Wenting Tu1, Guangyuan Sun2, Li Fan3, Yun Wang1, Yi Xia1, Yu Guan1, Qiong Li1, Di Zhang1, Shiyuan Liu1, Zhaobin Li4. 1. Department of Radiology, Changzheng Hospital, Second Military Medical University, No. 415 Fengyang Road, Shanghai 200003, China. 2. Department of Thoracic and Cardiovascular Surgery, Changzheng Hospital, Second Military Medical University, No. 415 Fengyang Road, Shanghai 200003, China. 3. Department of Radiology, Changzheng Hospital, Second Military Medical University, No. 415 Fengyang Road, Shanghai 200003, China. Electronic address: czyxfl@smmu.edu.cn. 4. Department of Radiation Oncology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai 200233, China. Electronic address: lizhaobin79@163.com.
Abstract
OBJECTIVES: To compare the predictive performance of radiomics signature and CT morphological features for epidermal growth factor receptor (EGFR) mutation status; then further to develop and compare the different predictive models for EGFR mutation in non-small cell lung cancer (NSCLC) patients. MATERIALS AND METHODS: This retrospective study involved 404 patients with NSCLC (243 cases in the training cohort and 161 cases in the validation cohort). Radiomics features were extracted from preoperative non-contrast CT images of the entire tumor. Correlations between the EGFR mutation status and candidate predictors were assessed using Mann-Whitney U test or Chi-square test. Unsupervised consensus clustering was used to analyze the representativeness and reduce the redundancy of radiomics features. Multivariable logistic regression analysis was performed to build radiomics signature and develop predictive models of EGFR mutation. ROC curve analysis and Delong test were used to compare the predictive performance among individual features and models. RESULTS: Of the 234 radiomics features, 93 radiomics features with high repeatability and high predictive significance were selected. The radiomics signature, which was built with one histogram and two textural features, showed the best predictive performance (AUC = 0.762 and 0.775 in the training and validation cohort) in comparison with all the clinical characteristics and conventional CT morphological features to differentiate EGFR mutation status (P < 0.05). The integrated model was developed with maximum diameter, location, sex and radiomics signature. In the training and validation cohort, the integrated model showed the most optimal predictive performance (AUC = 0.798, 0.818 in the training and validation cohort) compared with the clinical models. CONCLUSION: The radiomics signature showed better performance for predicting EGFR mutant than all the clinical and morphological features. Moreover, the integrated model built with radiomics signature, clinical and morphological features outperformed the clinical models, which is helpful for physicians to determine the targeted therapy.
OBJECTIVES: To compare the predictive performance of radiomics signature and CT morphological features for epidermal growth factor receptor (EGFR) mutation status; then further to develop and compare the different predictive models for EGFR mutation in non-small cell lung cancer (NSCLC) patients. MATERIALS AND METHODS: This retrospective study involved 404 patients with NSCLC (243 cases in the training cohort and 161 cases in the validation cohort). Radiomics features were extracted from preoperative non-contrast CT images of the entire tumor. Correlations between the EGFR mutation status and candidate predictors were assessed using Mann-Whitney U test or Chi-square test. Unsupervised consensus clustering was used to analyze the representativeness and reduce the redundancy of radiomics features. Multivariable logistic regression analysis was performed to build radiomics signature and develop predictive models of EGFR mutation. ROC curve analysis and Delong test were used to compare the predictive performance among individual features and models. RESULTS: Of the 234 radiomics features, 93 radiomics features with high repeatability and high predictive significance were selected. The radiomics signature, which was built with one histogram and two textural features, showed the best predictive performance (AUC = 0.762 and 0.775 in the training and validation cohort) in comparison with all the clinical characteristics and conventional CT morphological features to differentiate EGFR mutation status (P < 0.05). The integrated model was developed with maximum diameter, location, sex and radiomics signature. In the training and validation cohort, the integrated model showed the most optimal predictive performance (AUC = 0.798, 0.818 in the training and validation cohort) compared with the clinical models. CONCLUSION: The radiomics signature showed better performance for predicting EGFR mutant than all the clinical and morphological features. Moreover, the integrated model built with radiomics signature, clinical and morphological features outperformed the clinical models, which is helpful for physicians to determine the targeted therapy.
Authors: Erica L Carpenter; Despina Kontos; Bardia Yousefi; Michael J LaRiviere; Eric A Cohen; Thomas H Buckingham; Stephanie S Yee; Taylor A Black; Austin L Chien; Peter Noël; Wei-Ting Hwang; Sharyn I Katz; Charu Aggarwal; Jeffrey C Thompson Journal: Sci Rep Date: 2021-05-11 Impact factor: 4.379