The Predictive Value of CT-based Radiomics in Differentiating Indolent from Invasive Lung Adenocarcinoma in Patients with Pulmonary Nodules

Overview

Journal Eur Radiol

Specialty Radiology

Date 2018 Jun 6

PMID 29869172

Citations 66

Authors

Yunlang She

Lei Zhang

Huiyuan Zhu

Chenyang Dai

Dong Xie

Huikang Xie

Wei Zhang

Lilan Zhao

Liling Zou

Ke Fei

Xiwen Sun

Chang Chen

Affiliations

Soon will be listed here.

Abstract

Objectives: 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.

Methods: 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.

Results: 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.

Conclusion: 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.

Key Points: • Based on radiomics features, a signature is established to differentiate adenocarcinoma in situ and minimally invasive adenocarcinoma from invasive lung adenocarcinoma.

Citing Articles

Predicting the invasiveness of ground-glass opacity predominant lung adenocarcinoma with clinical stage Ia: a CT-based semantic and radiomics analysis.

Zhao Y, Ye Z, Yan Q, Sun H, Zhao F J Thorac Dis. 2024; 16(10):6713-6726.

PMID: 39552862 PMC: 11565351. DOI: 10.21037/jtd-24-775.

Development of a nomogram-based model incorporating radiomic features from follow-up longitudinal lung CT images to distinguish invasive adenocarcinoma from benign lesions: a retrospective study.

Wang Z, Wang F, Yang Y, Fan W, Wen L, Zhang D BMC Pulm Med. 2024; 24(1):534.

PMID: 39455958 PMC: 11515265. DOI: 10.1186/s12890-024-03360-8.

Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach.

Bin J, Wu M, Huang M, Liao Y, Yang Y, Shi X BMC Med Imaging. 2024; 24(1):240.

PMID: 39272029 PMC: 11396739. DOI: 10.1186/s12880-024-01421-2.

Evaluation of the invasiveness of pure ground-glass nodules based on dual-head ResNet technique.

Yang D, Yang Y, Zhao M, Ji H, Niu Z, Hong B BMC Cancer. 2024; 24(1):1080.

PMID: 39223592 PMC: 11367849. DOI: 10.1186/s12885-024-12823-4.

CT-based radiomics combined with clinical features for invasiveness prediction and pathological subtypes classification of subsolid pulmonary nodules.

Liu M, Duan R, Xu Z, Fu Z, Li Z, Pan A Eur J Radiol Open. 2024; 13:100584.

PMID: 39041055 PMC: 11260948. DOI: 10.1016/j.ejro.2024.100584.

References

Hwang I, Park C, Park S, Lee S, McAdams H, Jeon Y . Persistent Pure Ground-Glass Nodules Larger Than 5 mm: Differentiation of Invasive Pulmonary Adenocarcinomas From Preinvasive Lesions or Minimally Invasive Adenocarcinomas Using Texture Analysis. Invest Radiol. 2015; 50(11):798-804. DOI: 10.1097/RLI.0000000000000186. View

Liu S, Wang R, Zhang Y, Li Y, Cheng C, Pan Y . Precise Diagnosis of Intraoperative Frozen Section Is an Effective Method to Guide Resection Strategy for Peripheral Small-Sized Lung Adenocarcinoma. J Clin Oncol. 2015; 34(4):307-13. DOI: 10.1200/jco.2015.63.4907. View

Yeh Y, Nitadori J, Kadota K, Yoshizawa A, Rekhtman N, Moreira A . Using frozen section to identify histological patterns in stage I lung adenocarcinoma of ≤ 3 cm: accuracy and interobserver agreement. Histopathology. 2014; 66(7):922-38. PMC: 4536823. DOI: 10.1111/his.12468. View

Hawkins S, Wang H, Liu Y, Garcia A, Stringfield O, Krewer H . Predicting Malignant Nodules from Screening CT Scans. J Thorac Oncol. 2016; 11(12):2120-2128. PMC: 5545995. DOI: 10.1016/j.jtho.2016.07.002. View

Gillies R, Kinahan P, Hricak H . Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2015; 278(2):563-77. PMC: 4734157. DOI: 10.1148/radiol.2015151169. View

Davnall F, Yip C, Ljungqvist G, Selmi M, Ng F, Sanghera B . Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice?. Insights Imaging. 2012; 3(6):573-89. PMC: 3505569. DOI: 10.1007/s13244-012-0196-6. View

Bankier A, MacMahon H, Goo J, Rubin G, Schaefer-Prokop C, Naidich D . Recommendations for Measuring Pulmonary Nodules at CT: A Statement from the Fleischner Society. Radiology. 2017; 285(2):584-600. DOI: 10.1148/radiol.2017162894. View

Coroller T, Grossmann P, Hou Y, Velazquez E, Leijenaar R, Hermann G . CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol. 2015; 114(3):345-50. PMC: 4400248. DOI: 10.1016/j.radonc.2015.02.015. View

Chae H, Park C, Park S, Lee S, Kim K, Goo J . Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas. Radiology. 2014; 273(1):285-93. DOI: 10.1148/radiol.14132187. View

10.

Woo T, Okudela K, Mitsui H, Tajiri M, Yamamoto T, Rino Y . Prognostic value of the IASLC/ATS/ERS classification of lung adenocarcinoma in stage I disease of Japanese cases. Pathol Int. 2012; 62(12):785-91. DOI: 10.1111/pin.12016. View

11.

Lee S, Lee S, Goo J, Kim K, Kim Y, Park C . Usefulness of texture analysis in differentiating transient from persistent part-solid nodules(PSNs): a retrospective study. PLoS One. 2014; 9(1):e85167. PMC: 3885675. DOI: 10.1371/journal.pone.0085167. View

12.

Huang Y, Liang C, He L, Tian J, Liang C, Chen X . Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol. 2016; 34(18):2157-64. DOI: 10.1200/JCO.2015.65.9128. View

13.

Yoshizawa A, Motoi N, Riely G, Sima C, Gerald W, Kris M . Impact of proposed IASLC/ATS/ERS classification of lung adenocarcinoma: prognostic subgroups and implications for further revision of staging based on analysis of 514 stage I cases. Mod Pathol. 2011; 24(5):653-64. DOI: 10.1038/modpathol.2010.232. View

14.

Son J, Lee H, Lee K, Kim J, Han J, Jeong J . Quantitative CT analysis of pulmonary ground-glass opacity nodules for the distinction of invasive adenocarcinoma from pre-invasive or minimally invasive adenocarcinoma. PLoS One. 2014; 9(8):e104066. PMC: 4125172. DOI: 10.1371/journal.pone.0104066. View

15.

Song S, Park H, Lee G, Lee H, Sohn I, Kim H . Imaging Phenotyping Using Radiomics to Predict Micropapillary Pattern within Lung Adenocarcinoma. J Thorac Oncol. 2016; 12(4):624-632. DOI: 10.1016/j.jtho.2016.11.2230. View

16.

Kadota K, Villena-Vargas J, Yoshizawa A, Motoi N, Sima C, Riely G . Prognostic significance of adenocarcinoma in situ, minimally invasive adenocarcinoma, and nonmucinous lepidic predominant invasive adenocarcinoma of the lung in patients with stage I disease. Am J Surg Pathol. 2014; 38(4):448-60. PMC: 4164170. DOI: 10.1097/PAS.0000000000000134. View

17.

McNeish D . Using Lasso for Predictor Selection and to Assuage Overfitting: A Method Long Overlooked in Behavioral Sciences. Multivariate Behav Res. 2015; 50(5):471-84. DOI: 10.1080/00273171.2015.1036965. View

18.

Zhang J, Song W, Chen Z, Wei J, Liao Y, Lei J . Prognostic and predictive value of a microRNA signature in stage II colon cancer: a microRNA expression analysis. Lancet Oncol. 2013; 14(13):1295-306. DOI: 10.1016/S1470-2045(13)70491-1. View

19.

Ost D, Gould M . Decision making in patients with pulmonary nodules. Am J Respir Crit Care Med. 2011; 185(4):363-72. PMC: 3361350. DOI: 10.1164/rccm.201104-0679CI. View

20.

Travis W, Brambilla E, Noguchi M, Nicholson A, Geisinger K, Yatabe Y . International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma. J Thorac Oncol. 2011; 6(2):244-85. PMC: 4513953. DOI: 10.1097/JTO.0b013e318206a221. View