Value Of Contrast-Enhanced Magnetic Resonance Imaging-T2WI-Based Radiomic Features In Distinguishing Lung Adenocarcinoma From Lung Squamous Cell Carcinoma With Solid Components>8 Mm

Background:Radiomics is one of the research frontiers in the field of imaging and has excellent diagnostic performance.However,there is a lack of MRI-based omics studies on identifying pathological subtypes of lung cancer.Here we explored the value of the contrast-enhanced magnetic resonance imaging(MRI)-T2-weighted imaging(T2WI)-based radiomics analysis in distinguishing Ade from Squ with solid components>8 mm.Methods:A retrospective analysis was performed of a total of 71 lung cancer patients who underwent contrast-enhanced MRI and CT before treatment,and the nodules had solid components≥8 mm in our center from January 2020 to September 2021.All enrolled patients were divided into squamous cell carcinoma and adenocarcinoma groups according to the pathological results.In addition,the two groups were randomly divided into a training set and a validation set in a ratio of about 7:3.Radiomics software was used to extract the relevant radiomics features.The least absolute shrinkage and selection operator(Lasso)was used to screen radiomics features that were most relevant to lung cancer subtypes,thus calculating the radiomics scores(Rad-score)and constructing the radiomics models.Multivariate logistic regression was used to combine relevant clinical features with Rad-score to form combined model nomograms.The receiver operating characteristic(ROC)curves.the area under the ROC curve(AUC),the decision curve analysis(DCA),and the DeLong’s test were used to evaluate the clinical application potentials.Results:In the univariate analysis,gender and smoking history had certain significance in distinguishing Ade from Squ;in the multivariate logistic regression,however,only smoking history alone had a discriminating value,and gender and age were not statistically significant.The radiomics features were extracted from the contrast-enhanced MRI-T2WI images,and 4 features were finally retained after screening and dimensionality reduction by t-test and Lasso regression.The AUCs of the constructed magnetic resonance(MR)-Rad model for differentiating the pathological subtypes of lung cancer were 0.8651 and 0.8438,respectively,in the training and validation sets.Based on the CT images,10 radiomics features were screened out and a CT-Rad model was constructed,and the AUCs in the training set and validation set were 0.8948 and 0.8892,respectively.The AUCs of the MR comprehensive model were为 0.9570 and 0.8016 respectively,in the training and validation sets.The AUCs of the CT comprehensive diagnostic model in the training set and validation set were 0.9316 and 0.8175,respectively.There was no significant difference in diagnostic performance between the MR-Rad model and the CT-Rad model(P>0.05).Conclusions:The contrast-enhanced MRI-T2WI-based radiomics model has a good diagnostic performance in distinguishing Ade from Squ with solid components>8 mm.It is helpful for clinicians to make diagnostic decisions and to carry out individualized treatment and prognosis assessments of patients in advance.However,before this technology can be used in clinical practice,its limitations and obstacles must be solved.