Comparison and Fusion Prediction Model for Lung Adenocarcinoma with Micropapillary and Solid Pattern Using Clinicoradiographic, Radiomics and Deep Learning Features

Purpose: To investigate whether the combination scheme of deep learning score (DL-score) and radiomics can improve preoperative diagnosis in the presence of micropapillary/ solid (MPP/SOL) patterns in lung adenocarcinoma (ADC). Material: and Methods: A retrospective cohort of 514 confirmed pathologically lung ADC in 512 patients after surgery was enrolled. The clinicoradiographic model (model 1) and radiomics model (model2) were developed with logistic regression. The deep learning model (model3) was constructed based on the deep learning score (DL-score). The combine model(model4) was based on DL-score and R-score and clincoradiographic variables. The performance of these models was evaluated with area under the receiver operating characteristic curve (AUC) and compared using DeLong's test. The prediction nomogram was plotted and clinical utility was depicted with decision curve. Results: : The performance of model1, model2, model3 and model4 was supported by AUCs of 0.848, 0.896,0.906, 0.921 in the Testing set, respectively. These models existed statistical significance (model4 vs model3, P=0.016; model4 vs model1, P=0.009, respectively). The decision curve analysis (DCA) demonstrated that model 4 predicting the lung ADC with MPP/SOL structure would be more beneficial than the model 1 but comparable with the model2 and model3. Conclusion: The combined model can improve preoperative diagnosis in the presence of MPP/SOL pattern in lung ADC in clinical practice.