Dataset Information

Radiomics Signature as a Predictive Factor for EGFR Mutations in Advanced Lung Adenocarcinoma.

ABSTRACT: Purpose: To develop and validate a radiomic signature to identify EGFR mutations in patients with advanced lung adenocarcinoma. Methods: This study involved 201 patients with advanced lung adenocarcinoma (140 in the training cohort and 61 in the validation cohort). A total of 396 features were extracted from manual segmentation based on enhanced and non-enhance CT imaging after image preprocessing. The Lasso algorithm was used for feature selection, 6 machine learning methods were used to construct radiomics models. Receiver operating characteristic (ROC) curve analysis was applied to evaluate the performance of the radiomic signature between different data and methods. A nomogram was developed using clinical factors and the radiomics signature, then it was analyzed based on its discriminatory ability and calibration. Decision curve analysis (DCA) was implemented to evaluate the clinical utility. Results: Ten features for contrast data and eleven features for non-contrast data were selected through LASSO algorithm. The performance of the radiomics signature for contrast images was better than that for non-contrast images in all of the 6 different machine learning methods. Finally, the best radiomics signature was built with logistic regression method based on enhanced CT imaging with an area under the curve (AUC) of 0.851 (95% CI, 0.750 to 0.951) in the validation cohort. A nomogram was developed using the radiomics signature and sex with a C-index of 0.908 (95%CI, 0.862 to 0.954) in the training cohort and 0.835 (95% CI, 0.825 to 0.845) in the validation cohort. It showed good discrimination and calibration (Hosmer-Lemeshow test, P = 0.621 for the training cohort and P = 0.605 for the validation cohort). Conclusion: Radiomics signature can help to distinguish between EGFR positive and wild type advanced lung adenocarcinomas.

SUBMITTER: Hong D

PROVIDER: S-EPMC7005234 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics Signature as a Predictive Factor for EGFR Mutations in Advanced Lung Adenocarcinoma.

Hong Duo D Xu Ke K Zhang Lina L Wan Xiaoting X Guo Yan Y

Frontiers in oncology 20200131

<b>Purpose:</b> To develop and validate a radiomic signature to identify EGFR mutations in patients with advanced lung adenocarcinoma. <b>Methods:</b> This study involved 201 patients with advanced lung adenocarcinoma (140 in the training cohort and 61 in the validation cohort). A total of 396 features were extracted from manual segmentation based on enhanced and non-enhance CT imaging after image preprocessing. The Lasso algorithm was used for feature selection, 6 machine learning methods were ...[more]

PMID: 32082997

Similar Datasets

Project description:The findings of EGFR mutations and the development of targeted therapies have significantly improved the overall survival of lung cancer patients. Still, the prognosis remains poor, so we need to know more about the genetic alterations in lung cancer. MicroRNAs are dysregulated in lung cancer, and some of them can regulate EGFR. So it is very important to predict the candidate microRNAs that target mutated EGFR and to investigate the role of these candidate microRNAs in lung cancer. In this study, we investigated the difference of microRNAs expression between lung adenocarcinoma cell lines with EGFR exon 19 deletion (H1650 and PC9) and wild-type (H1299 and A549) using the Phalanx Human Whole Genome Microarray. Then the expression of individual microRNAs was validated by qRT-PCR assays. Moreover, we detected the microRNAs expression in plasma of lung adenocarcinoma patients with EGFR exon 19 deletion and wild-type. Lastly, we explored the function of the positive microRNA in EGFR tyrosine kinase inhibitors (EGFR-TKIs ) resistance using MTT and Annexin V-APC assays. The expression of 1,732 microRNAs was evaluated, and we found that microRNAs expression was different between these two groups. Hsa-miR-141-3p, hsa-miR-200c-3p, hsa-miR-203, hsa-miR-3182, hsa-miR-934 were up-regulated and hsa-miR-3196 was down-regulated in the EGFR exon 19 deletion group compared with wild-type group. The detection of circulating microRNAs showed that miR-3196 was down-regulated in lung adenocarcinoma patients with EGFR exon 19 deletion compared with wild-type. And then the MTT assay results showed that miR-3196 had no effect on the sensitivity of erlotinib. The results of apoptosis analysis showed that inhibition of miR-3196 and erlotinib induced more apoptosis in H1299 cells than erlotinib alone, and overexpressed miR-3196 and erlotinib induced less apoptosis in PC9 cells than erlotinib alone (P<0.05). It is suggested that microRNAs associate with EGFR exon 19 deletion and miR-3196 may be further explored as a potential predictor and targeted biomarker when it is difficult to get the tumors.

Dataset Information

Radiomics Signature as a Predictive Factor for EGFR Mutations in Advanced Lung Adenocarcinoma.

Publications

Radiomics Signature as a Predictive Factor for EGFR Mutations in Advanced Lung Adenocarcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets