Search

Abstract Background To develop and validate a preoperative nomogram model combining the radiomics signature and clinical features for preoperative prediction of visceral pleural invasion (VPI) in lung nodules presenting as part‐solid density. Methods We retrospectively reviewed 156 patients with pathologically confirmed invasive lung adenocarcinomas after surgery from January 2016 to August 2019. The patients were split into training and validation sets by a ratio of 7:3. The radiomic features were extracted with the aid of FeAture Explorer Pro (FAE). A CT‐based radiomics model was constructed to predict the presence of VPI and internally validated. Multivariable regression analysis was conducted to construct a nomogram model, and the performance of the models were evaluated with the area under the receiver operating characteristic curve (AUC) and compared with each other. Results The enrolled patients were split into training (n = 109) and validation sets (n = 47). A total of 806 features were extracted and the selected 10 optimal features were used in the construction of the radiomics model among the 707 stable features. The AUC of the nomogram model was 0.888 (95% CI: 0.762–0.961), which was superior to the clinical model (0.787, 95% CI: 0.643–0.893; p = 0.049) and comparable to the radiomics model (0.879, 95% CI: 0.751–0.965; p > 0.05). The nomogram model achieved a sensitivity of 90.5% and a specificity of 76.9% in the validation dataset. Conclusions The nomogram model could be considered as a noninvasive method to predict VPI with either highly sensitive or highly specific diagnoses depending on clinical needs.

Abstract Background Segmentectomy has been recommended for ground glass opacity (GGO)‐dominant small‐sized non–small cell lung cancer (NSCLC) or those with GGO component. Pure solid NSCLC is a special sub‐type and has an inferior prognosis. Whether segmentectomy could achieve comparable long‐term outcomes with lobectomy for pure solid small‐sized NSCLC remained controversial. This study aimed to compare the prognosis of segmentectomy and lobectomy for pure solid NSCLC. Methods NSCLC patients with a pure solid nodule (≤2 cm) who received segmentectomy or lobectomy between January 2010 and June 2019 were retrospectively screened. Log‐rank test, univariable, and multivariable Cox regression analyses were used for prognostic comparison. Further, the propensity score matching analysis was adopted to yield a matched cohort. Results After screening, 344 pure solid NSCLC patients with a median follow‐up time of 56 months were reserved. Among them, 98 patients underwent segmentectomy and the other 246 subjects received lobectomy. The lobectomy group had a larger tumor size, a higher rate of lymph node metastasis than the segmentectomy arm. Generally, patients with segmentectomy had a better disease‐free survival (DFS) (p = 0.011) and overall survival (OS) (p = 0.028) than those with lobectomy. However, the multivariable Cox regression analysis indicated that no significant survival difference existed between segmentectomy and lobectomy after adjusting the potential confounding factors (DFS: hazard ratio [HR], 0.72; 95% confidence interval [CI], 0.30–1.77, p = 0.476; OS: HR, 0.36; 95% CI, 0.08–1.59, p = 0.178). Consistently, in the propensity score matched cohort, segmentectomy (n = 74) yielded similar DFS (p = 0.960) and OS (p = 0.320) with lobectomy (n = 74). Conclusions Segmentectomy could achieve comparable oncological outcomes with lobectomy for pure solid small‐sized NSCLC.