Deep Learning Model for Quality Assessment of Urinary Bladder Ultrasound Images using Multi-scale and Higher-order Processing.

Autonomous Ultrasound Image Quality Assessment (US-IQA) is a promising tool to aid the interpretation by practicing sonographers and to enable the future robotization of ultrasound procedures. However, autonomous US-IQA has several challenges. Ultrasound images contain many spurious artifacts, such as noise due to handheld probe positioning, errors in the selection of probe parameters and patient respiration during the procedure. Further, these images are highly variable in appearance with respect to the individual patient's physiology. We propose to use a deep Convolutional Neural Network (CNN), USQNet, which utilizes a Multi-scale and Local-to-Global Second-order Pooling (MS-L2GSoP) classifier to conduct the sonographer-like assessment of image quality. This classifier first extracts features at multiple scales to encode the inter-patient anatomical variations, similar to a sonographer's understanding of anatomy. Then, it uses second-order pooling in the intermediate layers (local) and at the end of the network (global) to exploit the second-order statistical dependency of multi-scale structural and multi-region textural features. The L2GSoP will capture the higher-order relationships between different spatial locations and provide the seed for correlating local patches, much like a sonographer prioritizes regions across the image. We experimentally validated the USQNet for a new dataset of the human urinary bladder ultrasound images. The validation involved first with the subjective assessment by experienced radiologists' annotation, and then with state-of-the-art CNN networks for US-IQA and its ablated counterparts. The results demonstrate that USQNet achieves a remarkable accuracy of 92.4% and outperforms the SOTA models by 3 - 14% while requiring comparable computation time.

Robotic ultrasound: An initial feasibility study.

BACKGROUND: Performing ultrasound during the current pandemic time is quite challenging. To reduce the chances of cross-infection and keep healthcare workers safe, a robotic ultrasound system was developed, which can be controlled remotely. It will also pave way for broadening the reach of ultrasound in remote distant rural areas as well. AIM: To assess the feasibility of a robotic system in performing abdominal ultrasound and compare it with the conventional ultrasound system. METHODS: A total of 21 healthy volunteers were recruited. Ultrasound was performed in two settings, using the robotic arm and conventional hand-held procedure. Images acquired were analyzed by separate radiologists. RESULTS: Our study showed that the robotic arm model was feasible, and the results varied based on the organ imaged. The liver images showed no significant difference. For other organs, the need for repeat imaging was higher in the robotic arm, which could be attributed to the radiologist's learning curve and ability to control the haptic device. The doctor and volunteer surveys also showed significant comfort with acceptance of the technology and they expressed their desire to use it in the future. CONCLUSION: This study shows that robotic ultrasound is feasible and is the need of the hour during the pandemic.

The Association of Health-Related Fitness and Chronic Absenteeism Status in New York City Middle School Youth.

BACKGROUND: Extensive research demonstrates the benefits of fitness on children's health and academic performance. Although decreases in health-related fitness may increase school absenteeism, multiple years of prospective, child-level data are needed to examine whether fitness changes predict subsequent chronic absenteeism status. METHODS: Six cohorts of New York City public school students were followed from grades 5-8 (2006/2007-2012/2013; N = 349,381). A longitudinal 3-level logistic generalized linear mixed model with random intercepts was used to test the association of individual children's changes in fitness and 1-year lagged chronic absenteeism. RESULTS: The odds of chronic absenteeism increased 27% [odds ratio (OR) 95% confidence interval (CI), 1.25-1.30], 15% (OR 95% CI, 1.13-1.18), 9% (OR 95% CI, 1.07-1.11), and 1% (OR 95% CI, 0.98-1.04), for students who had a >20% decrease, 10%-20% decrease, <10% increase or decrease, and 10%-20% increase in fitness, respectively, compared with >20% fitness increase. CONCLUSION: These findings contribute important longitudinal evidence to a cross-sectional literature, demonstrating reductions in youth fitness may increase absenteeism. Given only 25% of youth aged 12-15 years achieve the recommended daily 60 minutes or more of moderate to vigorous physical activity, future work should examine the potential for youth fitness interventions to reduce absenteeism and foster positive attitudes toward lifelong physical activity.

The association of fitness and school absenteeism across gender and poverty: a prospective multilevel analysis in New York City middle schools.

PURPOSE: One-fifth to one-third of students in high poverty, urban school districts do not attend school regularly (missing ≥6 days/year). Fitness is shown to be associated with absenteeism, although this relationship may differ across poverty and gender subgroups. METHODS: Six cohorts of New York City public school students were followed up from grades 5 to 8 during 2006/2007-2012/2013 (n = 349,381). Stratified three-level longitudinal generalized linear mixed models were used to test the association between changes in fitness and 1-year lagged child-specific days absent across gender and poverty. RESULTS: In girls attending schools in high/very high poverty areas, greater improvements in fitness the prior year were associated with greater reductions in absenteeism (P = .034). Relative to the reference group (>20% decrease in fitness composite percentile scores from the prior year), girls with a large increase in fitness (>20%) demonstrated 10.3% fewer days absent (incidence rate ratio [IRR] 95% confidence interval [CI]: 0.834, 0.964), followed by those who had a 10%-20% increase in fitness (9.2%; IRR 95% CI: 0.835, 0.987), no change (5.4%; IRR 95% CI: 0.887, 1.007), and a 10%-20% decrease in fitness (3.8%; IRR 95% CI: 0.885, 1.045). In girls attending schools in low/mid poverty areas, fitness and absenteeism also had an inverse relationship, but no clear trend emerged. In boys, fitness and absenteeism had an inverse relationship but was not significant in either poverty group. CONCLUSIONS: Fitness improvements may be more important to reducing absenteeism in high/very high poverty girls compared with low/mid poverty girls and both high/very high and low/mid poverty boys. Expanding school-based physical activity programs for youth particularly in high poverty neighborhoods may increase student attendance.

Individual-Level Fitness and Absenteeism in New York City Middle School Youths, 2006-2013.

INTRODUCTION: Youth health-related fitness positively affects academic outcomes, although limited research has focused on the relationship between fitness and school absenteeism. We examined the longitudinal association between individual children's fitness and lagged school absenteeism over 4 years in urban middle schools. METHODS: Six cohorts of New York City public school students were followed from grades 5 through 8 (school years 2006-2007 through 2012-2013; n = 349,381). A 3-level longitudinal generalized linear mixed model was used to test the association of change in fitness composite percentile scores and 1-year lagged child-specific days absent. RESULTS: Adjusted 3-level negative binomial models showed that students with a more than 20% increase, 10% to 20% increase, less than 10% increase or decrease, and 10% to 20% decrease in fitness from the year prior had 11.9% (95% confidence interval [CI], 7.2-16.8), 6.1% (95% CI, 1.0-11.4), 2.6% (95% CI, -1.1 to 6.5), and 0.4% (95% CI, -4.3 to 5.4) lower absenteeism compared with students with a more than 20% fitness decrease. CONCLUSION: Cumulative effects of fitness improvement could have a significant impact on child absenteeism over time, particularly in high-need subgroups. Future research should examine the potential for school-based fitness interventions to reduce absenteeism rates, particularly for youths who have fitness drop-offs in adolescence.

Household environment and behavioral determinants of respiratory tract infection in infants and young children in northern Bangladesh.

OBJECTIVES: Respiratory tract infections (RTI) are one of the leading causes of under-five mortality in Bangladesh. Solid biomass fuels are the main source of domestic fuel used for cooking across Bangladesh, leading to smoke and pollution exposure in the home. This article aims to identify risk factors for RTI among children aged under five years in Bangladesh with a particular focus on the household environment, fuel use, and cooking practices. METHODS: A cross-sectional household-health survey was carried out in 321 households in northern Bangladesh. The survey included care-giver interviews on cooking practices, child health, and household behaviors during cooking. Health status of the youngest child (under five years) from each household was recorded through maternal interviews, medical diagnosis, and assessment of biomarkers (C-reactive protein (CRP), hemoglobin) from finger-prick blood samples. Anthropometric status (weight, height) was recorded. RESULTS: Children who spent ≥30 minutes/day within 5 feet of the stove during cooking had a significantly increased risk of moderate/severe RTI compared with children spending <30 minutes/day close to the stove (OR = 2.15, 95%CI: 1.20-3.86, P = 0.01), independent of socio-economic status (SES), biomass fuel type (wood, dung, plant-derived, compressed rice husks), child age, anthropometric status, CRP and hemoglobin. CONCLUSIONS: In environments with a heavy reliance on solid biomass fuels, the amount of time a child spends near the stove during cooking may be an important risk for RTI. These novel findings from Bangladesh warrant further investigation of mother-infant behaviors during cooking in relation to child health, to ascertain whether the association is likely to be causal.

The effects of changes in physical fitness on academic performance among New York City youth.

PURPOSE: To evaluate whether a change in fitness is associated with academic outcomes in New York City (NYC) middle-school students using longitudinal data and to evaluate whether this relationship is modified by student household poverty. METHODS: This was a longitudinal study of 83,111 New York City middle-school students enrolled between 2006-2007 and 2011-2012. Fitness was measured as a composite percentile based on three fitness tests and categorized based on change from the previous year. The effect of the fitness change level on academic outcomes, measured as a composite percentile based on state standardized mathematics and English Language Arts test scores, was estimated using a multilevel growth model. Models were stratified by sex, and additional models were tested stratified by student household poverty. RESULTS: For both girls and boys, a substantial increase in fitness from the previous year resulted in a greater improvement in academic ranking than was seen in the reference group (girls: .36 greater percentile point improvement, 95% confidence interval: .09-.63; boys: .38 greater percentile point improvement, 95% confidence interval: .09-.66). A substantial decrease in fitness was associated with a decrease in academics in both boys and girls. Effects of fitness on academics were stronger in high-poverty boys and girls than in low-poverty boys and girls. CONCLUSIONS: Academic rankings improved for boys and girls who increased their fitness level by >20 percentile points compared to other students. Opportunities for increased physical fitness may be important to support academic performance.

Survival of newborns: implications for achieving the millennium development goal in Bangladesh.

The global burden of neonatal deaths is around 37% of all under-five deaths (UNICEF 2008). In Bangladesh, neonatal deaths account for almost half of all under-five mortality. Most newborn deaths in Bangladesh take place at home and in the absence of a skilled hand. The target of Millennium Development Goal 4 for Bangladesh is to reduce under-five mortality by two thirds by 2015 from 1990 levels. The objectives of this article are to give an overview of newborn health in Bangladesh and provide a strategy for further reducing under-five mortality to achieve MDG 4. Data for this study were obtained from the Bangladesh Demographic and Health Survey (BDHS) 2004 data set (National Institute of Population and Training [NIPORT] et al. 2005). According to the BDHS, under-five mortality in Bangladesh declined from 133 per 1000 live births in 1991 to 88 per 1000 in 2001, about 4.1% per year. However, the decline was faster between 1991 and 1997 than from 1997 to 2001. The BDHS shows that while neonatal deaths were 39% of all under-five deaths in 1991, they constituted almost half in 2001. The highest concentration of newborn deaths occurred during delivery and within the first 24 hours of birth. Reducing newborn deaths will be an important strategy to achieve MDG 4.