scholarly journals ReCoNet: Multi-level Preprocessing of Chest X-rays for COVID-19 Detection Using Convolutional Neural Networks

2020 ◽  
Author(s):  
Sabbir Ahmed ◽  
Moi Hoon Yap ◽  
Maxine Tan ◽  
Md. Kamrul Hasan
Keyword(s):  
Network Performance ◽  
Data Augmentation ◽  
X Rays ◽  
Modular Architecture ◽  
Learning Loss ◽  
Middle Income ◽  
Middle Income Countries ◽  
Life Threatening ◽  
Multi Level ◽  
End To End

Life-threatening COVID-19 detection from radiomic features has become a dire need of the present time for infection control and socio-economic crisis management around the world. In this paper, a novel convolutional neural network (CNN) architecture, ReCoNet (residual image-based COVID-19 detection network), is proposed for COVID-19 detection. This is achieved from chest X-ray (CXR) images shedding light on the preprocessing task considered to be very useful for enhancing the COVID-19 fingerprints. The proposed modular architecture consists of a CNN-based multi-level preprocessing filter block in cascade with a multi-layer CNN-based feature extractor and a classification block. A multi-task learning loss function is adopted for optimization of the preprocessing block trained end-to-end with the rest of the proposed network. Additionally, a data augmentation technique is applied for boosting the network performance. The whole network when pre-trained end-to-end on the CheXpert open source dataset, and trained and tested with the COVIDx dataset of 15,134 original CXR images yielded an overall benchmark accuracy, sensitivity, and specificity of 97.48%, 96.39%, and 97.53%, respectively. The immense potential of ReCoNet may be exploited in clinics for rapid and safe detection of COVID-19 globally, in particular in the low and middle income countries where RT-PCR labs and/or kits are in a serious crisis.

scholarly journals Accelerating access and scale-up of optimized antiretroviral therapy in low-income and middle-income countries: results of a coordinated end-to-end approach

AIDS ◽  
2021 ◽  
Vol 35 (Supplement 2) ◽  
pp. S165-S171
Author(s):  
Emily Lark Harris ◽  
Katherine Blumer ◽  
Carmen Perez Casas ◽  
Danielle Ferris ◽  
Carolyn Amole ◽  
...  
Keyword(s):  
Antiretroviral Therapy ◽  
Low Income ◽  
Scale Up ◽  
Middle Income ◽  
Middle Income Countries ◽  
End To End

Efficacy of pre-participation cardiac evaluation recommendations among athletes participating in World Athletics Championships

2019 ◽  
Vol 27 (14) ◽  
pp. 1480-1490 ◽  
Author(s):  
Örjan Dahlström ◽  
Paolo Emilio Adami ◽  
Kristina Fagher ◽  
Jenny Jacobsson ◽  
Victor Bargoria ◽  
...  
Keyword(s):  
International Association ◽  
Cost Effective ◽  
Track And Field ◽  
Cross Sectional ◽  
Middle Income ◽  
Web Based ◽  
Middle Income Countries ◽  
Cardiac Evaluation ◽  
Life Threatening ◽  
Very High

Background Athletes competing in athletics (track and field) at international level may be participating with underlying undiagnosed life-threatening cardiovascular conditions. Our objective was to analyse variations in pre-participation cardiac evaluation prevalence among athletes participating in two International Association of Athletics Federations (IAAF) World Athletics Championships, with regard to the human developmental level and global region of their home countries, as well as athletes' age category, gender, event group and medical insurance type. Design Cross-sectional web-based survey. Methods A total of 1785 athletes competing in the IAAF World Under 18 Championships Nairobi 2017 and World Championships London 2017 were invited to complete a pre-participation health questionnaire investigating the experience of a pre-participation cardiac examination. Results A total of 704 (39%) of the athletes participated. Among these, 59% (60% of women; 58% of men) reported that they had been provided at least one type of pre-participation cardiac evaluation. Athletes from very high income countries, Europe and Asia, showed a higher prevalence of at least one pre-participation cardiac evaluation. Conclusions The prevalence of pre-participation cardiac evaluation in low to middle income countries, and the African continent in particular, needs urgent attention. Furthermore, increases in evaluation prevalence should be accompanied by the development of cost-effective methods that can be adopted in all global regions.

scholarly journals Object Detection and Instance Segmentation in Chest X-rays for Tuberculosis Screening

2021 ◽  
Vol 3 (1) ◽  
pp. 1-24
Author(s):  
Terence Griffin ◽  
Yu Cao ◽  
Benyuan Liu ◽  
Maria J. Brunette ◽  
Xinzi Sun
Keyword(s):  
Object Detection ◽  
False Positive Rate ◽  
X Rays ◽  
Tuberculosis Screening ◽  
Screening Process ◽  
Middle Income ◽  
Middle Income Countries ◽  
Positive Rate ◽  
Object Level ◽  
Instance Segmentation

Tuberculosis (TB) is a highly contagious disease leading to the deaths of approximately 2 million people annually. TB primarily affects the lungs and is spread through the air when people cough, sneeze, or spit. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries (LMICs) with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-nobreakdash-CNN, Mask R-nobreakdash-CNN, Cascade versions of each, and SOLOv2, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that object detection and instance segmentation of CXRs can be achieved with a dataset of high-quality, object level annotations, and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis in LMICs, if properly integrated into the healthcare system and adapted to existing clinical workflows and local regulations.

scholarly journals Quality of medicines for life-threatening pregnancy complications in low- and middle-income countries: A systematic review

PLoS ONE ◽  
2020 ◽  
Vol 15 (7) ◽  
pp. e0236060 ◽  
Author(s):  
Maria Regina Torloni ◽  
Mercedes Bonet ◽  
Ana Pilar Betrán ◽  
Carolina C. Ribeiro-do-Valle ◽  
Mariana Widmer
Keyword(s):  
Systematic Review ◽  
Pregnancy Complications ◽  
Middle Income ◽  
Middle Income Countries ◽  
Life Threatening ◽  
Low And Middle Income

scholarly journals RURAL LIVELIHOODS TRANSITIONS: TOWARDS AN INTEGRATION OF THE SUSTAINABLE LIVELIHOODS APPROACH AND THE MULTI-LEVEL PERSPECTIVE

2018 ◽  
Author(s):  
Hamid EL BILALI ◽  
Michael HAUSER ◽  
Sinisa BERJAN ◽  
Otilija MISECKAITE ◽  
Lorenz PROBST
Keyword(s):  
Rural Areas ◽  
Empirical Work ◽  
Sustainable Livelihoods ◽  
Rural Livelihoods ◽  
Livelihood Diversification ◽  
Sustainable Livelihood ◽  
Middle Income ◽  
Middle Income Countries ◽  
Multi Level ◽  
Agricultural Transitions

In rural areas, especially in low and middle-income countries, livelihoods have to diversify to include new on- and off-farm activities. However, sustainable livelihood concepts have so far not sufficiently accommodated transition dynamics. Mostly, rural livelihoods and sustainability transitions are addressed separately in the scientific literature. The aim of this review paper is to explore opportunities to integrate the Sustainable Livelihoods Approach (SLA) and the Multi-Level Perspective (MLP) on transitions. We provide an overview of the SLA and MLP. We then focus on the conceptual linkages between SLA and MLP, in particular regarding livelihood diversification strategies. Our review shows that the conceptual overlaps of the SLA and the MLP allow for a meaningful combination of both approaches to harness their respective strengths. Vulnerabilities from the SLA perspective (e.g. shocks, trends, changes) are considered at the landscape level in MLP. Policies, institutions, processes in SLA are part of ‘regime’ in the MLP heuristic. The livelihood diversification in SLA, e.g. the development of new on- and off-farm activities, can be described as niches in MLP. Some empirical work on agricultural transitions from the MLP perspective has adopted a territorial approach to take into consideration the pluri-activity of farms and the interactions between different subsystems (food, energy and tourism). This resonates well with the idea of livelihood diversification as a strategy in SLA. We conclude that integrating SLA and MLP will help to better understand livelihood diversification processes and we provide a preliminary proposal for a livelihood transition framework.

scholarly journals The forgotten people with thalassemia in the time of COVID-19: South Asian perspective

2020 ◽  
Vol 15 (1) ◽  
Author(s):  
Mohammad Sorowar Hossain ◽  
Enayetur Raheem ◽  
Mahbubul H. Siddiqee
Keyword(s):  
Public Health ◽  
South Asian ◽  
Human Mobility ◽  
Safety Net ◽  
Beta Thalassemia ◽  
Middle Income ◽  
Middle Income Countries ◽  
Blood Banks ◽  
Life Threatening ◽  
Threatening Situation

Abstract South Asia is the hotspot of beta-thalassemia, with an estimated 200,000 patients whose lives depend on regular blood transfusion. Due to COVID-19 pandemic, many countries have adopted unprecedented lockdown to minimize the spread of transmission. Restriction of nationwide human mobility and fear of COVID-19 infection has put thalassemia patients in a life-threatening situation because of an acute shortage of blood supply. As a public health preparedness strategy during a crisis like COVID-19 pandemic, the plights of thalassemia patients should be considered. Government-sponsored community blood-banks needs to be established or coverage expanded as a safety net for the thalassemia patients in lower- and middle-income countries.

Sign in / Sign up

Export Citation Format

Share Document