Multiparametric MRI‐Based Radiomics Approaches for Preoperative Prediction of EGFR Mutation Status in Spinal Bone Metastases in Patients with Lung Adenocarcinoma. Issue 2 (27th February 2021)

• Record Type: Journal Article
• Authors: Jiang, Xiran; Ren, Meihong; Shuang, Xue; Yang, Huazhe; Shi, Dabao; Lai, Qingyuan; Dong, Yue
• Is Part Of: Journal of magnetic resonance imaging. Volume 54:Issue 2(2021)
• Page Start: 497
• Page End: 507
• Publication Date: 2021-02-27
• Subjects: EGFR -- spinal bone metastases -- lung adenocarcinoma -- MRI -- radiomics -- deep learning; Magnetic resonance imaging -- Periodicals; 616
• DOI: 10.1002/jmri.27579
• Languages: English
• ISSNs: 1053-1807

Abstract

Abstract : Background: Preoperative prediction of epidermal growth factor receptor (EGFR) mutation status in patients with spinal bone metastases (SBM) from primary lung adenocarcinoma is potentially important for treatment decisions. Purpose: To develop and validate multiparametric magnetic resonance imaging (MRI)‐based radiomics methods for preoperative prediction of EGFR mutation based on MRI of SBM. Study Type: Retrospective. Population: A total of 97 preoperative patients with lumbar SBM from lung adenocarcinoma (77 in training set and 20 in validation set). Field Strength/Sequence: T1‐weighted, T2‐weighted, and T2‐weighted fat‐suppressed fast spin echo sequences at 3.0 T. Assessment: Radiomics handcrafted and deep learning‐based features were extracted and selected from each MRI sequence. The abilities of the features to predict EGFR mutation status were analyzed and compared. A radiomics nomogram was constructed integrating the selected features. Statistical Tests: The Mann‐Whitney U test and χ 2 test were employed for evaluating associations between clinical characteristics and EGFR mutation status for continuous and discrete variables, respectively. Least absolute shrinkage and selection operator was used for selection of predictive features. Sensitivity (SEN), specificity (SPE), and area under the receiver operating characteristic curve (AUC) were used to evaluate the ability of radiomics models to predict the EGFR mutation. Calibration and decision curve analysis (DCA) were performed to assess and validate nomogram results. Results: The radiomics signature comprised five handcrafted and one deep learning‐based features and achieved good performance for predicting EGFR mutation status, with AUCs of 0.891 (95% confidence interval [CI], 0.820–0.962, SEN = 0.913, SPE = 0.710) in the training group and 0.771 (95% CI, 0.551–0.991, SEN = 0.750, SPE = 0.875) in the validation group. DCA confirmed the potential clinical usefulness of the radiomics models. Data Conclusion: Multiparametric MRI‐based radiomics is potentially clinical valuable for predicting EGFR mutation status in patients with SBM from lung adenocarcinoma. Level of Evidence: 3 Technical Efficacy: 2