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]

PURPOSE The aim of this study was to evaluate the diagnostic performance of iodine uptake parameters using dual-energy computed tomography (DECT) in discriminating inflammatory nodules from malignant tumors. METHODS This retrospective study included 116 solid pulmonary nodules from 112 patients who were admitted to our hospital between January and September 2018. All nodules were confirmed by surgery or puncture. The degree of enhancement of a single-section region of interest was evalu ated. After total tumor volume-of-interest segmentation, the mean iodine density of the whole tumor was measured. Meanwhile, iodine uptake parameters, including total iodine uptake vol ume, total iodine concentration, vital iodine uptake volume, and vital iodine concentration, were calculated, and a predictive model was established. The overall ability to discriminate between inflammatory and malignant nodules was analyzed using an independent samples t-test for normally distributed variables. The diagnostic accuracy and prognostic performance of DECT parameters were evaluated and compared using receiver operating characteristic curve analysis and logistic regression analysis. A multivariate logistic regression analysis was used to determine the prognostic factors and goodness-of-fit of the whole tumor mean iodine and iodine uptake parameters for discriminating malignant nodules. RESULTS There were 116 non-calcified nodules, including 64 inflammatory nodules and 52 malignant nodules. The degree of enhancement in malignant nodules was significantly lower than that in inflammatory nodules (P=.043). All iodine uptake parameters in malignant nodules were signifi cantly higher than those in inflammatory nodules (P < .001). The area under the receiver operat ing curve value, accuracy, sensitivity, and specificity of the established model based on iodine uptake parameters were 0.803, 76.72%, 82.69%, and 84.37%, respectively, which exhibited bet ter diagnostic performance than the degree of enhancement on weighted average images with respective values of 0.609, 59.48%, 61.54%, and 59.38%. CONCLUSION The iodine uptake parameters of DECT exhibited better diagnostic accuracy in discriminating inflammatory nodules from malignant nodules than the degree of enhancement on weighted average images.