CT delta-radiomics for identification of advanced EGFR-Mutated lung adenocarcinoma Sensitive to Therapies Targeting EGFR Pathway

Abstract

Purpose: In this study, a non-invasive radiomics method was used to extract a large amount of valuable information from patient CT images (including pre-treatment and follow-up images), and the image features were effectively combined with treatment effect evaluation, aiming to solve the problem of lung adenocarcinoma in patients with EGFR mutation positive. The early efficacy evaluation of cancer EGFR-TKI targeted drugs provides a scientific basis for clinical drug selection and adjustment of treatment plans. Methods: It is planned to include 106 patients with EGFR-TKI targeted therapy for lung adenocarcinoma in Shaoxing People's Hospital (pathologically confirmed EGFR mutation positive), and randomly divide them into a training group and a validation group in a ratio of 7:3. The CT plain scan images of patients before and 2 months after treatment were collected, and the images were segmented by ITK-SNAP software. Perform feature screening and modeling, and draw nomograms, calibration curves, and decision curves. Results: After Lasso dimensionality reduction, three features with non-zero coefficients are extracted between groups, sumEntropy,LongRunLowGreyLevelEmphasis_angle0_offset1, LongRunLowGreyLevelEmphasis_angle0_offset4. The average area under the curve (AUC) of the logistic regression model in the training group and the validation group was 0.778 and 0.773, respectively; the Nomogram chart showed that after the three radiomics parameters were scored, the total score was 0-130, and the corresponding effective The risk was 0.1-0.9; the calibration curve showed that the predicted value and the actual clinical observation value approached a 45° slope, indicating that the model was well calibrated; while the decision curve radiomics model was used to evaluate EGFR-TKI in lung adenocarcinoma Targeted drugs have better clinical benefits when they have early efficacy. Conclusions: The radiomics model established based on the radiomics features of CT unenhanced images has good performance in evaluating the efficacy of EGFR-TKI targeted drugs in the treatment of lung adenocarcinoma, and the final Nomogram map can quantitatively evaluate the curative effect, providing individual patient information.