ABSTRACT
Objective:To develop and validate the models based on mixed enhanced computed tomography (CT) radiomics and deep learning features, and evaluate the efficacy for differentiating pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC) before surgery.Methods:The clinical data of 201 patients with surgically resected and histopathologically confirmed PASC (PASC group) and 332 patients with surgically resected histopathologically confirmed PDAC (PDAC group) who underwent enhanced CT within 1 month before surgery in the First Affiliated Hospital of Naval Medical University from January 2011 to December 2020 were retrospectively collected. The patients were chronologically divided into a training set (treated between January 2011 and January 2018, 156 patients with PASC and 241 patients with PDAC) and a validation set (treated between February 2018 and December 2020, 45 patients with PASC and 91 patients with PDAC) according to the international consensus on the predictive model. The nnU-Net model was used for pancreatic tumor automatic segmentation, the clinical and CT images were evaluated, and radiomics features and deep learning features during portal vein phase were extracted; then the features were dimensionally reduced and screened. Binary logistic analysis was performed to develop the clinical, radiomics and deep learning models in the training set. The models' performances were determined by area under the ROC curve (AUC), sensitivity, specificity, accuracy, and decision curve analysis (DCA).Results:Significant differences were observed in tumor size, ring-enhancement, upstream pancreatic parenchymal atrophy and cystic degeneration of tumor both in PASC and PDAC group in the training and validation set (all P value <0.05). The multivariable logistic regression analysis showed the tumor size, ring-enhancement, dilation of the common bile duct and upstream pancreatic parenchymal atrophy were associated with PASC significantly in the clinical model. The ring-enhancement, dilation of the common bile duct, upstream pancreatic parenchymal atrophy and radiomics score were associated with PASC significantly in the radiomics model. The ring-enhancement, upstream pancreatic parenchymal atrophy and deep learning score were associated with PASC significantly in the deep learning model. The diagnostic efficacy of the deep learning model was highest, and the AUC, sensitivity, specificity, and accuracy of the deep learning model was 0.86 (95% CI 0.82-0.90), 75.00%, 84.23%, and 80.60% and those of clinical and radiomics models were 0.81 (95% CI 0.76-0.85), 62.18%, 85.89%, 76.57% and 0.84 (95% CI 0.80-0.88), 73.08%, 82.16%, 78.59% in the training set. In the validation set, the area AUC, sensitivity, specificity, and accuracy of deep learning model were 0.78 (95% CI 0.67-0.84), 68.89%, 78.02% and 75.00%, those of clinical and radiomics were 0.72 (95% CI 0.63-0.81), 77.78%, 59.34%, 65.44% and 0.75 (95% CI 0.66-0.84), 86.67%, 56.04%, 66.18%. The DCA in the training and validation sets showed that if the threshold probabilities were >0.05 and >0.1, respectively, using the deep learning model to distinguish PASC from PDAC was more beneficial for the patients than the treat-all-patients as having PDAC scheme or the treat-all-patients as having PASC scheme. Conclusions:The deep learning model based on CT automatic image segmentation of pancreatic neoplasm could effectively differentiate PASC from PDAC, and provide a new non-invasive method for confirming PASC before surgery.
ABSTRACT
Objective@#To investigate the factors that impacts of therapeutic effect in advanced non-small cell lung cancer (NSCLC) patients with mild tumor enlargement and the rational therapeutic strategy for them.@*Methods@#The clinicopathological features and prognostic data of advanced NSCLC patients whose sum of tumor longest diameters with 0 to 20% increase were retrospectively explored, and the Cox proportional hazards model was used to analyze the independent prognostic factors in patients.@*Results@#The median progression-free survival (PFS) of 54 patients with the original regimen was 87 days, significantly less than 168 days of the median PFS of 49 patients with replacing regimen (P<0.001). The median PFS of other chemotherapeutic regiems (154 days) and the targeted therapy (287 days) were longer than the origional therapy (P<0.05 for all). The left 7 patients received radiotherapy. Receiver operating characteristic (ROC) curve indicated a significant difference in the PFS when the maximal cut-off value of tumor enlargement ratio was 7%. Univariate analysis of patients with targeted therapy after disease progression showed that gender, pathological type, clinical stage, lung metastasis and tumor enlargement ratio were the prognostic factors (all of P<0.05). Multivariate analysis showed that the tumor enlargement ratio was an independent prognostic factor (P=0.001). Single factor analysis showed that the chemotherapeutic regimens before and after disease progression were prognostic factors of patients received chemotherapy after disease progression (P<0.05). Cox multivariate analysis showed that the chemotherapeutic regimen after disease progression was an independent prognostic factor of patients (P=0.004). In the patients whose tumor enlargement ratio was 0 to 7%, Univariate analysis showed that chemotherapeutic regimen before tumor enlargement was a prognostic factor (P=0.030), while Cox multivariate analysis showed that it was not an independent prognostic factor (P=0.560). In the patients whose tumor enlargement ratio was 7.1% to 20%, single factor analysis showed that pathological type, bone metastasis and chemotherapeutic regimen after disease progression were prognostic factors (all of P<0.05), and Cox multivariate analysis showed that all of them were independent prognostic factors of these patients (all of P<0.05).@*Conclusions@#To the advanced NSCLC patients whose tumor enlargement ratio is 0 to 20%, the PFS of patients receive replacing regimen is longer than that of patients receive original regimen. There is a significant difference in the PFS when the maximal cut-off value of tumor enlargement ratio is 7%. To patients undergo second-line chemotherapy before disease progression and the tumor enlargement ratio is 7.1% to 20%, the PFS of patients receive replacing regimen is significantly extended. Dual drug replacing regimen is especially benefit to the adenocarcinoma patients without bone metastasis.
ABSTRACT
Objective: To evaluate the effects of vascular endothelial growthfactor A (VEGFA) and vascular endothelial growth factor receptor2 (VEGFR2) on disease-free survival (DFS) of patients with lungadenocarcinoma receiving surgery.Methods: Immunohistochemistry (IHC) was performed to detect theexpressions of VEGFA and VEGFR2 proteins in adenocarcinoma tissues from 114 patients after surgery. The information on clinical characteristics includinggender, age, smoking status, tumor size, number of positive lymph nodes (PLNs), clinicalstage and treatment after surgery was collected, and the associations of VEGFA and VEGFR2expressions with the clinical characteristics were analyzed. The COX proportional hazardsregression model was used to identify the independent prognostic factors for DFS.Results: The IHC result showed that the positive rates of VEGFA and VEGFR2 expressions inadenocarcinoma tissue samples were 46.49% (53/114) and 46.49% (53/114), respectively.There was no evidence indicating that VEGFA expression was significantly associated withthe clinical characteristics of patients with lung adenocarcinoma, but VEGFR2 expression wassignificantly correlated with the tumor size (P = 0.03). COX proportional hazards regressionmodel revealed that VEGFA and VEGFR2 expressions had no significant effects on patients'DFS; the tumor size > 4 cm (relative risk: 2.29; 95% confidence interval: 1.32-3.97; P = 0.003)and the number of PLNs ≥ 2 (relative risk: 2.15; 95% confidence interval: 1.27-3.64; P = 0.005)were independent factors to predict DFS of patients with lung adenocarcinoma after surgery.Conclusion: For patients with lung adenocarcinoma receiving surgery, VEGFA and VEGFR2expressions have no significant correlation with DFS; the tumor size > 4 cm and the numberof PLNs ≥ 2 may be the independent factors affecting DFS.
ABSTRACT
Objective: To evaluate the clinical indications of CD151 in patients with lung adenocarcinoma with positive expressions of vascular endothelial growth factor A (VEGFA) or vascular endothelial growth factor receptor (VEGFR). Methods: The expressions of VEGFA, VEGFR1, VEGFR2 and CD151 in 116 specimens of patients with lung adenocarcinoma after surgery were detected by immunohistochemistry. The association of CD151 expression with the clinical features of patients with lung adenocarcinoma with positive expression of VEGFA or VEGFR was analyzed. The effect of CD151 expression on the disease-free survival (DFS) of patients with lung adenocarcinoma with positive expression of VEGFA or VEGFR was evaluated. Results: The positive rates of VEGFA, VEGFR1, VEGFR2 and CD151 in lung adenocarcinoma tissues were 69.83% (81/116), 69.83% (81/116), 44.83% (52/116), and 42.24% (49/116), respectively. For patients with lung adenocarcinoma with positive expression of VEGFA, positive expression of CD151 was positively correlated with clinical TNM stage (r = 0.24, P = 0.04) as well as lymph node metastasis (r = 0.26, P = 0.02). CD151 was an independent factor predicting DFS of patients with lung adenocarcinoma with positive expression of VEGFA [hazard ratio (HR) = 1.80, 95% confidence interval (CI): 1.00 - 3.19, P = 0.048]. The median DFS of CD151-positive patients with positive expression of VEGFA was significantly shorter than that of CD151-negative patients (20 vs 34 months, P < 0.05). For patients with lung adenocarcinoma with positive expression of VEGFR1, positive expression of CD151 was positively correlated with TNM stage (r = 0.28, P = 0.01) and lymph node metastasis (r = 0.31, P < 0.01). Moreover, CD151 was an independent factor predicting DFS of patients with lung adenocarcinoma with positive expression of VEGFR2 (HR = 2.10 C95% CI: 1.02 - 4.33, P = 0.044), and the median DFS of CD151-positive patients with positive expression of VEGFR2 was significantly shorter than that of CD151-negative patients (21 vs 42 months, P < 0.05). Conclusion: CD151 is an independent factor predicting DFS of patients with lung adenocarcinoma with positive expression of VEGFA or VEGFR2.