CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network

Background At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs. Purpose A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF-ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs). Materials and methods This study is a retrospective analysis of pancreatic unenhanced and enhanced CT images in 63 patients with pancreatic SCNs and 47 patients with MCNs (3 of which were mucinous cystadenocarcinoma) confirmed by pathology from December 2010 to August 2016. Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs). Then, the comparisons of classification results were made based on sensitivity, specificity, precision, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), with pathological results serving as the gold standard. Results Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs. Conclusion The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs. Graphic abstract

Endoscopic ultrasound-guided radiofrequency ablation of pancreatic microcystic serous cystic neoplasms: a retrospective study

Background Endoscopic ultrasound-guided radiofrequency ablation (EUS-RFA) has been increasingly used for the management of various solid pancreatic tumors. This study aimed to evaluate the feasibility and safety of EUS-RFA for serous cystic neoplasms (SCNs). Methods 13 patients with microcystic SCNs with honeycomb appearance underwent EUS-RFA using a 19-gauge RFA needle. Before ablation, cystic fluid was aspirated until a thin layer of fluid remained. Results EUS-RFA was successful in all patients. Seven patients underwent a single session and the remaining six patients underwent a second session of EUS-RFA. One patient (7.7 %) experienced self-limited abdominal pain after EUS-RFA. During a median follow-up period of 9.21 months (interquartile range [IQR] 5.93 – 15.38), the median volume of the SCNs decreased from 37.82 mL (IQR 15.03 – 59.53) at baseline to 10.95 mL (IQR 4.79 – 32.39) at the end of follow-up. A radiologic partial response was achieved in eight patients (61.5 %). Conclusions EUS-RFA is technically feasible and showed an acceptable rate of adverse events for patients with SCNs. A long-term follow-up study is required to evaluate the efficacy of EUS-RFA.