Search

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). A retrospective cohort of 514 confirmed pathologically lung ADC in 512 patients after surgery was enrolled. The clinicoradiographic model (model 1) and radiomics model (model 2) were developed with logistic regression. The deep learning model (model 3) was constructed based on the deep learning score (DL-score). The combine model (model 4) was based on DL-score and R-score and clinicoradiographic variables. The performance of these models was evaluated with area under the receiver operating characteristic curve (AUC) and compared using DeLong's test internally and externally. The prediction nomogram was plotted, and clinical utility depicted with decision curve. The performance of model 1, model 2, model 3 and model 4 was supported by AUCs of 0.848, 0.896, 0.906, 0.921 in the Internal validation set, that of 0.700, 0.801, 0.730, 0.827 in external validation set, respectively. These models existed statistical significance in internal validation (model 4 vs model 3, P = 0.016; model 4 vs model 1, P = 0.009, respectively) and external validation (model 4 vs model 2, P = 0.036; model 4 vs model 3, P = 0.047; model 4 vs model 1, P = 0.016, 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 1and model 3 but comparable with the model 2. The combined model can improve preoperative diagnosis in the presence of MPP/SOL pattern in lung ADC in clinical practice. [ABSTRACT FROM AUTHOR]

Visceral pleural invasion (VPI) in stageI lung adenocarcinoma is an independent negative prognostic factor. However, no studies proved any morphologic pattern could be referred to as a prognostic factor. Thus, we aim to investigate the potential prognostic impact of VPI by extracting high-dimensional radiomics features on thin-section computed tomography (CT). A total of 327 surgically resected pathological-N0M0 lung adenocarcinoma 3 cm or less in size were evaluated. Radiomics signature was generated by calculating the contribution weight of each feature and validated using repeated leaving-one-out ten-fold cross-validation approach. The accuracy of proposed radiomics signature for predicting VPI achieved 90.5% with ROC analysis (AUC, 0.938, sensitivity, 90.6%, specificity, 93.2%, PPV: 91.2, NPV: 92.8). The cut-off value allowed separation of patients in the validation data into high-risk and low-risk groups with an odds ratio 12.01. Radiomics signature showed a concordance index of 0.895 and AIC value of 88.9% with regression analysis. Among these radiomics features, percentile 10%, wavEnLL_S_2, S_0_1_SumAverage represented as independent factors for determining VPI. Results suggested that radiomics signature on CT exhibited as an independent prognostic factor in discriminating VPI in lung adenocarcinoma and could potentially help to discriminate the prognosis difference in stage I lung adenocarcinoma.