Radiomics-based machine learning and deep learning to predict serosal involvement in gallbladder cancer.

OBJECTIVE: Our study aimed to determine whether radiomics models based on contrast-enhanced computed tomography (CECT) have considerable ability to predict serosal involvement in gallbladder cancer (GBC) patients. MATERIALS AND METHODS: A total of 152 patients diagnosed with GBC were retrospectively enrolled and divided into the serosal involvement group and no serosal involvement group according to paraffin pathology results. The regions of interest (ROIs) in the lesion on all CT images were drawn by two radiologists using ITK-SNAP software (version 3.8.0). A total of 412 features were extracted from the CT images of each patient. The Mann‒Whitney U test was applied to identify features with significant differences between groups. Seven machine learning algorithms and a deep learning model based on fully connected neural networks (f-CNNs) were used for radiomics model construction. The prediction efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis. RESULTS: Through the Mann‒Whitney U test, 75 of the 412 features extracted from the CT images of patients were significantly different between groups (P < 0.05). Among all the algorithms, logistic regression achieved the highest performance with an area under the curve (AUC) of 0.944 (sensitivity 0.889, specificity 0.8); the f-CNN deep learning model had an AUC of 0.916, and the model showed high predictive power for serosal involvement, with a sensitivity of 0.733 and a specificity of 0.801. CONCLUSION: Radiomics models based on features derived from CECT showed convincing performances in predicting serosal involvement in GBC.

Biliary Neuroendocrine Neoplasms: Analysis of Prognostic Factors and Development and Validation of a Nomogram.

BACKGROUND: For this study, we explored the prognostic profiles of biliary neuroendocrine neoplasms (NENs) patients and identified factors related to prognosis. Further, we developed and validated an effective nomogram to predict the overall survival (OS) of individual patients with biliary NENs. METHODS: We included a total of 446 biliary NENs patients from the SEER database. We used Kaplan-Meier curves to determine survival time. We employed univariate and multivariate Cox analyses to estimate hazard ratios to identify prognostic factors. We constructed a predictive nomogram based on the results of the multivariate analyses. In addition, we included 28 biliary NENs cases from our center as an external validation cohort. RESULTS: The median survival time of biliary NENs from the SEER database was 31 months, and the value of gallbladder NENs (23 months) was significantly shorter than that of the bile duct (45 months) and ampulla of Vater (33.5 months, p=0.023). Multivariate Cox analyses indicated that age, tumor size, pathological classification, SEER stage, and surgery were independent variables associated with survival. The constructed prognostic nomogram demonstrated good calibration and discrimination C-index values of 0.783 and 0.795 in the training and validation dataset, respectively. CONCLUSION: Age, tumor size, pathological classification, SEER stage, and surgery were predictors for the survival of biliary NENs. We developed a nomogram that could determine the 3-year and 5-year OS rates. Through validation of our central database, the novel nomogram is a useful tool for clinicians in estimating individual survival among biliary NENs patients.