Ensemble Transfer Learning for Fetal Head Analysis: From Segmentation to Gestational Age and Weight Prediction.

Ultrasound is one of the most commonly used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. Specifically, ultrasound images are routinely utilized to gather fetal information, including body measurements, anatomy structure, fetal movements, and pregnancy complications. Recent developments in artificial intelligence and computer vision provide new methods for the automated analysis of medical images in many domains, including ultrasound images. We present a full end-to-end framework for segmenting, measuring, and estimating fetal gestational age and weight based on two-dimensional ultrasound images of the fetal head. Our segmentation framework is based on the following components: (i) eight segmentation architectures (UNet, UNet Plus, Attention UNet, UNet 3+, TransUNet, FPN, LinkNet, and Deeplabv3) were fine-tuned using lightweight network EffientNetB0, and (ii) a weighted voting method for building an optimized ensemble transfer learning model (ETLM). On top of that, ETLM was used to segment the fetal head and to perform analytic and accurate measurements of circumference and seven other values of the fetal head, which we incorporated into a multiple regression model for predicting the week of gestational age and the estimated fetal weight (EFW). We finally validated the regression model by comparing our result with expert physician and longitudinal references. We evaluated the performance of our framework on the public domain dataset HC18: we obtained 98.53% mean intersection over union (mIoU) as the segmentation accuracy, overcoming the state-of-the-art methods; as measurement accuracy, we obtained a 1.87 mm mean absolute difference (MAD). Finally we obtained a 0.03% mean square error (MSE) in predicting the week of gestational age and 0.05% MSE in predicting EFW.

The Role of Artificial Intelligence in Decoding Speech from EEG Signals: A Scoping Review.

Background: Brain traumas, mental disorders, and vocal abuse can result in permanent or temporary speech impairment, significantly impairing one's quality of life and occasionally resulting in social isolation. Brain-computer interfaces (BCI) can support people who have issues with their speech or who have been paralyzed to communicate with their surroundings via brain signals. Therefore, EEG signal-based BCI has received significant attention in the last two decades for multiple reasons: (i) clinical research has capitulated detailed knowledge of EEG signals, (ii) inexpensive EEG devices, and (iii) its application in medical and social fields. Objective: This study explores the existing literature and summarizes EEG data acquisition, feature extraction, and artificial intelligence (AI) techniques for decoding speech from brain signals. Method: We followed the PRISMA-ScR guidelines to conduct this scoping review. We searched six electronic databases: PubMed, IEEE Xplore, the ACM Digital Library, Scopus, arXiv, and Google Scholar. We carefully selected search terms based on target intervention (i.e., imagined speech and AI) and target data (EEG signals), and some of the search terms were derived from previous reviews. The study selection process was carried out in three phases: study identification, study selection, and data extraction. Two reviewers independently carried out study selection and data extraction. A narrative approach was adopted to synthesize the extracted data. Results: A total of 263 studies were evaluated; however, 34 met the eligibility criteria for inclusion in this review. We found 64-electrode EEG signal devices to be the most widely used in the included studies. The most common signal normalization and feature extractions in the included studies were the bandpass filter and wavelet-based feature extraction. We categorized the studies based on AI techniques, such as machine learning and deep learning. The most prominent ML algorithm was a support vector machine, and the DL algorithm was a convolutional neural network. Conclusions: EEG signal-based BCI is a viable technology that can enable people with severe or temporal voice impairment to communicate to the world directly from their brain. However, the development of BCI technology is still in its infancy.

Public attitudes on social media toward vaccination before and during the COVID-19 pandemic.

With the success of COVID-19 vaccines in clinical trials, vaccination programs are being administered for the population with the hopes of herd immunity. However, the success of any vaccination program depends on the percentage of people willing to get vaccination which is influenced by social, economic, demographic, and vaccine-specific factors. Thus, it is important to understand public attitudes and perceptions toward vaccination. This study aims to measure public attitude toward vaccines and vaccinations before and during the COVID-19 pandemic, using public data from Twitter. A total of 880,586 tweets for 57,529 unique users were included in the study. Most of the tweets were posted in five languages: French, English, Swedish, Dutch, and Italian. These tweets were divided into two time periods: before COVID-19 (T1) and during COVID-19 (T2). This study observed the shift in the sentiments of the public attitude toward vaccines before and during COVID-19 pandemic. Both positive and negative shifts in sentiments were observed for the users of various languages but shifts toward positive sentiments were more prominent during the COVID-19 pandemic.

Artificial Intelligence-Based Models for Predicting Vaccines Critical Tweets: An Experimental Study.

We studied the suitability of Artificial Intelligence (AI)-based models to predict vaccine-critical tweets on the social media platform Twitter. We manually labeled a sample of 800 tweets as either "vaccine-critical" (i.e, anti-vaccine tweets, mentioned concerns related to vaccine safety and efficacy, and are against vaccine mandates or vaccine passports) or "other" (i.e., tweets that are neutral, report news, or are ambiguous) and used them to train and test AI-based models for automatically predicting vaccine-critical tweets. We fine-tuned two pre-trained deep learning-based language models, BERT and BERTweet, and implemented four classical AI-based models, Random Forest, Logistics Regression, Linear Support Vector Machines, and Multinomial Naïve Bayes. We evaluated these AI-based models using f1 score, accuracy, precision, and recall in three-fold cross-validation. We found that BERTweet outperformed all other models using these measures.

A Conceptual Framework for Fetus Head Analysis Based on Ultrasound Images.

Ultrasound images are the most used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. In particular, the obstetrician uses fetus head images to monitor the growth state and identify essential features such as Gestational age (GA), estimated fetus weight (EFW), and brain anatomical structures. However, this work requires an expert obstetrician, and it is time-consuming and costly. Therefore, we proposed an automatic framework by adopting a hybrid approach that combines three components i) automatic segmentation to segment the region of interest (ROI) in the fetus head, ii) measurement extraction to measure the segmented ROI, and iii) anomaly and features detection to predict fetus GA, EFW, and abnormality status.

Toward deep observation: A systematic survey on artificial intelligence techniques to monitor fetus via ultrasound images.

Several reviews have been conducted regarding artificial intelligence (AI) techniques to improve pregnancy outcomes. But they are not focusing on ultrasound images. This survey aims to explore how AI can assist with fetal growth monitoring via ultrasound image. We reported our findings using the guidelines for PRISMA. We conducted a comprehensive search of eight bibliographic databases. Out of 1269 studies 107 are included. We found that 2D ultrasound images were more popular (88) than 3D and 4D ultrasound images (19). Classification is the most used method (42), followed by segmentation (31), classification integrated with segmentation (16) and other miscellaneous methods such as object-detection, regression, and reinforcement learning (18). The most common areas that gained traction within the pregnancy domain were the fetus head (43), fetus body (31), fetus heart (13), fetus abdomen (10), and the fetus face (10). This survey will promote the development of improved AI models for fetal clinical applications.

The role of generative adversarial networks in brain MRI: a scoping review.

The performance of artificial intelligence (AI) for brain MRI can improve if enough data are made available. Generative adversarial networks (GANs) showed a lot of potential to generate synthetic MRI data that can capture the distribution of real MRI. Besides, GANs are also popular for segmentation, noise removal, and super-resolution of brain MRI images. This scoping review aims to explore how GANs methods are being used on brain MRI data, as reported in the literature. The review describes the different applications of GANs for brain MRI, presents the most commonly used GANs architectures, and summarizes the publicly available brain MRI datasets for advancing the research and development of GANs-based approaches. This review followed the guidelines of PRISMA-ScR to perform the study search and selection. The search was conducted on five popular scientific databases. The screening and selection of studies were performed by two independent reviewers, followed by validation by a third reviewer. Finally, the data were synthesized using a narrative approach. This review included 139 studies out of 789 search results. The most common use case of GANs was the synthesis of brain MRI images for data augmentation. GANs were also used to segment brain tumors and translate healthy images to diseased images or CT to MRI and vice versa. The included studies showed that GANs could enhance the performance of AI methods used on brain MRI imaging data. However, more efforts are needed to transform the GANs-based methods in clinical applications.

Vaccine Rollout and Shift in Public Sentiment: Twitter-Based Surveillance Study.

This study aims to find out the variation of Twitter users' sentiment before and after the COVID-19 vaccine rollout. We analyzed all COVID-19 related tweets posted on Twitter within two timeframes: September 2020 (T1) and March 2021 (T2). A total of 3 million tweets from over 132 thousand users were analyzed. We then categorized the users into two groups whose overall sentiment shifted positively or negatively from T1 to T2. Our analysis showed that 27% of users' sentiment shifted from T1 to T2 positively and the users were more confident about vaccine safety and efficacy. Users reported positive sentiments about travelling and the easing of lockdown measures. Also, 20.4% of the users' sentiment shifted negatively from T1 to T2. This group of Twitter users were more concerned about the adverse side effects of the vaccine, the pace of vaccine development as well as the emerging novel coronavirus variants. Interestingly, over half of the users' overall sentiment remained the same in both periods of T1 and T2, indicating indifference about vaccine rollout. We believe that our analysis will support the exploration of public reaction to COVID-19 vaccine rollout and assess policy makers' decision to combat the pandemic.

Thematic Analysis on User Reviews for Depression and Anxiety Chatbot Apps: Machine Learning Approach.

BACKGROUND: Anxiety and depression are among the most commonly prevalent mental health disorders worldwide. Chatbot apps can play an important role in relieving anxiety and depression. Users' reviews of chatbot apps are considered an important source of data for exploring users' opinions and satisfaction. OBJECTIVE: This study aims to explore users' opinions, satisfaction, and attitudes toward anxiety and depression chatbot apps by conducting a thematic analysis of users' reviews of 11 anxiety and depression chatbot apps collected from the Google Play Store and Apple App Store. In addition, we propose a workflow to provide a methodological approach for future analysis of app review comments. METHODS: We analyzed 205,581 user review comments from chatbots designed for users with anxiety and depression symptoms. Using scraper tools and Google Play Scraper and App Store Scraper Python libraries, we extracted the text and metadata. The reviews were divided into positive and negative meta-themes based on users' rating per review. We analyzed the reviews using word frequencies of bigrams and words in pairs. A topic modeling technique, latent Dirichlet allocation, was applied to identify topics in the reviews and analyzed to detect themes and subthemes. RESULTS: Thematic analysis was conducted on 5 topics for each sentimental set. Reviews were categorized as positive or negative. For positive reviews, the main themes were confidence and affirmation building, adequate analysis, and consultation, caring as a friend, and ease of use. For negative reviews, the results revealed the following themes: usability issues, update issues, privacy, and noncreative conversations. CONCLUSIONS: Using a machine learning approach, we were able to analyze ≥200,000 comments and categorize them into themes, allowing us to observe users' expectations effectively despite some negative factors. A methodological workflow is provided for the future analysis of review comments.

Recent Developments in Artificial Intelligence-Based Techniques for Prostate Cancer Detection: A Scoping Review.

Artificial intelligence (AI) techniques can contribute to the early diagnosis of prostate cancer. Recently, there has been a sharp increase in the literature on AI techniques for prostate cancer diagnosis. This review article presents a summary of the AI methods that detect and diagnose prostate cancer using different medical imaging modalities. Following the PRISMA-ScR principle, this review covers 69 studies selected from 1441 searched papers published in the last three years. The application of AI methods reported in these articles can be divided into three broad categories: diagnosis, grading, and segmentation of tissues that have prostate cancer. Most of the AI methods leveraged convolutional neural networks (CNNs) due to their ability to extract complex features. Some studies also reported traditional machine learning methods, such as support vector machines (SVM), decision trees for classification, LASSO, and Ridge regression methods for features extraction. We believe that the implementation of AI-based tools will support clinicians to provide better diagnosis plans for prostate cancer.

A Scoping Review to Find Out Worldwide COVID-19 Vaccine Hesitancy and Its Underlying Determinants.

BACKGROUND: The current crisis created by the coronavirus pandemic is impacting all facets of life. Coronavirus vaccines have been developed to prevent coronavirus infection and fight the pandemic. Since vaccines might be the only way to prevent and stop the spread of coronavirus. The World Health Organization (WHO) has already approved several vaccines, and many countries have started vaccinating people. Misperceptions about vaccines persist despite the evidence of vaccine safety and efficacy. OBJECTIVES: To explore the scientific literature and find the determinants for worldwide COVID-19 vaccine hesitancy as reported in the literature. METHODS: PRISMA Extension for Scoping Reviews (PRISMA-ScR) guidelines were followed to conduct a scoping review of literature on COVID-19 vaccine hesitancy and willingness to vaccinate. Several databases (e.g., MEDLINE, EMBASE, and Google Scholar) were searched to find relevant articles. Intervention- (i.e., COVID-19 vaccine) and outcome- (i.e., hesitancy) related terms were used to search in these databases. The search was conducted on 22 February 2021. Both forward and backward reference lists were checked to find further studies. Three reviewers worked independently to select articles and extract data from selected literature. Studies that used a quantitative survey to measure COVID-19 vaccine hesitancy and acceptance were included in this review. The extracted data were synthesized following the narrative approach and results were represented graphically with appropriate figures and tables. RESULTS: 82 studies were included in this scoping review of 882 identified from our search. Sometimes, several studies had been performed in the same country, and it was observed that vaccine hesitancy was high earlier and decreased over time with the hope of vaccine efficacy. People in different countries had varying percentages of vaccine uptake (28-86.1%), vaccine hesitancy (10-57.8%), vaccine refusal (0-24%). The most common determinants affecting vaccination intention include vaccine efficacy, vaccine side effects, mistrust in healthcare, religious beliefs, and trust in information sources. Additionally, vaccination intentions are influenced by demographic factors such as age, gender, education, and region. CONCLUSIONS: The underlying factors of vaccine hesitancy are complex and context-specific, varying across time and socio-demographic variables. Vaccine hesitancy can also be influenced by other factors such as health inequalities, socioeconomic disadvantages, systemic racism, and level of exposure to misinformation online, with some factors being more dominant in certain countries than others. Therefore, strategies tailored to cultures and socio-psychological factors need to be developed to reduce vaccine hesitancy and aid informed decision-making.

Overview of Technologies Implemented During the First Wave of the COVID-19 Pandemic: Scoping Review.

BACKGROUND: Technologies have been extensively implemented to provide health care services for all types of clinical conditions during the COVID-19 pandemic. While several reviews have been conducted regarding technologies used during the COVID-19 pandemic, they were limited by focusing either on a specific technology (or features) or proposed rather than implemented technologies. OBJECTIVE: This review aims to provide an overview of technologies, as reported in the literature, implemented during the first wave of the COVID-19 pandemic. METHODS: We conducted a scoping review using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) Extension for Scoping Reviews. Studies were retrieved by searching 8 electronic databases, checking the reference lists of included studies and relevant reviews (backward reference list checking), and checking studies that cited included studies (forward reference list checking). The search terms were chosen based on the target intervention (ie, technologies) and the target disease (ie, COVID-19). We included English publications that focused on technologies or digital tools implemented during the COVID-19 pandemic to provide health-related services regardless of target health condition, user, or setting. Two reviewers independently assessed the eligibility of studies and extracted data from eligible papers. We used a narrative approach to synthesize extracted data. RESULTS: Of 7374 retrieved papers, 126 were deemed eligible. Telemedicine was the most common type of technology (107/126, 84.9%) implemented in the first wave of the COVID-19 pandemic, and the most common mode of telemedicine was synchronous (100/108, 92.6%). The most common purpose of the technologies was providing consultation (75/126, 59.5%), followed by following up with patients (45/126, 35.7%), and monitoring their health status (22/126, 17.4%). Zoom (22/126, 17.5%) and WhatsApp (12/126, 9.5%) were the most commonly used videoconferencing and social media platforms, respectively. Both health care professionals and health consumers were the most common target users (103/126, 81.7%). The health condition most frequently targeted was COVID-19 (38/126, 30.2%), followed by any physical health conditions (21/126, 16.7%), and mental health conditions (13/126, 10.3%). Technologies were web-based in 84.1% of the studies (106/126). Technologies could be used through 11 modes, and the most common were mobile apps (86/126, 68.3%), desktop apps (73/126, 57.9%), telephone calls (49/126, 38.9%), and websites (45/126, 35.7%). CONCLUSIONS: Technologies played a crucial role in mitigating the challenges faced during the COVID-19 pandemic. We did not find papers describing the implementation of other technologies (eg, contact-tracing apps, drones, blockchain) during the first wave. Furthermore, technologies in this review were used for other purposes (eg, drugs and vaccines discovery, social distancing, and immunity passport). Future research on studies on these technologies and purposes is recommended, and further reviews are required to investigate technologies implemented in subsequent waves of the pandemic.

The Role of Neural Network for the Detection of Parkinson's Disease: A Scoping Review.

Background: Parkinson's Disease (PD) is a chronic neurodegenerative disorder that has been ranked second after Alzheimer's disease worldwide. Early diagnosis of PD is crucial to combat against PD to allow patients to deal with it properly. However, there is no medical test(s) available to diagnose PD conclusively. Therefore, computer-aided diagnosis (CAD) systems offered a better solution to make the necessary data-driven decisions and assist the physician. Numerous studies were conducted to propose CAD to diagnose PD in the early stages. No comprehensive reviews have been conducted to summarize the role of AI tools to combat PD. Objective: The study aimed to explore and summarize the applications of neural networks to diagnose PD. Methods: PRISMA Extension for Scoping Reviews (PRISMA-ScR) was followed to conduct this scoping review. To identify the relevant studies, both medical databases (e.g., PubMed) and technical databases (IEEE) were searched. Three reviewers carried out the study selection and extracted the data from the included studies independently. Then, the narrative approach was adopted to synthesis the extracted data. Results: Out of 1061 studies, 91 studies satisfied the eligibility criteria in this review. About half of the included studies have implemented artificial neural networks to diagnose PD. Numerous studies included focused on the freezing of gait (FoG). Biomedical voice and signal datasets were the most commonly used data types to develop and validate these models. However, MRI- and CT-scan images were also utilized in the included studies. Conclusion: Neural networks play an integral and substantial role in combating PD. Many possible applications of neural networks were identified in this review, however, most of them are limited up to research purposes.

An Efficient Method to Predict Pneumonia from Chest X-Rays Using Deep Learning Approach.

Pneumonia is a severe health problem causing millions of deaths every year. The aim of this study was to develop an advanced deep learning-based architecture to detect pneumonia using chest X-ray images. We utilized a convolutional neural network (CNN) based on VGG16 architecture consisting of 16 fully connected convolutional layers. A total of 5856 high-resolution frontal view chest X-ray images were used for training, validating, and testing the model. The model achieved an accuracy of 96.6%, sensitivity of 98.1%, specificity of 92.4%, precision of 97.2%, and a F1 Score of 97.6%. This indicates that the model has an excellent performance in classifying pneumonia cases and normal cases. We believe, the proposed model will reduce physician workload, expand the performance of pneumonia screening programs, and improve healthcare service.