Search

BackgroundFirst-line surveillance on hepatitis B virus (HBV)-infected populations with B-mode ultrasound is relatively limited to identifying hepatocellular carcinoma (HCC) without elevated α-fetoprotein (AFP). To improve the present HCC surveillance strategy, the state of the art of artificial intelligence (AI), a deep learning (DL) approach, is proposed to assist in the diagnosis of a focal liver lesion (FLL) in HBV-infected liver background.MethodsOur proposed deep learning model was based on B-mode ultrasound images of surgery that proved 209 HCC and 198 focal nodular hyperplasia (FNH) cases with 413 lesions. The model cohort and test cohort were set at a ratio of 3:1, in which the test cohort was composed of AFP-negative HBV-infected cases. Four additional deep learning models (MobileNet, Resnet50, DenseNet121, and InceptionV3) were also constructed as comparative baselines. To evaluate the models in terms of diagnostic power, sensitivity, specificity, accuracy, confusion matrix, F1-score, and area under the receiver operating characteristic curve (AUC) were calculated in the test cohort.ResultsThe AUC of our model, Xception, achieved 93.68% in the test cohort, superior to other baselines (89.06%, 85.67%, 83.94%, and 78.13% respectively for MobileNet, Resnet50, DenseNet121, and InceptionV3). In terms of diagnostic power, our model showed sensitivity, specificity, accuracy, and F1-score of 96.08%, 76.92%, 86.41%, and 87.50%, respectively, and PPV, NPV, FPR, and FNR calculated from the confusion matrix were respectively 80.33%, 95.24%, 23.08%, and 3.92% in identifying AFP-negative HCC from HBV-infected FLL cases. Satisfactory robustness of our proposed model was shown based on 5-fold cross-validation performed among the models above.ConclusionsOur DL approach has great potential to assist B-mode ultrasound in identifying AFP-negative HCC from FLL found in surveillance of HBV-infected patients.

Background/AimsPancreatic ductal adenocarcinoma (PDAC) can occur in different parts of the pancreas. This study aimed to identify clinicopathological characteristics independently correlated with the prognosis of PDAC of the pancreatic head/uncinate (PHC) or body-tail (PBTC), and to develop novel nomograms for predicting cancer-specific survival (CSS) according to different primary cancer locations.Methods1160 PDAC patients were retrospectively enrolled and assigned to training and test sets with each set divided into PHC and PBTC groups. Comparative analysis of clinicopathologic characteristics, survival analysis, and multivariate analysis were performed. Independent factors were identified and used for constructing nomograms. The performance of the nomograms was validated in the test set.ResultsPrimary tumor location was an independent risk factor for prognosis of PDAC after surgery. Specially, gender, fasting blood glucose, and preoperative cancer antigen 19-9 were significantly associated with prognosis of PHC, whereas age, body mass index, and lymph nodes were significantly correlated with the prognosis of PBTC. A significant difference in prognosis was found between PHC and PBTC in stage Ia and stage III. Three nomograms were established for predicting the prognosis for PDAC, PHC, and PBTC. Notably, these nomograms were calibrated modestly (c-indexes of 0.690 for PDAC, 0.669 for PHC, and 0.704 for PBTC), presented better accuracy and reliability than the 8th AJCC staging system, and achieved clinical validity.ConclusionsPHC and PBTC share the differential clinical-pathological characteristics and survival. The nomograms show good performance for predicting prognosis in PHC and PBTC. Therefore, these nomograms hold potential as novel approaches for predicting survival of PHC and PBTC patients after surgery.