In the extraction of fetal electrocardiogram (ECG) signal, due to the unicity of the scale of the U-Net same-level convolution encoder, the size and shape difference of the ECG characteristic wave between mother and fetus are ignored, and the time information of ECG signals is not used in the threshold learning process of the encoder’s residual shrinkage module. In this paper, a method of extracting fetal ECG signal based on multi-scale residual shrinkage U-Net model is proposed. First, the Inception and time domain attention were introduced into the residual shrinkage module to enhance the multi-scale feature extraction ability of the same level convolution encoder and the utilization of the time domain information of fetal ECG signal. In order to maintain more local details of ECG waveform, the maximum pooling in U-Net was replaced by Softpool. Finally, the decoder composed of the residual module and up-sampling gradually generated fetal ECG signals. In this paper, clinical ECG signals were used for experiments. The final results showed that compared with other fetal ECG extraction algorithms, the method proposed in this paper could extract clearer fetal ECG signals. The sensitivity, positive predictive value, and F1 scores in the 2013 competition data set reached 93.33%, 99.36%, and 96.09%, respectively, indicating that this method can effectively extract fetal ECG signals and has certain application values for perinatal fetal health monitoring.
Abstract In order to repair the bone defect afteroperation of benign lesion of extremity, the fetal demineralized bone was applied in 10 cases. These cases were followed up for 6 months to 8 years. The results showed that the grafted bone was integrated with the host bone in 6 months. Noadverse effect was found. The demineralized bone did not induce rejection. The advantages of using fetal demineralized bone were as follows: easily obtainable,its preparation and method of storage simple, and low finacial cast.
OBJECTIVE To evaluate the clinical results of repair of bone defect by embryonic bone transplantation. METHODS From January 1994 to June 1999, 148 cases of bone defect were repaired by embryonic bone transplantation following alcohol treatment, there were 63 cases with bone cyst, 42 cases with fibrous dysplasia of bone, 26 cases with giant cell tumor of bone, and 17 cases with enchondroma among them. The maximal bone defect was 3.5 cm x 10.0 cm, while the minimal defect was 0.5 cm x 1.0 cm. RESULTS All of those bone defect with benign tumor were bone union used by embryonic bone transplantation after 3 months to 1 year of operation, the average healing course was 6.2 months, followed up 1 to 6 years, averaged 14 months, no tumor recurrence and no obvious local or system response were observed. CONCLUSION Embryonic bone can be used as a good repairing material of postoperative bone defect of benign tumors, the clinical results are satisfactory.
This review provides an overview of prenatal interventional treatments for fetal congenital heart disease (CHD), with a particular focus on the latest advancements in fetal aortic valvuloplasty (FAV) and fetal pulmonary valvuloplasty (FPV). FAV aims to improve left heart hemodynamics, prevent hypoplastic left heart syndrome (HLHS), and promote biventricular circulation. FPV seeks to improve the natural history of pulmonary atresia with intact ventricular septum (PA/IVS) and critical pulmonary stenosis with intact ventricular septum (CPS/IVS), alleviate right ventricular outflow tract obstruction, and promote biventricular circulation. This article discusses patient selection, technical details, risk assessment, and clinical outcomes for these procedures, highlighting the challenges in current research, including the lack of standardized patient selection criteria and long-term prognostic studies. Additionally, it emphasizes the opportunities and challenges of fetal cardiac intervention (FCI) development in China and proposes recommendations for future improvements and research directions.
Objective To search and review the best clinical evidence to direct the use of ultrasound. Methods After developing clinical questions, we searched the following databases for evidence: PROQUEST (1984 to 2004), SUMSEARCH (1980 to 2004) and The Cochrane Library (Issue 4, 2004). The key words were “repeated ultrasound exposure and children development (outcome)”. Results We found 3 systematic reviews, 3 randomized controlled trials, 1 cohort study and 1 case-control study. Most of the trials concluded that the effects of ultrasound to fetus were to be identified, some of the trials showed that ultrasound exposure could have an effect on fetus growth and language ability after delivery. Conclusions The pregnant women should avoid ultrasound as much as possible.
Objective To define an evidence-based conclusion concerning ultrasound screening for fetal genital system malformations during pregnancy. Methods In order to assess whether or not ultrasound screening for fetal genital system malformations is effective and feasible, we searched The Cochrane Library (Issue 3, 2009), MEDLINE (1981 to 2009), ACP Journal Club (1991 to 2008), and BMJ Clinical Evidence (1999 to 2008) for systematic reviews, randomized controlled trials (RCTs), cohort studies, and controlled clinical trials. Results Five cohort studies and three crosssectional studies were retrieved. The results showed ultrasound screening detected fetal sex determination by the contour of the rump and the angle of the genital tubercle to a horizontal line through the lumbosacral skin surface in the first trimester. Scrotal size and penile length increases with gestational age for male fetuses, and by 32 weeks, bilateral testicular descent was observed in most cases. Ultrasonographic scans, fetal genetic studies, and hormonal assays of amniotic fluid can diagnosis certain diseases, fetal sex differentiation disorders, fetal endocrinal disorders, and chromosome abnormality. Conclusion The findings of this study should reassure physicians and parents alike that ultrasound screening is an reliable option for the prenatal diagnosis of fetal genital system malformations, but more randomized controlled trials are needed to further supply relevant evidence.
Fetal electrocardiogram signal extraction is of great significance for perinatal fetal monitoring. In order to improve the prediction accuracy of fetal electrocardiogram signal, this paper proposes a fetal electrocardiogram signal extraction method (GA-LSTM) based on genetic algorithm (GA) optimization with long and short term memory (LSTM) network. Firstly, according to the characteristics of the mixed electrocardiogram signal of the maternal abdominal wall, the global search ability of the GA is used to optimize the number of hidden layer neurons, learning rate and training times of the LSTM network, and the optimal combination of parameters is calculated to make the network topology and the mother body match the characteristics of the mixed signals of the abdominal wall. Then, the LSTM network model is constructed using the optimal network parameters obtained by the GA, and the nonlinear transformation of the maternal chest electrocardiogram signals to the abdominal wall is estimated by the GA-LSTM network. Finally, using the non-linear transformation obtained from the maternal chest electrocardiogram signal and the GA-LSTM network model, the maternal electrocardiogram signal contained in the abdominal wall signal is estimated, and the estimated maternal electrocardiogram signal is subtracted from the mixed abdominal wall signal to obtain a pure fetal electrocardiogram signal. This article uses clinical electrocardiogram signals from two databases for experimental analysis. The final results show that compared with the traditional normalized minimum mean square error (NLMS), genetic algorithm-support vector machine method (GA-SVM) and LSTM network methods, the method proposed in this paper can extract a clearer fetal electrocardiogram signal, and its accuracy, sensitivity, accuracy and overall probability have been better improved. Therefore, the method could extract relatively pure fetal electrocardiogram signals, which has certain application value for perinatal fetal health monitoring.
Computer analysis of cardiotocography (CTG) is very significant to evaluate fetal status. However, current computer analysis based on traditional classification criteria is not ideal. In order to improve the accuracy of fetal status assessment, we proposed a new method. The new method improves the classification criteria and uses fuzzy set to represent the CTG parameters. And then feature vector is formed by that set to represent the CTG signal. By calculating and comparing the Euclidean distance between the signal feature vector and the standard state feature vector, the corresponding fetal status of the signal can be determined. Experiments showed that compared to the results of the first expert, the accuracy rate of new method was 88.3% which was higher than that (69.9%) of the traditional method, and the false positive rate of new method was 7.2% which was much lower than that (34.9%) of traditional methods. While compared to the results of the second expert, the accuracy of new method was 90.3% which was higher than that (66.0%) of the traditional method, and the false positive rate of new method was 9.0% which was well below the 38.2% of the traditional method. Thus the new method is reliable and effective.