Abstract
This study was aimed to explore magnetic resonance imaging (MRI) based on deep learning belief network model in evaluating serum bile acid profile and adverse perinatal outcomes of intrahepatic cholestasis of pregnancy (ICP) patients. Fifty ICP pregnant women diagnosed in hospital were selected as the experimental group, 50 healthy pregnant women as the blank group, and 50 patients with cholelithiasis as the gallstone group. Deep learning belief network (DLBN) was built by stacking multiple restricted Boltzmann machines, which was compared with the recognition rate of convolutional neural network (CNN) and support vector machine (SVM), to determine the error rate of different recognition methods on the test set. It was found that the error rate of deep learning belief network (7.68%) was substantially lower than that of CNN (21.34%) and SVM (22.41%) (P < 0.05). The levels of glycoursodeoxycholic acid (GUDCA), glycochenodeoxycholic acid (GCDCA), and glycocholic acid (GCA) in the experimental group were dramatically superior to those in the blank group (P < 0.05). Both the experimental group and the blank group had notable clustering of serum bile acid profile, and the experimental group and the gallstone group could be better distinguished. In addition, the incidence of amniotic fluid contamination, asphyxia, and premature perinatal infants in the experimental group was dramatically superior to that in the blank group (P < 0.05). The deep learning confidence model had a low error rate, which can effectively extract the features of liver MRI images. In summary, the serum characteristic bile acid profiles of ICP were glycoursodeoxycholic acid, glycochenodeoxycholic acid, and glycocholic acid, which had a positive effect on clinical diagnosis. The toxic effects of high concentrations of serum bile acids were the main cause of adverse perinatal outcomes and sudden death.