scholarly journals Residual-Shuffle Network with Spatial Pyramid Pooling Module for COVID-19 Screening

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1497
Author(s):  
Mohd Asyraf Zulkifley ◽  
Siti Raihanah Abdani ◽  
Nuraisyah Hani Zulkifley ◽  
Mohamad Ibrani Shahrimin
Keyword(s):  
Imaging Modality ◽  
Screening Method ◽  
Middle Layer ◽  
World Health ◽  
Polymerase Chain Reaction Test ◽  
Global Features ◽  
X Ray ◽  
The World ◽  
Spatial Pyramid Pooling ◽  
Spatial Pyramid

Since the start of the COVID-19 pandemic at the end of 2019, more than 170 million patients have been infected with the virus that has resulted in more than 3.8 million deaths all over the world. This disease is easily spreadable from one person to another even with minimal contact, even more for the latest mutations that are more deadly than its predecessor. Hence, COVID-19 needs to be diagnosed as early as possible to minimize the risk of spreading among the community. However, the laboratory results on the approved diagnosis method by the World Health Organization, the reverse transcription-polymerase chain reaction test, takes around a day to be processed, where a longer period is observed in the developing countries. Therefore, a fast screening method that is based on existing facilities should be developed to complement this diagnosis test, so that a suspected patient can be isolated in a quarantine center. In line with this motivation, deep learning techniques were explored to provide an automated COVID-19 screening system based on X-ray imaging. This imaging modality is chosen because of its low-cost procedures that are widely available even in many small clinics. A new convolutional neural network (CNN) model is proposed instead of utilizing pre-trained networks of the existing models. The proposed network, Residual-Shuffle-Net, comprises four stacks of the residual-shuffle unit followed by a spatial pyramid pooling (SPP) unit. The architecture of the residual-shuffle unit follows an hourglass design with reduced convolution filter size in the middle layer, where a shuffle operation is performed right after the split branches have been concatenated back. Shuffle operation forces the network to learn multiple sets of features relationship across various channels instead of a set of global features. The SPP unit, which is placed at the end of the network, allows the model to learn multi-scale features that are crucial to distinguish between the COVID-19 and other types of pneumonia cases. The proposed network is benchmarked with 12 other state-of-the-art CNN models that have been designed and tuned specially for COVID-19 detection. The experimental results show that the Residual-Shuffle-Net produced the best performance in terms of accuracy and specificity metrics with 0.97390 and 0.98695, respectively. The model is also considered as a lightweight model with slightly more than 2 million parameters, which makes it suitable for mobile-based applications. For future work, an attention mechanism can be integrated to target certain regions of interest in the X-ray images that are deemed to be more informative for COVID-19 diagnosis.

scholarly journals COVID-19 Screening Using a Lightweight Convolutional Neural Network with Generative Adversarial Network Data Augmentation

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1530 ◽  
Author(s):  
Mohd Asyraf Zulkifley ◽  
Siti Raihanah Abdani ◽  
Nuraisyah Hani Zulkifley
Keyword(s):  
Deep Learning ◽  
Physical Contact ◽  
Generative Adversarial Network ◽  
X Ray ◽  
Multi Scale ◽  
Adversarial Network ◽  
The World ◽  
Spatial Pyramid Pooling ◽  
Targeted Approach ◽  
Spatial Pyramid

COVID-19 is a disease that can be spread easily with minimal physical contact. Currently, the World Health Organization (WHO) has endorsed the reverse transcription-polymerase chain reaction swab test as a diagnostic tool to confirm COVID-19 cases. This test requires at least a day for the results to come out depending on the available facilities. Many countries have adopted a targeted approach in screening potential patients due to the cost. However, there is a need for a fast and accurate screening test to complement this targeted approach, so that the potential virus carriers can be quarantined as early as possible. The X-ray is a good screening modality; it is quick at capturing, cheap, and widely available, even in third world countries. Therefore, a deep learning approach has been proposed to automate the screening process by introducing LightCovidNet, a lightweight deep learning model that is suitable for the mobile platform. It is important to have a lightweight model so that it can be used all over the world even on a standard mobile phone. The model has been trained with additional synthetic data that were generated from the conditional deep convolutional generative adversarial network. LightCovidNet consists of three components, which are entry, middle, and exit flows. The middle flow comprises five units of feed-forward convolutional neural networks that are built using separable convolution operators. The exit flow is designed to improve the multi-scale capability of the network through a simplified spatial pyramid pooling module. It is a symmetrical architecture with three parallel pooling branches that enable the network to learn multi-scale features, which is suitable for cases wherein the X-ray images were captured from all over the world independently. Besides, the usage of separable convolution has managed to reduce the memory usage without affecting the classification accuracy. The proposed method managed to get the best mean accuracy of 0.9697 with a low memory requirement of just 841,771 parameters. Moreover, the symmetrical spatial pyramid pooling module is the most crucial component; the absence of this module will reduce the screening accuracy to just 0.9237. Hence, the developed model is suitable to be implemented for mass COVID-19 screening.

Determination of Heavy Metals in Damascus Drinking Water Using Total Reflection X-Ray Fluorescence

1999 ◽  
Vol 34 (2) ◽  
pp. 305-316 ◽  
Author(s):  
E.H. Bakraji ◽  
J. Karajo
Keyword(s):  
Trace Elements ◽  
Drinking Water ◽  
Total Reflection ◽  
World Health ◽  
X Ray ◽  
Quality Guidelines ◽  
The World ◽  
The Mean ◽  
Health Organization

Abstract Total reflection X-ray fluorescence spectrometry and chemical preconcentration have been applied for multi-elemental analysis of Damascus drinking water. Water was taken directly from taps of several city sectors and analyzed for the following trace elements: Ti, V, Cr, Fe, Co, Ni, Cu, Zn, Se and Pb. The detection limits were found to be in the range of 0.1 to 0.4 µg/L. The mean levels of trace elements in the Damascus drinking water were below the World Health Organization drinking water quality guidelines.

scholarly journals Vehicle Pedestrian Detection Method Based on Spatial Pyramid Pooling and Attention Mechanism

Information ◽  
2020 ◽  
Vol 11 (12) ◽  
pp. 583
Author(s):  
Mingtao Guo ◽  
Donghui Xue ◽  
Peng Li ◽  
He Xu
Keyword(s):  
Object Detection ◽  
Clustering Algorithm ◽  
Pedestrian Detection ◽  
Attention Mechanism ◽  
Complex Environments ◽  
Global Features ◽  
Feature Map ◽  
Spatial Pyramid Pooling ◽  
Institute Of Technology ◽  
Spatial Pyramid

Object detection for vehicles and pedestrians is extremely difficult to achieve in autopilot applications for the Internet of vehicles, and it is a task that requires the ability to locate and identify smaller targets even in complex environments. This paper proposes a single-stage object detection network (YOLOv3-promote) for the detection of vehicles and pedestrians in complex environments in cities, which improves on the traditional You Only Look Once version 3 (YOLOv3). First, spatial pyramid pooling is used to fuse local and global features in an image to better enrich the expression ability of the feature map and to more effectively detect targets with large size differences in the image; second, an attention mechanism is added to the feature map to weight each channel, thereby enhancing key features and removing redundant features, which allows for strengthening the ability of the feature network to discriminate between target objects and backgrounds; lastly, the anchor box derived from the K-means clustering algorithm is fitted to the final prediction box to complete the positioning and identification of target vehicles and pedestrians. The experimental results show that the proposed method achieved 91.4 mAP (mean average precision), 83.2 F1 score, and 43.7 frames per second (FPS) on the KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) dataset, and the detection performance was superior to the conventional YOLOv3 algorithm in terms of both accuracy and speed.

scholarly journals Identification of Pneumonia Disease Applying an Intelligent Computational Framework Based on Deep Learning and Machine Learning Techniques

2021 ◽  
Vol 2021 ◽  
pp. 1-20
Author(s):  
Yar Muhammad ◽  
Mohammad Dahman Alshehri ◽  
Wael Mohammed Alenazy ◽  
Truong Vinh Hoang ◽  
Ryan Alturki
Keyword(s):  
Machine Learning ◽  
Medical Image Analysis ◽  
Machine Learning Techniques ◽  
World Health ◽  
X Ray ◽  
Expert Radiologist ◽  
Learning Techniques ◽  
Effective Manner ◽  
The World ◽  
Chest X Ray

Pneumonia is a very common and fatal disease, which needs to be identified at the initial stages in order to prevent a patient having this disease from more damage and help him/her in saving his/her life. Various techniques are used for the diagnosis of pneumonia including chest X-ray, CT scan, blood culture, sputum culture, fluid sample, bronchoscopy, and pulse oximetry. Medical image analysis plays a vital role in the diagnosis of various diseases like MERS, COVID-19, pneumonia, etc. and is considered to be one of the auspicious research areas. To analyze chest X-ray images accurately, there is a need for an expert radiologist who possesses expertise and experience in the desired domain. According to the World Health Organization (WHO) report, about 2/3 people in the world still do not have access to the radiologist, in order to diagnose their disease. This study proposes a DL framework to diagnose pneumonia disease in an efficient and effective manner. Various Deep Convolutional Neural Network (DCNN) transfer learning techniques such as AlexNet, SqueezeNet, VGG16, VGG19, and Inception-V3 are utilized for extracting useful features from the chest X-ray images. In this study, several machine learning (ML) classifiers are utilized. The proposed system has been trained and tested on chest X-ray and CT images dataset. In order to examine the stability and effectiveness of the proposed system, different performance measures have been utilized. The proposed system is intended to be beneficial and supportive for medical doctors to accurately and efficiently diagnose pneumonia disease.

scholarly journals Medical technology innovation for a sustainable impact in Low- and Middle-Income countries: a holistic approach.

2020 ◽  
Author(s):  
Solomzi Makoliso ◽  
Bertrand Klaiber ◽  
Romain Sahli ◽  
Jean Roger Moulion Tapouh ◽  
Samuel Nko'o Amvene ◽  
...  
Keyword(s):  
Social Impact ◽  
Business Models ◽  
World Health ◽  
World Population ◽  
Full Potential ◽  
Middle Income ◽  
X Ray ◽  
X Ray Imaging ◽  
The World ◽  
Low And Middle Income

Technologies that have been designed for use in high-income countries often fail to deliver their full potential when transposed to Low and Middle-Income Contexts (LMICs). The health sector is a case in point, as medical devices, whether donated or purchased, are generally short lived in those contexts. The mismatch between needs and available solutions originates from the inadequacy of both the technology and the business models. Essential medical technologies such as oxygen concentrators, neonatal incubators, anesthesia machines or diagnostic X-ray systems are classic examples. The case of diagnostic X-ray imaging is particularly striking: 125 years after its invention, up to two thirds of the world population still does not have access to radiology services, according to the World Health Organisation. This is despite the fact that X-ray radiology is one of the cornerstone of healthcare and a crucial instrument for diagnosing a variety of health issues ranging from trauma to tuberculosis and other lung diseases.We are presenting an integrated methodological approach, to develop innovative solutions adapted to the context of LMICs. The approach relies on three crucial pillars: cooperation, interdisciplinarity and entrepreneurship with a long-term sustainability perspective. We propose a set of four complementary tools that increase the chances of successfully developing and deploying the technologies at scale. The tools, while very practical, allow striking a balance between economic viability, environmental and social impact. We illustrate the use of these tools with the case of diagnostic X-ray imaging. We propose that using the approach and tools presented here could allow to rethink other complex technologies that have the potential to address social challenges, in the perspective of making them suitable for LMICs. We also believe that this approach to developing solutions addressing the needs of poorer communities, may lead to better products in industrialized contexts as well.

scholarly journals DETERMINATION OF LEAD FROM GOLD ORE USING PROTON INDUCED X-RAY EMISSION TECHNIQUE

2021 ◽  
Vol 5 (1) ◽  
pp. 490-494
Author(s):  
A. Bello
Keyword(s):  
Research Work ◽  
World Health ◽  
Elemental Content ◽  
Northern Nigeria ◽  
X Ray ◽  
Mining Sites ◽  
The World ◽  
Health Organization ◽  
Pb Concentration

The impetus for this research work arose from alleged signs of Lead (Pb) poisoning from Medicines Sans Frontiers (Doctors without Borders).These poisonings were narrowed down to areas of solid minerals mining and extraction in Northern Nigeria. The aim of this research work is to identify mining Sites with ores having high Pb concentration. Fifteen samples were collected from areas located at approximately latitudes 𝟶𝟶70𝟶8.69𝟶ˈE and longitudes 𝟶90 34ˈ224ˈˈN and interrogated using Proton induced X-ray emission (PIXE) technique for their elemental content. PIXE was chosen because of its sample nondestructive and it does not contaminate the environment. The result obtained varied between 24.3 – 632303.3 ppm. The world Health Organization recommends that sites with Pb concentration above 400 ppm are inimical to human health and ordered that children be evacuated from such areas. Exposure to Pb poisoning may cause anemia, weakness, and Kidney and brain damage; particularly in children.

scholarly journals Medical And Legal Reasons Of Compulsory PCRTest Implementation in Covid-19 With Ethical Assessment

2020 ◽  
Author(s):  
Çağatay Üstün ◽  
Gülsün Ayhan Aygörmez ◽  
Seçil Özçiftçi ◽  
Mehmet Korkmaz
Keyword(s):  
World Health ◽  
Polymerase Chain Reaction Test ◽  
Ethical Assessment ◽  
The World ◽  
Reaction Test ◽  
Polymerase Chain ◽  
Health Organization ◽  
Chain Reaction Test ◽  
Short Time ◽  
Pcr Test

COVID-19 disease, which emerged in December 2019, affected the world in a short time. A pandemic was declared by the World Health Organization (WHO) due to the increasing number of cases approximately 3 months after the first cases appeared. As every country has different strategic applications in the fight against disease, the disease has been dealt with thanks to the necessary interventions and measures since the fact that the facts have been observed in our country. The basis of the measures taken is to reduce the risk of transmission, rapid detection of the infected person and isolation measures. For this reason, PCR (Polymerase Chain Reaction) test is performed in early diagnosis and definitive diagnosis. However, whether the PCR test is applied to each individual, does not want to have the test performed, demanding another diagnostic method, etc. Situations such as are encountered. In this direction, it was aimed to evaluate the medical and legal justifications of PCR test in terms of ethics.

scholarly journals Reliability of RT-PCR tests to detect SARS-CoV-2: risk analysis

2020 ◽  
Vol 11 ◽  
pp. 15
Author(s):  
Clément Bezier ◽  
Géraldine Anthoine ◽  
Abdérafi Charki
Keyword(s):  
Risk Analysis ◽  
Diagnostic Tests ◽  
Test Method ◽  
World Health ◽  
Polymerase Chain Reaction Test ◽  
Internal Quality ◽  
Rt Pcr ◽  
The World ◽  
Criticality Analysis ◽  
Validation Of Results

The rapid escalation of the number of COVID-19 (Coronavirus Disease 2019) cases has forced countries around the world to implement systems for the widest possible testing of their populations. The World Health Organization (WHO) has in fact urged all countries to carry out as many tests as they can. Clinical laboratories have had to respond urgently to numerous and rising demands for diagnostic tests for SARS-CoV-2. The majority of laboratories have had to implement the RT-PCR (Reverse Transcriptase − Polymerase Chain Reaction) test method without the benefit of adequate experimental feedback. It is hoped that this article will make a useful contribution in the form of a methodology for the risk analysis of SARS-CoV-2 testing by RT-PCR and at the same time result reliability analysis of diagnostic tests, via an approach based on a combination of Fishbone Diagram and FMECA (Failure Mode, Effects, and Criticality Analysis) methods. The risk analysis is based on lessons learned from the actual experience of a real laboratory, which enabled the authors to pinpoint the principal risks that impact the reliability of RT-PCR test results. The probability of obtaining erroneous results (false positives or negatives) is implicit in the criticality assessment obtained via FMECA. In other words, the higher the criticality, the higher the risk of obtaining an erroneous result. These risks must therefore be controlled as a priority. The principal risks are studied for the following process stages: nucleic acid extraction, preparation of the mix and validation of results. For the extraction of nucleic acids, highly critical risks (exceeding the threshold set from experimentation) are the risk of error when depositing samples on the extraction plate and sample non-conformity. For the preparation of the mix the highest risks are a non-homogenous mix and, predominantly, errors when depositing samples on the amplification plate. For the validation of results, criticality can reach the maximum severity rating: here, the risks that require particular attention concern the interpretation of raw test data, poor IQC (Internal Quality Control) management and the manual entry of results and/or file numbers. Recommendations are therefore made with regard to human factor influences, internal contamination within the laboratory, management of reagents, other consumables and critical equipment, and the effect of sample quality. This article demonstrates the necessity to monitor, both internally and externally, the performance of the test process within a clinical laboratory in terms of quality and reliability.

The Classification of Covid-19 cases through the Employment of Transfer Learning on X-ray images

Mekatronika ◽  
2021 ◽  
Vol 3 (1) ◽  
pp. 44-51
Author(s):  
Nur Ameerah Hakimi ◽  
Mohd Azhar Mohd Razman ◽  
Anwar P. P. Abdul Majeed
Keyword(s):  
Transfer Learning ◽  
Screening Method ◽  
X Ray ◽  
The People ◽  
Machine Learning Model ◽  
The World ◽  
Chest X Ray ◽  
Alternative Test ◽  
Chest Radiology

Covid-19 is a contagious disease that known to cause respirotary infection in humans. Almost 219 countries are effected by the outbreak of the latest coronavirus pandemic, exceed 100 millions of confirmed cases and about 2 million death recorded aound the world. This condition is alarming as some of the people who are infected with the virus show no symptoms of the disease. Due to the number of confirmed cases rapidly rising around the world, it is crucial  find another method to diagnose the disease at the beginnings stage in order to control the spreading of the virus. Another alternative test from the main screening method is by using chest radiology image based detection which are X-ray or CT scan images. The aim of this research is to classify the Covid-19 cases by using the image classification technique.The dataset consist of 2000 images of chest X-ray images and have two classes which are Covid and Non-Covid. Each of the class consists of 1000 images.This research compare the performance of the various Transfer Learning models (VGG-16, VGG-19, and Inception V3) in extracting the feature from X-ray image combined with machine learning model (SVM, kNN, and Random Forest) as a classifier. The experiment result showed the VGG-19, VGG-16, and Inception V3 coupled with optimized SVM pipelines are comparably efficient in classifying the cases as compared to other pipelines evaluated in this reaseach and could archieved 99% acuuracy on the test datasets.

COVID-19 Chest X-Ray Images Diagnosis: A Neutrosophic and Deep Transfer Learning Approach

2020 ◽  
Author(s):  
Nour Eldeen M. Khalifa ◽  
Florentin Smarandache ◽  
Mohamed Loey
Keyword(s):  
Deep Learning ◽  
Performance Metrics ◽  
World Health ◽  
Transfer Model ◽  
X Ray ◽  
Proposed Model ◽  
The World ◽  
Chest X Ray ◽  
Testing Accuracy ◽  
Transfer Models

Coronavirus, also known as COVID-19, has spread to several countries around the world. It was announced as a pandemic disease by The World Health Organization (WHO) in 2020 for its devastating impact on humans. With the advancements in computer science algorithms, the detection of this type of virus in the early stages is urgently needed for the fast recovery of patients. In this paper, a neutrosophic with a deep learning model for the detection of COVID-19 from chest X-ray medical digital images is presented. The proposed model relies on neutrosophic theory by converting the medical images from the grayscale spatial domain to the neutrosophic domain. The neutrosophic domain consists of three types of images and they are, the True (T) images, the Indeterminacy (I) images, and the Falsity (F) images. Using neutrosophic images has positively affected the accuracy of the proposed model. The dataset used in this research has been collected from different sources as there is no benchmark dataset for COVID-19 chest X-ray until the writing of this research. The dataset consists of four classes and they are COVID-19, Normal, Pneumonia bacterial, and Pneumonia virus. After the conversion to the neutrosophic domain, the images are fed into three different deep transfer models and they are Alexnet, Googlenet, and Restnet18. Those models are selected as they have a small number of layers on their architectures and they have been used with related work. To test the performance of the conversion to the neutrosophic domain, four scenarios have been tested. The first scenario is training the deep transfer models with True (T) neutrosophic images only. The second one is training on Indeterminacy (I) neutrosophic images, while the third scenario is training the deep models over the Falsity (F) neutrosophic images. The fourth scenario is training over the combined (T, I, F) neutrosophic images. According to the experimental results, the combined (T, I, F) neutrosophic images achieved the highest accuracy possible for the validation, testing and all performance metrics such Precision, Recall and F1 Score using Resnet18 as a deep transfer model. The proposed model achieved a testing accuracy with 78.70%. Furthermore, the proposed model using neutrosophic and Resnet18 had achieved superior testing accuracy with a related work which achieved 52.80% with the same experimental environmental setup and the same deep learning hyperparameters.

Sign in / Sign up

Export Citation Format

Share Document