FetNet: a recurrent convolutional network for occlusion identification in fetoscopic videos

To compare fetoscopic laser surgery with amniodrainage in the treatment of twin-to-twin transfusion syndrome (TTTS) diagnosed after 26 weeks of gestation. A retrospective cohort study. Leiden University Medical Centre, a tertiary referral hospital for fetal therapy. Between January 1991 and February 2006, 21 TTTS cases were diagnosed and treated after 26 weeks of gestation. Treatment of TTTS consisted of either amniodrainage or fetoscopic laser coagulation of vascular anastomoses. adverse outcome (intrauterine or neonatal death, major neonatal morbidity and/or severe cerebral injury). Secondary outcome: gestational age at birth. Eleven TTTS cases were treated with amniodrainage and ten with laser surgery. Median gestational age at birth in the amniodrainage group and in the laser surgery group was 29 and 31 weeks, respectively (P = 0.17) All infants were born alive. Major neonatal morbidity occurred more often in the amniodrainage group than in the laser surgery group, 27% (6/22) and 0% (0/20), respectively (P = 0.02). Severe cerebral injury in the amniodrainage group and in the laser surgery group occurred in 23% (5/22) and 15% (3/20) of infants, respectively (P = 0.70). Neonatal mortality in the amniodrainage group and in the laser surgery group was 14% (3/22) and 0% (0/20), respectively (P = 0.23). Overall adverse outcome was 36% (8/22) in the amniodrainage group and 15% (3/20) in the laser surgery group (P = 0.17). In TTTS diagnosed after 26 weeks of gestation, amniodrainage and laser surgery both result in 100% survival. However, infants born after laser surgery have less major neonatal morbidity.

To evaluate the efficiency of the Doppler examination of umbilical arterial blood flow for the antenatal diagnosis and the monitoring of fetal condition during intrauterine treatment of twin-to-twin transfusion syndrome (TTTS), we studied 33 pairs of twins including 5 TTTS cases. In all cases umbilical arterial blood flow was examined by Doppler ultrasound and pulsatility index (PI) was calculated as umbilical arterial impedance. In twins with TTTS, PI of the recipient was outside the normal range and the difference of PI was greater than +0.5. In discordant twins without TTTS and concordant twins, the PI was within the normal range and the difference of PI ranged from -0.5 to +0.5. In 2 cases these findings were found before the appearance of fetal hydrops. In 2 TTTS cases transmaternal digitalization prevented the development of hydrops in the recipient. The difference of PI decreased with improvement in the fetal condition, and vice versa. Our data suggested that, in cases with TTTS, Doppler examination of umbilical arterial blood flow was effective in predicting fetal hydrops. Doppler was also very useful for monitoring the fetal condition during intrauterine treatment.

An analysis of machine learning models for sentiment analysis of Tamil code-mixed data

PurposeNo randomized controlled trials of treatment of twin‐to‐twin transfusion syndrome (TTTS) exist. Since severely preterm neonatal survival has increased over time, survival as an outcome measure is confounded by calendar time. The diagnosis‐to‐delivery interval is a calendar year independent measure of success of treatment. We wished to evaluate whether treatment of TTTS is associated with a lengthening of the diagnosis‐to‐delivery interval.MethodsMEDLINE search supplemented by careful reference review. All TTTS series were included where the following information on each patient was available: survival, fetal demise, gestational age (GA) at diagnosis and diagnosis to delivery interval in days.Inclusion criteriaGA ≤ 29 weeks and diagnosis by ultrasound in the absence of maternal symptoms. Cases undergoing multiple types of treatment were excluded. Data were evaluated by Kruskal–Wallis anova, logistic regression & Wilcoxon rank sum testing.ResultsThe 8 publications used included the following cases: controls (n = 16), amnioreduction (n = 61), septostomy (n = 12), and fetoscopic laser occlusion of chorioangiopagus vessels (FLOC) (n = 51). FLOC therapy showed a significantly longer diagnosis‐to‐delivery interval compared to amnioreduction (median 75 vs. 56 days) (p = 0.01). There was no difference in overall survival, at least one survivor, or number of fetal deaths between the 4 groups. Logistic regression using at least one survivor as the dependent variable revealed a positive association with GA at diagnosis and with diagnosis to delivery interval, a negative correlation with fetal death, and no correlation with treatment group.ConclusionsFLOC therapy for TTTS is associated with a longer diagnosis‐to‐delivery interval compared to amnioreduction without a significant increase in survival. The lack of increase in survival appears to be due to a small sample size.

The accurate estimation of energy expenditure from simple objective accelerometry measurements provides a valuable method for investigating the effect of physical activity (PA) interventions or population surveillance. Methods have been evaluated previously, but none utilize the temporal aspects of the accelerometry data. In this study, we investigated the energy expenditure prediction from acceleration measured at the subjects’ hip, wrist, thigh, and back using recurrent neural networks utilizing temporal elements of the data. The acceleration was measured in children (N = 33) performing a standardized activity protocol in their natural environment. The energy expenditure was modelled using Multiple Linear Regression (MLR), stacked long short-term memory (LSTM) networks, and combined convolutional neural networks (CNN) and LSTM. The correlation and mean absolute percentage error (MAPE) were 0.76 and 19.9% for the MLR, 0.882 and 0.879 and 14.22% for the LSTM, and, with the combined LSTM-CNN, the best performance of 0.883 and 13.9% was achieved. The prediction error for vigorous intensities was significantly different (p < 0.01) from those of the other intensity domains: sedentary, light, and moderate. Utilizing the temporal elements of movement significantly improves energy expenditure prediction accuracy compared to other conventional approaches, but the prediction error for vigorous intensities requires further investigation.

Path planning algorithms generally require several steps including mapping, localization, sensor data processing, etc. Deep learning-based approach has been proposed to achieve end-to-end path planning, alleviating human design tasks and saving the cost of building maps. In this paper, a CNN-LSTM model which combines convolutional neural network (CNN) with Long Short-Term Memory (LSTM) is constructed to accomplish the path planning task of mobile robots. The CNN structure extracts environment features from the sensor data and calculates the proper command velocity while the LSTM module aims to learn the relationship between continuous actions and smooth the velocity of the robot. The input data of the model is acquired by a lidar, which abstracts the environment information and increases the generalization capability of different environments. In the Robot Operating System (ROS)-based simulator, the proposed model is tested in both the training map and a more complex new map. It performs well in the path planning task even in the untrained map. Compared to CNN model, the CNN-LSTM model has a great advantage in continuous planning and velocity smoothing. Furthermore, both the linear and angular velocity calculated by this model is within limited range and real time performance of this algorithm is satisfactory.

COVID-19 pandemic has indeed plunged the global community especially African countries into an alarming difficult situationculminating into a great deal amounts of catastrophes such as economic recession, political instability and loss of jobs. Thepandemic spreads exponentially and causes loss of lives. Following the outbreak of the omicron new variant of concern,forecasting and identification of the COVID-19 infection cases is very vital for government at various levels. Hence, havingknowledge of the spread at a particular point in time, swift actions can be taken by government at various levels with a view toaccordingly formulate new policies and modalities towards minimizing the trajectory of the consequences of COVID-19 pandemicto both public health and economic sectors. Here, a potent combination of Convolutional Neural Network (CNN) learning algorithm along with Long Short Term Memory(LSTM) learning algorithm has been proposed in this work in order to produce a hybrid of a deep learning algorithm ConvolutionalNeural Network - Long Short Term Memory (CNN-LSTM) for forecasting COVID-19 infection cases particularly in Nigeria, SouthAfrica and Botswana. Forecasting models for COVID-19 infection cases in Nigeria, South Africa and Botswana, were developedfor 10 days using deep learning-based approaches namely CNN, LSTM and CNN-LSTM deep learning algorithm respectively. The models were evaluated on the basis of four standard performance evaluation metrics which include accuracy, MSE, MAEand RMSE respectively. However, the CNN-LSTM deep learning-based forecasting model achieved the best accuracy of98.30%, 97.60%, and 97.74% for Nigeria, South Africa and Botswana respectively; and in the same manner, achieved lesserMSE, MAE and RMSE values compared to models developed with CNN and LSTM respectively. Taken together, the CNN-LSTM deep learning-based forecasting model for COVID-19 infection cases in Nigeria, South Africaand Botswana dramatically surpasses the two other DL based forecasting models (CNN and LSTM) for COVID-19 infectioncases in Nigeria, South Africa and Botswana in terms of not only the best accuracy of with 98.30%, 97.60%, and 97.74% but alsoin terms of lesser MSE, MAE and RMSE.

This study addressed the issues related to the difficulty of determining the operating status of machine tool spindle bearings due to the high rotational speeds and rapid temperature fluctuations. This paper presents an optimized model that combines Convolutional Neural Networks (CNNs) and Informer to dynamically predict the temperature rise process of bearings. Taking the H7006C angular contact ball bearing as the research object, a combination of experimental data and simulations was used to obtain the training dataset. Next, a model for predicting the temperature rise of the bearing was constructed using CNN + Informer and the structural parameters were optimized. Finally, the model’s generalization ability was then verified by predicting the bearing temperature rise process under various working conditions. The results show that the error of the simulation data source model was less than 1 °C at steady state; the temperature error of the bearing temperature rise prediction model was less than 0.5 °C at both the temperature rise and steady-state stages under variable rotational speeds and variable load conditions compared to Informer and Long Short Term Memory (LSTM) models; the maximum prediction error of the operating conditions outside the dataset was less than 0.5 °C, and the temperature rise prediction model has a high accuracy, robustness, and generalization capability.

The benefits of fetoscopic laser photocoagulation (FLP) for treatment of twin-to-twin transfusion syndrome (TTTS) have been recognized for over a decade, yet access to FLP remains limited in many settings. This means at a population level, the potential benefits of FLP for TTTS are far from being fully realized. In part, this is because there are many centers where the case volume is relatively low. This creates an inevitable tension; on one hand, wanting FLP to be readily accessible to all women who may need it, yet on the other, needing to ensure that a high degree of procedural competence is maintained. Some of the solutions to these apparently competing priorities may be found in novel training solutions to achieve, and maintain, procedural proficiency, and with the increased utilization of 'competence based' assessment and credentialing frameworks. We suggest an under-utilized approach is the development of collaborative surgical services, where pooling of personnel and resources can improve timely access to surgery, improve standardized assessment and management of TTTS, minimize the impact of the surgical learning curve, and facilitate audit, education, and research. When deciding which centers should offer laser for TTTS and how we decide, we propose some solutions from a collaborative model.

Urban air quality index forecasting using multivariate convolutional neural network based customized stacked long short-term memory model

With the rapid development of Natural Language Processing (NLP) technologies, text steganography methods have been significantly innovated recently, which poses a great threat to cybersecurity. In this paper, we propose a novel attentional LSTM-CNN model to tackle the text steganalysis problem. The proposed method firstly maps words into semantic space for better exploitation of the semantic feature in texts and then utilizes a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) recurrent neural networks to capture both local and long-distance contextual information in steganography texts. In addition, we apply attention mechanism to recognize and attend to important clues within suspicious sentences. After merge feature clues from Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), we use a softmax layer to categorize the input text as cover or stego. Experiments showed that our model can achieve the state-of-art result in the text steganalysis task.

Human Activity Recognition (HAR) based on data from wearable sensors has become an attractive research topic thanks to its applications in different fields such as healthcare and smart environments. Recently, the advancement of deep learning with capability to perform automatically high-level feature extraction has achieved promising results. However, the performance of the deep learning models depends deeply on the characteristics of the datasets such as the number of classes, the inter-similarity and intra-variation. Therefore, directly comparing these models has become difficult since a wide variety of experimental protocols, evaluation metrics, and datasets are employed. In this paper, for the first time, a systematic evaluation of several deep learning models for HAR from wearable sensors is provided. In particular, three models named Convolutional Neural Network (CNN) [1], DeepConvLSTM - a combination of CNN and Long Short Term Memory (LSTM) [2], and SensCapsNet - a Capsule Neural Network for wearable sensor-based HAR [3] were implemented and evaluated on three benchmark datasets that are 19NonSens, CMDFall, and UCI-HAR dataset. Moreover, to have an intuitive explanation of deep learning models, a visualization of features learnt from these models is given. The evaluation codebase and results will be made publicly available for community use.

Fetal laser surgery has emerged as the preferred treatment of twin‐to‐twin transfusion syndrome (TTTS). However, the limited field of view of the fetoscope and the complexity of the procedure make the treatment challenging. Therefore, preoperative planning and intraoperative guidance solutions have been proposed to cope with these challenges. This review uncovers the literature on computer‐assisted software solutions focused on TTTS. These solutions are classified by the pre‐ or intraoperative phase of the procedure and further categorized by discussed hardware and software approaches. In addition, it evaluates the current maturity of technologies by the technology readiness level and enumerates the necessary aspects to bring these new technologies to clinical practice.

Background/Purpose: We report a case study of jejunal atresia and the results of a systematic literature review of all reported cases of bowel complications occurring after fetoscopic laser ablation (FLA) for the treatment of twin-to-twin transfusion syndrome (TTTS). Methods: A systematic literature review was performed of bowel complications after FLA for TTTS according to PRISMA guidelines. Results: There are 11 published cases of small bowel atresia, 5 cases of necrotising enterocolitis (NEC), and 2 cases with foetal bowel perforations. Recipient twins were more likely to be affected by small bowel atresia (7 recipient and 4 donor cases) and NEC (3 recipient and 2 donor twins). Prenatal ultrasonographic abnormalities were demonstrated in 7 out of 9 cases with bowel atresia and in both cases of bowel perforation. The overall survival rate for neonates with bowel complications after FLA is 72%, but is much lower for co-twins at 22%. The survival rates for jejunoileal atresia and NEC are 91 and 40%, respectively. Conclusions: It is uncertain as to whether these bowel anomalies are due to bowel ischaemia associated with TTTS, the treatment with FLA, or a combination of both. Cases with prenatal abdominal ultrasonographic abnormalities after FLA should have close prenatal and postnatal assessment to detect bowel complications.

With the development of 5G technology, internet traffic has surged dramatically, presenting severe challenges to cybersecurity. Considering that network traffic exhibits temporal correlation, it can be used as a basis for identifying network attacks. In this paper, a joint framework of network traffic interpolation and intrusion detection is proposed. First, by leveraging historical network traffic, traffic characteristics can be obtained, allowing for preemptive prevention of network attacks. To obtain network features at equal time intervals, the Lagrange interpolation method is introduced. Second, a deep learning algorithm combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) Networks is proposed to extract spatiotemporal features from network traffic, distinguishing between normal and abnormal network activities. Experimental results based on real network traffic dataset show that the intrusion detection accuracy using CNN and LSTM can reach above 90%, which shows that the proposal can achieve reliable intrusion detection to defend against cyber attacks.