In recent years Deep Learning has brought about a breakthrough in Medical Image Segmentation. U-Net is the most prominent deep network in this regard, which has been the most popular architecture in the medical imaging community. Despite outstanding overall performance in segmenting multimodal medical images, from extensive experimentations on challenging datasets, we found out that the classical U-Net architecture seems to be lacking in certain aspects. Therefore, we propose some modifications to improve upon the already state-of-the-art U-Net model. Hence, following the modifications we develop a novel architecture MultiResUNet as the potential successor to the successful U-Net architecture. We have compared our proposed architecture MultiResUNet with the classical U-Net on a vast repertoire of multimodal medical images. Albeit slight improvements in the cases of ideal images, a remarkable gain in performance has been attained for challenging images. We have evaluated our model on five different datasets, each with their own unique challenges, and have obtained a relative improvement in performance of 10.15%, 5.07%, 2.63%, 1.41%, and 0.62% respectively.
BackgroundMalnutrition in children under five years remains a significant problem in Bangladesh, despite substantial socio-economic progress and a decade of interventions aimed at improving it. Although several studies have been conducted to identify the important risk factors of malnutrition, none of them assess the role of low birth weight (LBW) despite its high prevalence (36%). This study examines the association between LBW and malnutrition using data from the Bangladesh Demographic and Health Survey (BDHS) 2011 and provides practical guidelines for improving nutritional status of children.MethodsMalnutrition in children is measured in terms of their height-for-age, weight-for-height, and weight-for-age. Children whose Z-scores for either of these indices are below two standard deviations (–2SD) from median of WHO’s reference population are considered as stunted, wasted or underweight, respectively. The association between malnutrition and LBW was investigated by calculating adjusted risk-ratio (RR), which controls for potential confounders such as child’s age and sex, mother’s education and height, length of preceding-birth-interval, access to food, area of residence, household socio-economic status. Adjusted RR was calculated using both Cochran-Mantel-Haenszel approach and multivariable logistic regression models controlling for confounder.ResultsThe prevalence of malnutrition was markedly higher in children with LBW than those with normal birth-weights (stunting: 51% vs 39%; wasting: 25% vs 14% and underweight: 52% vs 33%). While controlling for the known risk factors, children with LBW had significantly increased risk of becoming malnourished compared to their counter part with RR 1.23 (95% CI:1.16–1.30), 1.71 (95% CI:1.53–1.92) and 1.47 (95% CI: 1.38–1.56) for stunting, wasting and underweight, respectively. The observed associations were not modified by factors known to reduce the prevalence of malnutrition, such as higher education of mother, better household socio-economic conditions and longer birth-interval.ConclusionsHigher education of mother, better household socio-economic conditions and prolonged birth intervals alone are not sufficient in bringing about substantial reductions in prevalence of child malnutrition in Bangladesh. Targeted interventions should be designed to reduce prevalence of LBW in addition to improving mother’s education and other socio-demographic conditions.
Prediction of new drug-target interactions is critically important as it can lead the researchers to find new uses for old drugs and to disclose their therapeutic profiles or side effects. However, experimental prediction of drug-target interactions is expensive and time-consuming. As a result, computational methods for predictioning new drug-target interactions have gained a tremendous interest in recent times. Here we present iDTI-ESBoost, a prediction model for identification of drug-target interactions using evolutionary and structural features. Our proposed method uses a novel data balancing and boosting technique to predict drug-target interaction. On four benchmark datasets taken from a gold standard data, iDTI-ESBoost outperforms the state-of-the-art methods in terms of area under receiver operating characteristic (auROC) curve. iDTI-ESBoost also outperforms the latest and the best-performing method found in the literature in terms of area under precision recall (auPR) curve. This is significant as auPR curves are argued as suitable metric for comparison for imbalanced datasets similar to the one studied here. Our reported results show the effectiveness of the classifier, balancing methods and the novel features incorporated in iDTI-ESBoost. iDTI-ESBoost is a novel prediction method that has for the first time exploited the structural features along with the evolutionary features to predict drug-protein interactions. We believe the excellent performance of iDTI-ESBoost both in terms of auROC and auPR would motivate the researchers and practitioners to use it to predict drug-target interactions. To facilitate that, iDTI-ESBoost is implemented and made publicly available at: http://farshidrayhan.pythonanywhere.com/iDTI-ESBoost/.
BackgroundWhen developing a prediction model for survival data it is essential to validate its performance in external validation settings using appropriate performance measures. Although a number of such measures have been proposed, there is only limited guidance regarding their use in the context of model validation. This paper reviewed and evaluated a wide range of performance measures to provide some guidelines for their use in practice.MethodsAn extensive simulation study based on two clinical datasets was conducted to investigate the performance of the measures in external validation settings. Measures were selected from categories that assess the overall performance, discrimination and calibration of a survival prediction model. Some of these have been modified to allow their use with validation data, and a case study is provided to describe how these measures can be estimated in practice. The measures were evaluated with respect to their robustness to censoring and ease of interpretation. All measures are implemented, or are straightforward to implement, in statistical software.ResultsMost of the performance measures were reasonably robust to moderate levels of censoring. One exception was Harrell’s concordance measure which tended to increase as censoring increased.ConclusionsWe recommend that Uno’s concordance measure is used to quantify concordance when there are moderate levels of censoring. Alternatively, Gönen and Heller’s measure could be considered, especially if censoring is very high, but we suggest that the prediction model is re-calibrated first. We also recommend that Royston’s D is routinely reported to assess discrimination since it has an appealing interpretation. The calibration slope is useful for both internal and external validation settings and recommended to report routinely. Our recommendation would be to use any of the predictive accuracy measures and provide the corresponding predictive accuracy curves. In addition, we recommend to investigate the characteristics of the validation data such as the level of censoring and the distribution of the prognostic index derived in the validation setting before choosing the performance measures.
Objective:To obtain projections of the prevalence of childhood malnutrition indicators up to 2030 and to analyse the changes of wealth-based inequality in malnutrition indicators and the degree of contribution of socio-economic determinants to the inequities in malnutrition indicators in Bangladesh. Additionally, to identify the risk factors of childhood malnutrition.Design:Cross-sectional study. A Bayesian linear regression model was used to estimate trends and projections of malnutrition. For equity analysis, slope index, relative index and decomposition in concentration index were used. Multilevel logistic models were used to identify risk factors of malnutrition.Setting:Household surveys in Bangladesh from 1996 to 2014.Participants:Children under the age of 5 years.Results:A decreasing trend was observed for all malnutrition indices. In 1990, predicted prevalence of stunting, wasting and underweight was 55·0, 15·9 and 61·8 %, respectively. By 2030, prevalence is projected to reduce to 28·8 % for stunting, 12·3 % for wasting and 17·4 % for underweight. Prevalence of stunting, wasting and underweight were 34·3, 6·9 and 32·8 percentage points lower in the richest households than the poorest households. Contribution of the wealth index to child malnutrition increased over time and the largest contribution of pro-poor inequity was explained by wealth index. Being an underweight mother, parents with a lower level of education and poorer households were the key risk factors for stunting and underweight.Conclusions:Our findings show an evidence-based need for targeted interventions to improve education and household income-generating activities among poor households to reduce inequalities and reduce the burden of child malnutrition in Bangladesh.
Sexually transmitted disease (STD) in rural Bangladesh is currently a topic of great concern. To date, little information is available in the literature regarding its prevalence. It is now known, however, that the current level of STD awareness among the rural population with regard to modes of transmission and means of prevention is inadequate. In 1994, the MCH-FP Extension Project (Rural) of ICDDR, B surveyed 8674 married women of reproductive age (MWRA) in 4 rural thanas to examine their awareness of STDs. The association between socio-demographic and programmatic factors (variables which affect STD information availability) and awareness of STDs was examined by both bivariate and multivariate analyses. Seven focus group discussions were conducted among groups of government health and family planning workers and paramedics to assess their knowledge of STDs and attitudes about their prevention. Only 12% of the original group had even a basic understanding about STDs and how to protect themselves from them. Twenty-five per cent of the women surveyed had ever heard of either syphilis or gonorrhoea. Of these women, less than half could mention specific mechanisms involved in the transmission of these diseases. Seven per cent reported that syphilis and gonorrhoea are transmitted through sexual intercourse. Thirteen per cent reported that the infections are transmitted from spouses to their partners. Four per cent reported that STDs can be spread by having multiple sexual partners. The results of logistic regression analysis indicate that awareness of STDs was higher among relatively older women than among younger women. Awareness of STDs was most strongly and positively associated with the education of both the women and their husbands. Awareness of STDs was also found to be higher among women who were more socially mobile (e.g. those who frequent cinemas or mothers' clubs). The findings of focus group discussions indicate that family planning and health care service providers have a moderate level of STD awareness. Modes of transmission and means of prevention, however, were areas of weakness. It will, therefore, be necessary, whether to prevent a potential STD epidemic or to combat current STD prevalence, to implement culturally acceptable and affordable means of disseminating knowledge in rural areas of Bangladesh. Training of health care providers will be an essential first step.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.