A novel radiomic nomogram for predicting epidermal growth factor receptor mutation in peripheral lung adenocarcinoma

Abstract

To predict the epidermal growth factor receptor (EGFR) mutation status in patients with lung adenocarcinoma using quantitative radiomic biomarkers and semantic features. We analyzed the computed tomography (CT) images and medical record data of 104 patients with lung adenocarcinoma who underwent surgical excision and EGFR mutation detection from 2016 to 2018 at our center. CT radiomic and semantic features that reflect the tumors’ heterogeneity and phenotype were extracted from preoperative non-enhanced CT scans. The least absolute shrinkage and selection operator method was applied to select the most distinguishable features. Three logistic regression models were built to predict the EGFR mutation status by combining the CT semantic with clinicopathological characteristics, using the radiomic features alone, and by combining the radiomic and clinicopathological features. Receiver operating characteristic (ROC) curve analysis was performed using five-fold cross-validation and the mean area under the curve (AUC) values were calculated and compared between the models to obtain the optimal model for predicting EGFR mutation. Furthermore, radiomic nomograms were constructed to demonstrate the performance of the model. In total, 1025 radiomic features were extracted and reduced to 13 features as the most important predictors to build the radiomic signature. The combined radiomic and clinicopathological features model was developed based on the radiomic signature, sex, smoking, vascular infiltration, and pathohistological type. The AUC was 0.90 ± 0.02 for the training, 0.88 ± 0.11 for the verification, and 0.894 for the test dataset. This model was superior to the other prediction models that used the combined CT semantic and clinicopathological features (AUC for the test dataset: 0.768) and radiomic features alone (AUC for the test dataset: 0.837). The prediction model built by radiomic biomarkers and clinicopathological features, including the radiomic signature, sex, smoking, vascular infiltration, and pathological type, outperformed the other two models and could effectively predict the EGFR mutation status in patients with peripheral lung adenocarcinoma. The radiomic nomogram of this model is expected to become an effective biomarker for patients with lung adenocarcinoma requiring adjuvant targeted treatment.

Systematic Review on the Association of Radiomics with Tumor Biological Endpoints

“…In total, 33 studies investigating radiomics and biological endpoints for lung lesions were identified. The imaging modalities employed were CT ( n = 22) [ 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 ], PET/CT ( n = 8) [ 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 ], PET ( n = 2) [ 100 , 101 ] and MRI ( n = 1) [ 102 ]. One study investigated radiomics from metastases, while all other studies associated tissue biomarkers with radiomics of the primary tumor.…”

“…Almost half of the studies selected histological subtypes and used adenocarcinoma patients only ( n = 15), whereas the other half used a mix of histologies. Research has predominantly focused on EGFR ( n = 26) [ 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 92 , 93 , 94 , 95 , 96 , 97 , 100 , 101 , 102 ], followed by KRAS ( n = 5) [ 83 , 97 , 100 , 101 , 102 ], ALK ( n = 3) [ 87 , 98 , 102 ], PD-L1 ( n = 3) [ 88 , 89 , 99 ], Ki-67 ( n = 2) [ 90 , 91 ], and TP-53 ( n = 1) [ 84 ]. All studies showed a significant relationship between EGFR and radiomic features (AUC = 0.66–0.95).…”

“…The power of CT radiomics to predict EGFR mutations status strongly varied among the studies using validation (AUC = 0.69–0.851) [ 72 , 73 , 74 , 75 , 76 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 ]. Across CT radiomics studies, relevant features for EGFR mutation status prediction were associated with texture heterogeneity, suggesting that mutated tumors were more heterogeneous.…”

“…In contrast to three-week post-treatment CT radiomics, one delta radiomic feature (i.e., change of feature value over time) was found predictive for EGFR mutation status (AUC = 0.74, weakly corrected to delta volume and diameter) [ 70 ]. Multiple studies were found using contrast-enhanced CT (CE CT) [ 74 , 84 , 85 ], non-CE CT imaging [ 70 , 72 , 73 , 77 , 78 , 79 , 81 , 82 ] or a mix of thereof [ 75 , 83 ]. In a recent study, it was shown that a model based on CE CT features did not significantly performed different to a model based non-CE CT for EGFR mutation status prediction [ 85 ].…”

Prognostic Value of Pre-Treatment CT Radiomics and Clinical Factors for the Overall Survival of Advanced (IIIB–IV) Lung Adenocarcinoma Patients

“…There are different treatment methods in mutated EGFR group and wild type EGFR group (18), so generally, their prognosis was studied separately. However, many previous studies have shown that radiomic has a high accuracy in distinguishing wild and mutated EGFR NSCLC patients (19,20), therefore, we combined two groups to increase the universality of the models. We also performed subgroup analysis which indicated that the radiomic signature own higher discrimination capacity for wild type EGFR group than mutated EGFR subgroup for all cut-off time points.…”