Therapeutic Response Assessment Of Non-Small Cell Lung Cancer Treated With Molecular Targeting Drugs Using DCE-MRI And A Radiomics Approach Based On CT Texture Features

Section IPilot Study on Icotinib and Endostar as First Line Therapy in Advanced Non-Small Cell Lung Cancer Patients Harboring EGFR Activating Mutations using Quantitative Dynamic Contrast Enhanced MRI and CT Texture AnalysisBackground:It is unclear about the clinical outcome of the combination of icotinib and rh-endostatin(endostar)in treating advanced non-small cell lung cancer(NSCLC)patients harboring epidermal growth factor receptor(EGFR)activating mutations.This single-arm pilot study aims to investigate the preliminary efficacy and safety of the combination therapy for those patients.Materials and Methods:Patients with histologically confirmed nonsquamous advanced NSCLC who had exon 19 del or L858R were included.All patients received icotinib(125 mg po TID)plus endostar(15 mg civ for ten days,every 3 weeks)until presence of disease progression or unacceptable toxicity.The primary endpoint was objective response rate(ORR)at 24 weeks,and secondary endpoint included progression-free survival(PFS),overall survival(OS)and safety.In addition,exploratory evaluation was performed using dynamic contrast enhanced MRI(DCE-MRI)to analyze the tumor vascular permeability parameter,Ktrans to facilitate early prediction of response.We also assessed the treatment response using non-contrast-enhanced computed tomography(CT)texture-based radiomics approach.Results:Ten patients have been enrolled in the pilot study.The median age was 60 years old(range 30-68 years old),with 7 female and 3 male patients.There were 6 patients with EGFR exon 19 del,3 patients with L858R mutation,and 1 patient with L858R and S768I mutation.The preliminary results showed the clinical ORR of 50%(1 complete response,4 partial responses,and 5 stable diseases)at 24 weeks and a mean reduction in tumor size of 32.5%.Median PFS was 8.29(95%CI:5.40-11.19)months.Median follow-up time was 26.2 months.Compared to baseline,the lowest post-therapy Ktrans was 0.22 and 0.40,with a decrease of 52:4%and 7.5%,for responding and non-responding patients,respectively.Responding patients showed a larger reduction in Ktrans after a single dose,compared to nonresponding patients.In responding group,the tumor Ktrans dropped as early as seven days after initial therapy.The dynamic changes of Ktrans were consistent with clinical outcome of tumor responses with correlation coefficient of 0.40.CT texture analysis suggested that skewness and hara entroy were two independent characteristic variables to predict the therapeutic response in NSCLC patients treated with icotinib and endostar.The overall tolerability of the combination was good,as there were no toxicities of Common Terminology Criteria for Adverse Events(CTC-AE)4.0 grade 3 or greater.Conclusions:The combination of icotinib and endostar was effective and safe.Serial Ktrans derived from DCE-MRI could be used as a non-invasive imaging biomarker to predict the tumor response after treatment,to optimize the regimen and facilitate the identification of the best patient population who may potentially benefit from this combination regimen.A radiomic discriminate model was built based on post-therapy CT texture features,which demonstrated a good performance in predicting the therapeutic response in NSCLC patients treated with icotinib and endostar.Section IITherapeutic Response Assessment of Non-Small Cell Lung Cancer Patients Treated With Apatinib:A Radiomics Approach based on CT Texture FeaturesBackground:Apatinib is a novel small molecular drug targeting vascular endothelial growth factor receptor-2(VEGFR-2),which is currently being studied in multiple tumor types.The purpose of this study was to assess the treatment response in non-small cell lung cancer(NSCLC)patients enrolled in a clinical trial of apatinib according to the response evaluation criteria in solid tumors(RECIST)using non-contrast-enhanced computed tomography(CT)texture-based radiomics approach.Methods:A total of 19 NSCLC patients from our single center participated in the currently undergoing multi-center phase III ANSWER study of apatinib(NCT 02332512).Patients were categorized as responders(CR and PR)and non-responders(SD and PD)according to RECIST criteria.Radiomic texture features were extracted from target lesions in post-therapy CT of NSCLC.Lasso regression was used to establish a model to discriminate between responders and non-responders.The performance of the model was assessed with ROC in both internal and independent validation cohorts.Results:Altogether,108 CT scans were performed.Among them,75 scans were randomly selected as internal validation group(70%),while the remaining 33 scans(30%)were identified as an independent validation group.Three hundred and eighty-four CT texture parameters were extracted and 21 out of 384 CT texture were finally selected for the model.The area under the curve(AUC)of ROC was 0.903 in the internal validation group,and that of the independent validation group was 0.714.Conclusions:A radiomic discriminate model was built based on post-therapy CT texture features,which demonstrated a good performance in assessing the therapeutic response in NSCLC patients treated with apatinib.