Large-scale annotation dataset for fetal head biometry in ultrasound images.

This dataset features a collection of 3832 high-resolution ultrasound images, each with dimensions of 959×661 pixels, focused on Fetal heads. The images highlight specific anatomical regions: the brain, cavum septum pellucidum (CSP), and lateral ventricles (LV). The dataset was assembled under the Creative Commons Attribution 4.0 International license, using previously anonymized and de-identified images to maintain ethical standards. Each image is complemented by a CSV file detailing pixel size in millimeters (mm). For enhanced compatibility and usability, the dataset is available in 11 universally accepted formats, including Cityscapes, YOLO, CVAT, Datumaro, COCO, TFRecord, PASCAL, LabelMe, Segmentation mask, OpenImage, and ICDAR. This broad range of formats ensures adaptability for various computer vision tasks, such as classification, segmentation, and object detection. It is also compatible with multiple medical imaging software and deep learning frameworks. The reliability of the annotations is verified through a two-step validation process involving a Senior Attending Physician and a Radiologic Technologist. The Intraclass Correlation Coefficients (ICC) and Jaccard similarity indices (JS) are utilized to quantify inter-rater agreement. The dataset exhibits high annotation reliability, with ICC values averaging at 0.859 and 0.889, and JS values at 0.855 and 0.857 in two iterative rounds of annotation. This dataset is designed to be an invaluable resource for ongoing and future research projects in medical imaging and computer vision. It is particularly suited for applications in prenatal diagnostics, clinical diagnosis, and computer-assisted interventions. Its detailed annotations, broad compatibility, and ethical compliance make it a highly reusable and adaptable tool for the development of algorithms aimed at improving maternal and Fetal health.

A comprehensive review of COVID-19 detection techniques: From laboratory systems to wearable devices.

Screening of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) among symptomatic and asymptomatic patients offers unique opportunities for curtailing the transmission of novel coronavirus disease 2019, commonly known as COVID-19. Molecular diagnostic techniques, namely reverse transcription loop-mediated isothermal amplification (RT-LAMP), reverse transcription-polymerase chain reaction (RT-PCR), and immunoassays, have been frequently used to identify COVID-19 infection. Although these techniques are robust and accurate, mass testing of potentially infected individuals has shown difficulty due to the resources, manpower, and costs it entails. Moreover, as these techniques are typically used to test symptomatic patients, healthcare systems have failed to screen asymptomatic patients, whereas the spread of COVID-19 by these asymptomatic individuals has turned into a crucial problem. Besides, respiratory infections or cardiovascular conditions generally demonstrate changes in physiological parameters, namely body temperature, blood pressure, and breathing rate, which signifies the onset of diseases. Such vitals monitoring systems have shown promising results employing artificial intelligence (AI). Therefore, the potential use of wearable devices for monitoring asymptomatic COVID-19 individuals has recently been explored. This work summarizes the efforts that have been made in the domains from laboratory-based testing to asymptomatic patient monitoring via wearable systems.

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.

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.

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.

PCovNet: A presymptomatic COVID-19 detection framework using deep learning model using wearables data.

While the advanced diagnostic tools and healthcare management protocols have been struggling to contain the COVID-19 pandemic, the spread of the contagious viral pathogen before the symptom onset acted as the Achilles' heel. Although reverse transcription-polymerase chain reaction (RT-PCR) has been widely used for COVID-19 diagnosis, they are hardly administered before any visible symptom, which provokes rapid transmission. This study proposes PCovNet, a Long Short-term Memory Variational Autoencoder (LSTM-VAE)-based anomaly detection framework, to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker. The framework was trained and evaluated in two configurations on a publicly available wearable device dataset consisting of 25 COVID-positive individuals in the span of four months including their COVID-19 infection phase. The first configuration of the framework detected RHR abnormality with average Precision, Recall, and F-beta scores of 0.946, 0.234, and 0.918, respectively. However, the second configuration detected aberrant RHR in 100% of the subjects (25 out of 25) during the infectious period. Moreover, 80% of the subjects (20 out of 25) were detected during the presymptomatic stage. These findings prove the feasibility of using wearable devices with such a deep learning framework as a secondary diagnosis tool to circumvent the presymptomatic COVID-19 detection problem.

Effect of gender on childhood maltreatment in the state of Qatar: Retrospective study.

BACKGROUND: International maltreatment studies show a range of results for overall rates of child maltreatment and gender differences. The ISPCAN Child Abuse Screening Tools (ICAST) were designed to reduce variability in data collection. OBJECTIVE: To investigate the influence of gender on the experiences of discipline and maltreatment in childhood among young people in Qatar, informingpractice and policy development. PARTICIPANTS AND SETTING: A representative sample of Qatari youth aged between 18 and 24 years were identified using a cross sectional random household survey. The total number of subjects was 697 of whom 46.8% were male. METHODS: Participants self-administered the ICAST-R (retrospective), which includes questions about exposure below the age of 18 to potentially abusive physical, psychological and sexual behaviors. Verbal consent was obtained following an introductory explanation and assurance ofconfidentiality. RESULTS: At least one form of physical abuse was reported by 22.1% of participants and was significantly higher among males (28.2%) than females (16.7%) p<0.001). A trend for greater abuse was identified among boys aged over five which become statistically significant between 10 -13 years (p=0.001). For psychological abuse the overall rates were very similar, 16.2% for girls and 15.0% for boys. Only 17 (2.5%) of participants reported sexual abuse, with no statistically significant gender difference. CONCLUSIONS: Physical, psychological and sexual abuse all occur in Qatar. This study demonstrates the importance of identifying the role of gender and age when exploring the extent and nature of maltreatment in a population. It allows for better targeting of preventative action.

Comparing disciplinary methods used by mothers in Palestine and Qatar.

This paper explores child disciplinary methods used by parents in Qatar and Palestine. In this study ICAST-P, an internationally recognized tool, was used with mothers reporting on one of their children up to their 12th birthday. It questions about disciplinary methods: nonviolent; physical: moderate and severe; and psychological methods that had been used in the previous year on the index child in the family. A comparative national cross-sectional household survey of mothers aged 25-50 years old was conducted in both Qatar and Palestine, both Arabic Muslim states, but with very different socio-economic and political contexts that place Qataris in a much more advantageous position. Our results show that the 1299 Palestinian mothers interviewed were younger, had more children and less education compared to the 1018 Qatari mothers. Fewer mothers from Palestine were working. The index child in Palestine tended to be younger with 60% being under 5 years, while 73.7% of Qatari children were over 5 years of age. Severe physical disciplinary methods were reported significantly more often, in Palestine, e.g. Kicking the child (P value < 0.001), using hand or pillow to prevent breathing (P value < 0.001) and hitting child with object or fist (P value < 0001). Moderate as well as psychological disciplinary methods were also significantly higher among Palestinian mothers (P value < 0.001). Our results suggest that challenging circumstances that Palestinian mothers experience, as compared to their Qatari peers, are associated with greater prevalence of the harsher forms of discipline. Our findings have policy implications and preventative strategies for child maltreatment in both countries.

Pediatric Traumatic Brain Injury: a 5-year descriptive study from the National Trauma Center in Qatar.

Background: The epidemiologic characteristics and outcomes of pediatric traumatic brain injury (pTBI) have not been adequately documented from the rapidly developing countries in the Arab Middle East. We aimed to describe the hospital-based epidemiologic characteristics, injury mechanisms, clinical presentation, and outcomes of pTBI and analyze key characteristics and determinant of pTBI that could help to make recommendations for policies to improve their care. Methods: We conducted a retrospective observational study in a level 1 trauma center (2010-2014) for all pTBI patients. Data were analyzed and compared according to different patient age groups. Results: Out of 945 traumatic brain injury patients, 167 (17.7%) were ≤ 18 years old with a mean age of 10.6 ± 5.9 and 81% were males. The rate of pTBI varied from 5 to 14 cases per 100,000 children per year. The most affected group was teenagers (15-18 years; 40%) followed by infants/toddlers (≤ 4 years; 23%). Motor vehicle crash (MVC; 47.3%) was the most frequent mechanism of injury followed by falls (21.6%). MVC accounted for a high proportion of pTBI among teenagers (77.3%) and adolescents (10-14 years; 48.3%). Fall was a common cause of pTBI for infants/toddlers (51.3%) and 5-9 years old group (30.3%). The proportion of brain contusion was significantly higher in adolescents (61.5%) and teenagers (58.6%). Teenagers had higher mean Injury Severity Scoring of 24.2 ± 9.8 and lower median (range) Glasgow Coma Scale of 3 (3-15) (P = 0.001 for all). The median ventilatory days and intensive care unit and hospital length of stay were significantly prolonged in the teenage group. Also, pTBI in teenage group showed higher association with pneumonia (46.4%) and sepsis (17.3%) than other age groups (P = 0.01). The overall mortality rate was 13% (n = 22); 11 died within the first 24 h, 7 died between the second and seventh day and 4 died one week post-admission. Among MVC victims, a decreasing trend of case fatality rate (CFR) was observed with age; teenagers had the highest CFR (85.7) followed by adolescents (75.0), young children (33.3), and infants/toddlers (12.5). Conclusions: This local experience to describe the burden of pTBI could be a basis to adopt and form an efficient, tailored strategy for safety in the pediatric population.

Satisfaction with a 2-day communication skills course culturally tailored for medical specialists in Qatar.

OBJECTIVE: Health-care communication skills training may be particularly needed in the Arabian Gulf countries because of the variety of cultures within the physician and patient populations. This study describes the implementation and results of a communication skills training program for physicians in Qatar that assessed previous training, and effect of previous training on participants' course evaluations. MATERIALS AND METHODS: We conducted a 2-day communication skills training course covering seven culturally adapted modules. Educational strategies included large and small group work with the standardized patient, demonstration videos, and lectures. At the end, participants completed a course evaluation survey. Data analysis performed with SPSS; frequencies and percentages were calculated, and Chi-square test applied to evaluate statistical significance. RESULTS: A total of 410 physicians in Qatar have participated in the course over a period of 2 years. Evaluation ratings of the course were high. Participants rated the module on Breaking Bad News as the most useful, and the small group role-play as the most helpful course component. One-third of participants had previously participated in experiential communication skills training. There was no association between previous experience and evaluation of the course. CONCLUSION: Physicians in Qatar positively evaluated a 2-day communication skills course, though the majority of participants did not have any previous exposure to experiential communication skills training.

Contextualizing the Physician Charter on Professionalism in Qatar: From Patient Autonomy to Family Autonomy.

BACKGROUND: The Physician Charter on medical professionalism has been endorsed by professional organizations worldwide, yet it is unclear if this Western framework of professionalism is applicable in non-Western countries. OBJECTIVE: This study examines how physicians practicing in a Middle Eastern context perceive the terms, principles, and commitments outlined in the charter. METHODS: In May 2013, the authors conducted 6 focus groups with 43 clinician-educators practicing at Hamad Medical Corporation in Doha, Qatar, to discuss the applicability of the Physician Charter in a local context. The research team coded and analyzed transcripts to identify sociocultural influences on professionalism. RESULTS: Participants generally expressed agreement with the applicability of the charter's principles to physician professionalism in Qatar. However, 3 contextual factors (religious beliefs and practices, family-centered decision making, and multinationality) complicated the application of the core principles of patient autonomy and social justice. Islamic beliefs reinforced the importance of professional values such as altruism, but presented a barrier to the principle of self-determination for female patients. The family-centered culture in Qatar called for enlarging the scope of patient-centered decision making to include the patient's family. Qatar's multinational population prompted debate over equal treatment and how to conceptualize and implement the principle of social justice. CONCLUSIONS: Several sociocultural contexts influence the conceptualization of the principles of medical professionalism in Qatar. The findings suggest that contextual factors should be considered when developing or adopting a professionalism framework in an international setting and context.

Child discipline in Qatar and Palestine: A comparative study of ICAST-R.

To compare the nature and determinants of child discipline in Qatar and Palestine among young adults through retrospective survey to develop legislation, policies and interventions for effective prevention of child maltreatment, and educational materials to promote positive discipline among parents and caregivers. Cross-sectional random household surveys were conducted in each country (Qataris N=697, Palestinians N=2064) using ISPCAN Child Abuse Screening Tool-Retrospective (ICAST-R) for young adults (18-24 years), to investigate child discipline methods into the maltreatment range. Qatari young adults were more educated (p<0.001) and had more full-time employment (p=0.004) than Palestinian young adults. Qatar reported lower physical and emotional abuse compared to their counterparts in Palestine, e.g. Hit/Punch, Kick (p<0.001) and Insult/Criticize, Threaten to be hurt/killed (p<0.001). Qatari participants found any harsh discipline they received in childhood was not reasonable and not justified compared to Palestinian participants. The more advantaged Qatari population was less likely to experience disciplinary methods that experts developing the ICAST-R defined as abuse compared to Palestinians where the higher incidence of child abuse could be attributed to lower economic advantage, lower level of education and greater exposure to violence. Suggestions are made for future studies in Qatar and Palestine to develop survey methodology with a more culturally appropriate level of intrusion, such as indirect yet meaningful child maltreatment questions.

Poisoning emergency visits among children: a 3-year retrospective study in Qatar.

BACKGROUND: Poisoning in toddlers and infants is almost always unintentional due to their exploratory behavior, which is different from adults. The prevalence and background of childhood poisoning in Qatar is still unknown. The aim of this study is to explore the extent of childhood poisoning in Qatar and, specifically, to describe the frequency of poisoning as a cause of Accident & Emergency (A&E) admission, the demographic profile of affected patients, the circumstances leading to exposure, and the specific agents involved in poisoning among children under age 14 in our setting. METHODS: This study was a cross-sectional survey of children up to 14 years old utilizing retrospective data between October 2009 and October 2012. The data were collected from the childhood poisoning case registry and patient medical records at the Accident and Emergency (A&E) Unit of all the Hamad Medical Corporation hospitals. Pharmacists reviewed all the handwritten medical records. Data written on the data collection form were transferred into excel and later into SPSS version 21. The data were analyzed using frequencies and percentages, and a chi-square test was used for categorical variables. RESULTS: Out of 1179 registered poisoning cases listed in the registry, only 794 cases (67.3%) were usable and included in the final analysis. A&E admissions for unintentional poisoning for children accounted for 0.22% of all A&E admissions from 2009 to 12. The majority of poisoning cases happened among children between 1 and 5 years old (n = 704, 59.7%). Cases were more frequent among non-Qatari than Qatari children (39.4% vs. 28.5%). Most cases occurred in the living room (28.2%) and typically took place in the afternoon (29.2%). Analgesic and antipyretic medicines were the most common agents ingested by children (n = 194, 36.9%), specifically paracetamol (n = 140, 26.6%). CONCLUSIONS: Cases of unintentional poisoning are higher among children aged 1 to 5 years, males and non-Qatari. Most cases occurred in the living room and typically took place in the afternoon. The most common type of poison ingested by children was medicines, i.e., analgesics and antipyretics, specifically paracetamol.

Analysis of pediatric trauma data from a hospital based trauma registry in Qatar.

BACKGROUND: Trauma is the leading killer in the young age children, but data about the injury burden on pediatric population are lacking. The aim of this study is to describe the epidemiology and outcome of the traumatic injuries among children in Qatar. MATERIALS AND METHODS: This is a retrospective analysis of a trauma registry database, which reviewed all cases of serious traumatic injury (ISS ≥ 9) to children aged 0-18 years who were admitted to the national pediatric Level I trauma center at the Hamad General Hospital (HGH), over a period of one year. Data included demographics, day of injuries, location, time, type and mechanism of injuries, co-morbidity, safety equipment use, pre-hospital intubation, mode of pre-hospital transport, Glasgow Coma Scale (GCS), Injury Severity Score (ISS), emergency department (ED) intervention, hospital length of stay and mortality outcome. RESULTS: The incidence of severe pediatric trauma was 163 per 280,000 children who visited the ED of HGH in 2011. Out of them, 83% were male, mean age was 9.6 ± 5.9 years and mortality rate was 1.8%. On presentation to the ED, the mean ISS was 13.9 ± 6.6 and GCS was 13.4 ± 3.8. Over half of the patients needed ICU admission. For the ages 0-4 years, injuries most frequently occurred at home; for 5-9 years (59%) and 15-18 years (68%), the street; and for 10-14 years (50%), sports and recreational sites. The most common mechanisms of injury for the age groups were falls for 0-4 years, motor vehicle collision (MVC) or pedestrian injury for 5-9 years, all-terrain vehicle (ATV)/bicycle injuries for 10-14 years, and MVC injuries for 15-18 years. Head (34%) and long bone (18%) injuries were the most common, with 18% suffering from polytrauma. None of the patients were using safety equipment when injured. CONCLUSION: Traumatic injuries to children have an age- and mechanism-specific pattern in Qatar. This has important implications for the formulation of focused injury prevention programs for the children of Qatar.