Congenital heart disease (CHD) is the most common fetal birth defect disease, which can seriously threaten the health and life of children. Echocardiography is the most commonly used diagnostic method for fetal CHD. The standard cardiac view planes of the fetus are used for the diagnosis of CHD on echocardiography. Recently deep learning methods were used for standard cardiac view planes recognition of fetuses. However, these studies did not consider the impact of imbalanced sample size on recognition. The recognition performance of fetal heart view planes using different deep learning models is compared. Specifically, the dataset used includes samples of congenital heart disease. An improved method for fetal cardiac view planes classification with unbalanced samples is proposed. It adopts a two-stage training method with weight decay and maximum norm restriction techniques. The experimental results validate the performance of the method proposed.

BACKGROUND: Breast diseases are a significant health threat for women. With the fast-growing BSGI data, it is becoming increasingly critical for physicians to accurately diagnose benign as well as malignant breast tumors. OBJECTIVE: The purpose of this study is to diagnose benign and malignant breast tumors utilizing the deep learning model, with the input of breast-specific gamma imaging (BSGI). METHODS: A benchmark dataset including 144 patients with benign tumors and 87 patients with malignant tumors was collected and divided into a training dataset and a test dataset according to the ratio of 8:2. The convolutional neural network ResNet18 was employed to develop a new deep learning model. The model proposed was compared with neural network and autoencoder models. Accuracy, specificity, sensitivity and ROC were used to evaluate the performance of different models. RESULTS: The accuracy, specificity and sensitivity of the model proposed are 99.1%, 98.8% and 99.3% respectively, which achieves the best performance among all methods. Additionally, the Grad-CAM method is used to analyze the interpretability of the diagnostic results based on the deep learning model. CONCLUSION: This study demonstrates that the proposed deep learning method could help physicians diagnose benign and malignant breast tumors quickly as well as reliably.

Objective:To evaluate the diagnostic value of the convolution neural network model DenseNet121 based on deep learning in the diagnosis of end-stage renal disease (ESRD).Methods:In this retrospective study, 489 kidney ultrasound images of patients diagnosed with end-stage renal disease from January 1, 2019 to September 30, 2019 and 450 kidney ultrasound images of healthy controls were selected at China-Japan Friendship Hospital. The deep learning-based supervised convolutional neural network model DenseNet121 was used for network training and verification. According to whether it was end-stage renal disease or not, the prediction results of the deep learning-based model were compared with the prediction results of professional imaging physicians. Receiver operating characteristic (ROC) curve analysis was used to evaluate the performance of the deep learning-based model, the accuracy, specificity, sensitivity, and area under the curve (AUC) were used as metrics to compare the performance of the deep learning-based model and professional imaging physicians, and Delong was used to compare the difference of AUC.Results:The prediction accuracy of professional imaging physicians for end-stage renal disease was 89.36%, the sensitivity was 81.63%, the specificity was 97.77%, and the AUC was 0.897. The prediction accuracy of the deep learning-based convolution neural network model DenseNet121 for end-stage renal disease was 93.51%, the sensitivity was 96.12%, the specificity was 90.66%, and the AUC was 0.934. Compared with professional physicians, the DenseNet121 model had higher diagnostic ability (Z=3.034, P=0.002).Conclusion:The ultrasonic diagnosis method based on deep learning shows high diagnostic performance, and it has the potential to assist professional imaging physicians in the diagnosis of end-stage renal disease.

目的 基于剪切波弹性成像(SWE)量化参数和卷积神经网络建立深度学习(DL)模型预测肾脏病变.方法 采集94例肾脏病变患者(病例组)和109名健康人(对照组)的肾脏超声SWE量化参数.利用卷积神经网络建立DL模型,比较DL模型和支持向量机、随机森林模型预测肾脏病变的敏感度、特异度、准确率和曲线下面积(AUC).结果 DL模型对预测肾脏病变的敏感度为90.48％,特异度为100％,准确率为95.12％,AUC为0.93;支持向量机模型的敏感度、特异度、准确率和AUC分别为80.74％、80.71％、80.98％、0.90,随机森林模型分别为82.22％、77.87％、80.33％和0.88.DL模型预测敏感度、特异度、准确率和AUC均高于支持向量机和随机森林模型,与支持向量机模型和随机森林模型预测肾脏病变差异均有统计学意义(P均＜0.05).结论 基于SWE量化参数和卷积神经网络的DL模型预测肾脏疾病性能良好,具有一定临床价值.

At present, intelligent ship has become a new hot spot of international maritime research and development. In order to achieve the purpose of safety, reliability, energy conservation, environmental protection, economy and efficiency, Intelligent ship integrates modern information technology, artificial intelligence technology and other new technologies with traditional ship technology. In this essay, the rapid development of intelligent cabin technology in recent years is surveyed. The intelligent cabin technology and the development trend of the current technology is analyzed, and the possible development direction in the future is pointed out. Collection, transmission and storage of sensor data are summarized. The development of status perception of cabin equipment and environment is discussed. Data-driven intelligent applications are summarized, and the development in the future is discussed. Intelligent cabin system is a data driven information system, which involves data acquisition, communication, storage, analysis, visualization and other rich content. Using the data provided by intelligent ship, more and more intelligent applications will be developed for ships.