Establishment and Optimization of Radiomics Algorithms for Prediction of KRAS Gene Mutation by Integration of NSCLC Gene Mutation Mutual Exclusion Information

Abstract

Purpose: To assess the significance of mutation mutual exclusion information in the optimization of radiomics algorithms for predicting gene mutation.Methods: We retrospectively analyzed 258 non-small cell lung cancer (NSCLC) patients. Patients were randomly divided into training (n = 180) and validation (n = 78) cohorts. Based on radiomics features, radiomics score (RS) models were developed for predicting KRAS proto-oncogene mutations. Furthermore, a composite model combining mixedRS and epidermal growth factor receptor (EGFR) mutation status was developed.Results: Compared with CT model, the PET/CT radiomics score model exhibited higher AUC for predicting KRAS mutations (0.834 vs. 0.770). By integrating EGFR mutation information into the PET/CT RS model, the AUC, sensitivity, specificity, and accuracy for predicting KRAS mutations were all elevated in the validation cohort (0.921, 0.949, 0.872, 0.910 vs. 0.834, 0.923, 0.641, 0.782). By adding EGFR exclusive mutation information, the composite model corrected 64.3% false positive cases produced by the PET/CT RS model in the validation cohort.Conclusion: Integrating EGFR mutation status has potential utility for the optimization of radiomics models for prediction of KRAS gene mutations. This method may be used when repeated biopsies would carry unacceptable risks for the patient.

CT‐based non‐invasive identification of the most common gene mutation status in patients with non‐small cell lung cancer

“…32,37 In the KRAS group, smoking history was excluded from the final model, which is inconsistent with some studies, 38,39 suggesting that smoking history may be an influencing factor when predicting KRAS mutation status in patients with NSCLC, but not in patients with EGFR − tumors. Furthermore, glszm_SZNUN was found to be statistically significant, similar to Wang's finding, 35 possibly because both studies considered EGFR mutation status when predicting the KRAS mutation status.…”

“…In comparison, our study included more patients and showed impressive performance. Among studies predicting KRAS mutation status, only the study by Wang et al 35 considered the mutual exclusivity of EGFR and KRAS. They demonstrated that EGFR mutation is an essential predictor of KRAS mutation and optimized the model's performance to predict KRAS mutation status by adding the known EGFR mutation status to CT and PET/CTbased radiomics models.…”

“…In comparison, our study included more patients and showed impressive performance. Among studies predicting KRAS mutation status, only the study by Wang et al 35 . considered the mutual exclusivity of EGFR and KRAS.…”

Prediction of oncogene mutation status in non-small cell lung cancer: A systematic review and meta-analysis with a special focus on artificial-intelligence-based methods

“…In 24 studies, no information on treatment was detailed, although in some of them image acquisition before surgery 31, 36-41 , before polymerase chain reaction (PCR) 42 , or before pathological diagnosis 43 was detailed as an inclusion criterion. In five studies 19, 44-47 , authors specify that patients had not received radiotherapy or chemotherapy, but no information on targeted therapy was provided. Finally, only one study 48 out of the 89 included in the systematic review, which did not meet the inclusion criteria to be considered for the meta-analysis, included patients who had received treatment with tyrosine kinase inhibitors (TKIs).…”

“…Four studies met the inclusion criteria for the meta-analysis assessing models for KRAS mutation prediction 47, 50, 54, 62 , among which, three of them also developed models for EGFR mutation prediction 50, 54, 62 . KRAS/EGFR models were independently built except in one study, in which a multi-channel multi-task DL model for the prediction of both KRAS and EGFR mutations was developed 50 .…”