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.

Allopregnanolone in the brain: protecting pregnancy and birth outcomes

A successful pregnancy requires multiple adaptations in the mother's brain that serve to optimise foetal growth and development, protect the foetus from adverse prenatal programming and prevent premature delivery of the young. Pregnancy hormones induce, organise and maintain many of these adaptations. Steroid hormones play a critical role and of particular importance is the progesterone metabolite and neurosteroid, allopregnanolone. Allopregnanolone is produced in increasing amounts during pregnancy both in the periphery and in the maternal and foetal brain. This review critically examines a role for allopregnanolone in both the maternal and foetal brain during pregnancy and development in protecting pregnancy and birth outcomes, with particular emphasis on its role in relation to stress exposure at this time. Late pregnancy is associated with suppressed stress responses. Thus, we begin by considering what is known about the central mechanisms in the maternal brain, induced by allopregnanolone, that protect the foetus(es) from exposure to harmful levels of maternal glucocorticoids as a result of stress during pregnancy. Next we discuss the central mechanisms that prevent premature secretion of oxytocin and consider a role for allopregnanolone in minimising the risk of preterm birth. Allopregnanolone also plays a key role in the foetal brain, where it promotes development and is neuroprotective. Hence we review the evidence about disruption to neurosteroid production in pregnancy, through prenatal stress or other insults, and the immediate and long-term adverse consequences for the offspring. Finally we address whether progesterone or allopregnanolone treatment can rescue some of these deficits in the offspring.