lung adenocarcinoma, which might be useful in guiding the intervention choice for patients with pulmonary nodules.
• Based on radiomics features, a signature is established to differentiate adenocarcinoma in situ and minimally invasive adenocarcinoma from invasive lung adenocarcinoma.
KeywordsLung neoplasms Tomography, spiral computed Radiomics Multivariate analysis Forecasting
Adenocarcinoma in situ
Area under the curve
Least absolute shrinkage and selection operator
Minimally invasive adenocarcinoma
This study has received funding by Shanghai Hospital Development Center (16CR3116B).
Compliance with ethical standards
The scientific guarantor of this publication is Chang Chen.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Written informed consent was waived by the institutional review board.
Institutional review board approval was obtained.
• performed at one institution
- 9.Verma V, Simone CB, Krishnan S, Lin SH, Yang J, Hahn SM (2017) The rise of radiomics and implications for oncologic management. J Natl Cancer Inst. https://doi.org/10.1093/jnci/djx055