U-Net Based Covid-19 Infected Lesion Detection and Deep Learning Based Classification on CXR

The Covid-19 disease, which emerged in China in December 2019 and caused by the coronavirus virus, soon became a pandemic all over the world. The fact that the Transcription Polymerase Chain Reaction (RT-PCR) test produces false negatives in some studies and the diagnosis time is long, has led to the search for new alternatives for the diagnosis of this virus, which can result in death, especially with the damage it causes to the lungs. Therefore, chest images have become suitable tools for diagnosis from chest images with data obtained from Computed Tomography or CXR imaging techniques. Deep learning studies have been proposed to provide diagnosis with these tools and to determine the infected region of Covid-19 and Pneumonia disease. In this paper, a two-stage system is proposed as segmentation and classification. In the segmentation process, infected regions segmented from the labeled data were determined. In the classifier stage, Covid- 19/Pneumonia/Normal classification was performed using three different deep learning models named VGG16, ResNet50 and InceptionV3. To the best of our knowledge, this is the first attempt to sequentially design classification and segmentation systems into a more precise diagnosis. As a result of the study, 95% segmentation accuracy was obtained. Classifier models achieved 99%, 90% and 98% accuracy, respectively. © 2022 IEEE.

VGG-FusionNet: A Feature Fusion Framework from CT scan and Chest X-ray Images based Deep Learning for COVID-19 Detection

COVID-19 has been rampant across the globe since it was discovered in 2020, but the method of virus detection still lacks efficiency and requires human resources. Given the slow delivery of the PCR test and the many possible false negatives of the rapid tests, medical imaging such as a chest computed tomography (CT) scan or chest X-ray (CXR) is an alternative and efficient way to detect the coronavirus accurately. For the past two years, many researchers have proposed different deep learning methods for COVID-19 detection using CT scans or CXR images. Due to the lack of available data, our study aims to propose a new deep learning framework VGG-FusionNet that takes advantage of integrating features from both CT scan and CXR images while avoiding some pitfalls from previous studies, including a high risk of bias due to lack of demographic information for the dataset, poor reproducibility, and no evaluation on different data sources to study the generalizability. Specifically, we use the convolutional layers of GoogLeNet, ResNet, and VGG to extract features from CT scan and CXR images and fuse them before training through fully connected layers. The result shows that using VGG's convolutional layers achieves the best overall performance with an accuracy of 0.93. Our proposed framework outperforms the deep learning models, using features from CT scans or CXR. © 2022 IEEE.

Detection of COVID-19 Using CNN and ML Algorithms

As we see coronavirus is the very dangerous diseases and to identify this diseases in one's body is also not as easy. So during identification of diseases there are many false positive cases we see that person does not have corona and still the prediction comes true and also in some cases, it happens that person has corona but it does not get detected (false negative case). So due to this problem, we here come up with the two approaches and make comparison between these two approaches and decide which one is better to analyze the diseases in the body. We are using CNN to scan chest X-ray dataset and ML algorithms for tabular dataset as it contains many text information too. So in this project, we explain in detail, what is CNN, what is ML, how to implement CNN and ML algorithms on particular dataset, what output we will get as a comparison. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Detection of COVID-19 Using CNN and ML Algorithms

As we see coronavirus is the very dangerous diseases and to identify this diseases in one’s body is also not as easy. So during identification of diseases there are many false positive cases we see that person does not have corona and still the prediction comes true and also in some cases, it happens that person has corona but it does not get detected (false negative case). So due to this problem, we here come up with the two approaches and make comparison between these two approaches and decide which one is better to analyze the diseases in the body. We are using CNN to scan chest X-ray dataset and ML algorithms for tabular dataset as it contains many text information too. So in this project, we explain in detail, what is CNN, what is ML, how to implement CNN and ML algorithms on particular dataset, what output we will get as a comparison. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Consequences and Lessons from 2020 Pandemic Disaster: Game-Theoretic Recalibration of COVID-19 to Mobilize and Vaccinate by Rectifying False Negatives and False Positives

The main purpose of this applied research paper is to optimize the probabilities of the false negative (FN) error, β, and the false positive (FP) error, α in a pandemic healthcare setting. The overall objective is to estimate the number of those patients falsely declared uninfected, and those falsely declared infected, aiming to recalibrate the overall count of cases aligned with the world’s mobilization and vaccination efforts. Incomplete FN results can have devastating impacts on current efforts to contain the SARS-CoV-2 (COVID-19) outbreak as infected patients are mistakenly given the go-ahead to return to normal life, likely infecting others. The whole world experienced in 2020 that the number of deaths were undercounted due to existence of false negatives or asymptomatic carriers. But there did not exist universally unbiased scientific methods other than controversial comparisons with the past seasonal death records. This game-theoretic research effort fills a void to replace guesswork and judgment-calls by employing data-scientific health informatics. This article reasons by citing real-data examples why von Neumann’s mixed-strategy game-theoretic feasible solutions to predict the FN cases are noteworthy to prevent more fatalities by facilitating timely pandemic mobilization. FP counts are however not so critical other than causing panic and waste of resources. In the wake of vaccination relief efforts, this research topic is still valid and invaluable for the future unprecedented pandemics such as a hypothetical COVID-35. A fringe benefit of the article is to transform hypothesis testing from subjective to objective for scientific, medical and engineering decisions. Evolutionary game theory may be incorporated for evolving and mutating pandemic variants e.g. OMICRON and DELTA for further research tips. Copyright © 2022 by the authors.

A Study on COVIDBIT as a COVID-19 Detection Device for an Alternative Reverse Transcription-Polymerase Chain Reaction (RT-PCR) Machine

At the end of 2019, Coronavirus disease (COVID-19) started and as of now, it is still the number one problem of the world today. This virus can be transmitted through droplets of saliva from an infected person which can be from a sneeze, cough, and exhales. As of now, there are a total of 111 million cases of the virus and there are technologies that were introduced to help in the detection of the infection and to reduce the spread of the virus. One of this technology is the Reverse Transcription-Polymerase Chain Reaction (RT-PCR) Machine. This machine detects any specific genetic material, including a virus. Samples from the body are treated with several chemical solutions which remove substances and only allow Ribonucleic Acid (RNA) to remain. But the problem with this machine is the elicitation of false-positive and false-negative results and certain malfunctions. Due to the issues in using RT-PCR, our team has come up with a newer and improvised version of the machine and called it COVIDBIT. COVIDBIT is a more simplified and portable version of the RT-PCR at a cheaper price. In this study, the team analyzed COVIDBIT as a virus detection device and an alternative for RT-PCR machine using SEM model and found out that there is a significant difference in terms of effectiveness and portability in usage and showed that the 210 respondents from the medical industry are most likely to use these kinds of machine. © 2022 ACM.

Evaluation of the Bluetooth-based Proximity Estimation for Automatic Exposure Determination

A commonly used methodology to estimate the proximity of two individuals in an automatic exposure notification system uses the signal strength of the Bluetooth signal from their mobile phones. However, there is an underlying error in Bluetooth-based proximity detection that can result in wrong exposure decisions. A wrong decision in the exposure determination leads to two types of errors: false negatives and false positives. A false negative occurs when an exposed individual is incorrectly identified as not exposed. Similarly, a false positive occurs when a non-exposed individual is mistakenly identified as exposed. Both errors have costly implications and can ultimately determine the effectiveness of Bluetooth-based automatic exposure notification in containment of pandemics such as COVID-19. In this paper, we present a platform that allows for the analysis of the system performance under various parameters. This platform enables us to gain a better understanding on how the underlying technology error propagates through the contact tracing system. Preliminary results show the considerable impact of the Bluetooth-based proximity estimation error on false exposure determination. Alternatively, using this platform, analysis can be performed to determine the acceptable accuracy level of a proximity detection mechanism in order to have a more effective contact tracing solution. © 2022 IEEE.

Empirical Analysis of Machine Learning and Deep Learning Techniques for COVID-19 Detection Using Chest X-rays

Due to the Coronavirus (COVID-19) cases growing rapidly, the effective screening of infected patients is becoming a necessity. One such way is through chest radiography. With the high stakes of false negatives being potential cause of innumerable more cases, expert opinions on x-rays are high in demand. In this scenario, Deep Learning and Machine Learning techniques offer fast and effective ways of detecting abnormalities in chest x-rays and can help in identifying patients affected by COVID-19. In this paper, we did comparative analysis of various Machine Learning and Deep Learning techniques on chest x-rays based on accuracy, precision, recall, f1 score, and Matthews correlation coefficient. It was observed that improved results were obtained using Deep Learning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Automatic COVID-19 Detection from Chest X-Rays using Deep Learning Techniques

COVID-19 emerged in November 2019 in the Wuhan city of China. Since then, it has expanded exponentially and reached every corner of the world. To date, it has infected more than three hundred eighty-five million people and caused more than five million seven hundred deaths. Traditional COVID-19 diagnostic tests lack sensitivity and result in false-negative reports several times. Using X-Rays and CT scans to detect covid-19 can aid the diagnosis process when powered by deep learning techniques. Using deep learning will provide accurate results in a fast and automatic manner. The proposed research work has performed a total of twenty-eight experiments. This research work has experimented with seven different Deep Learning models including, DenseNet201, MobileNetV2, DenseNet121, VGG16, VGG19, InceptionV3, and ResNet50. The performance of each model is tested based on the distinct image enhancement techniques. The four different experiments include raw data, data preprocessed with gamma correction for two different gamma values (0.7 and 1.2), and Contrast Limited Adaptive Histogram Equalization (CLAHE). Gamma Correction with gamma value 1.2 performed the best. Lastly, this research work has created an ensemble of three best-performing algorithms including, DenseNet201, MobileNetV2, DenseNet121, and achieved an accuracy, precision, recall, f1 score, and AUC of 98.34%, 98.61%, 98.78%, 98.2%, and 99.8%, respectively. © 2022 IEEE.

Supporting the Contact Tracing Process with WiFi Location Data: Opportunities and Challenges

Contact tracers assist in containing the spread of highly infectious diseases such as COVID-19 by engaging community members who receive a positive test result in order to identify close contacts. Many contact tracers rely on community member's recall for those identifications, and face limitations such as unreliable memory. To investigate how technology can alleviate this challenge, we developed a visualization tool using de-identified location data sensed from campus WiFi and provided it to contact tracers during mock contact tracing calls. While the visualization allowed contact tracers to find and address inconsistencies due to gaps in community member's memory, it also introduced inconsistencies such as false-positive and false-negative reports due to imperfect data, and information sharing hesitancy. We suggest design implications for technologies that can better highlight and inform contact tracers of potential areas of inconsistencies, and further present discussion on using imperfect data in decision making. © 2022 ACM.

A Computational Study of COVID-19 Detection using Colorimetric Plasmonic Sensors

Traditional molecular techniques for COVID-19 viral detection are time-consuming and can exhibit a high probability of false negatives. In this work, we present a computational study of COVID-19 detection using plasmonic gold nanoparticles. The resonance wavelength of a COVID-19 virion was recently estimated to be in the near-infrared region. By engineering gold nanospheres to bind with the outer surface of the COVID-19 virus specifically, the resonance frequency can be shifted to the visible range (380 nm-700 nm). Moreover, we show that broadband absorption will emerge in the visible spectrum when the virus is partially covered with gold nanoparticles at a certain percentage. This broadband absorption can be used to guide the development of an efficient and accurate colorimetric plasmon sensor for COVID-19 detection. © 2021 IEEE.

Crowd Safety Sensing (CroSS) for the Post Pandemic Era

Due to its long incubation period, aggressive asymptomatic transmission, and new mutations of the virus, COVID-19 is causing multiple pandemic waves worldwide. Despite recent vaccination, social distancing, and social restriction efforts, false negatives, and dormant positives can make pandemics challenging to restrain. In addition to rapid vaccination, effective contact tracing, mask-wearing, and social distancing are critical for out-break containment and for achieving herd immunity. However, the existing technology solutions, such as contact tracing apps and social-distance sensing, have been met with suspicion due to privacy and accuracy concerns and have not been widely adopted. Without achieving a critical mass of individual users, these personal technologies have been rendered useless. On the other hand, large-scale policy efforts have been complicated, requiring the coordination of federal, state, and local governments and regulation enforcement logistics. However, local communities balance these approaches and are an unrealized, powerful resource to prevent future outbreaks.This paper proposes a novel Crowd Safety Sensing (CroSS) for building a sustainable safe community cluster against COVID-19 and beyond using affordable Internet of Things (IoT) technologies. CroSS monitors social distancing policies to small, focused communities for accommodating efficient technology penetration, greater accuracy, effective practices, and privacy policy assistance. We implemented a social distancing method and integrated it into an edge-based IoT system. The experimental results show that CroSS detects false-positive social distancing cases. © 2021 IEEE.

Multimodality Data Fusion for COVID-19 Diagnosis

The method wherein a human expert diagnose a patient for COVID-19 with the help of a chest CT scan or X-ray image could be one of the most reliable methods. However, this method of diagnosis is challenging and non-scalable while considering limited medical-care infrastructure and disease spread rate. We train COVID-19 diagnosis models for classification using both the image modalities, chest CT scan and X-ray datasets. We have used fusion approach for multimodal data fusion and proposed two variants. The first model is trained using an automated deep learning approach and in the second model features from the images are extracted using transfer learning approach followed by fine tuning of model. The performance of these models are evaluated with metrics like testing accuracy, recall, precision and f1-score. False negatives are critical and to ensure a smaller number of false negatives, cost-sensitive learning is enforced. The cost-sensitive convnet model achieves an accuracy of 97%. © 2021 IEEE.

Medical diagnosis of COVID-19 using blood tests and machine learning

Severe Acute Respiratory Syndrome Coronavirus 2(SARS-CoV-2), colloquially known as Coronavirus surfaced in late 2019 and is an extremely dangerous disease. RT-PCR (Reverse transcription Polymerase Chain Reaction) tests are extensively used in COVID-19 diagnosis. However, they are prone to a lot of false negatives and erroneous results. Hence, alternate methods are being researched and discovered for the detection of this infectious disease. We diagnose and forecast COVID-19 with the help of routine blood tests and Artificial Intelligence in this paper. The COVID-19 patient dataset was obtained from Israelita Albert Einstein Hospital, Brazil. Logistic regression, random forest, k nearest neighbours and Xgboost were the classifiers used for prediction. Since the dataset was extremely unbalanced, a technique called SMOTE was used to perform oversampling. Random forest obtained optimal results with an accuracy of 92%. The most important parameters according to the study were leukocytes, eosinophils, platelets and monocytes. This preliminary COVID-19 detection can be utilised in conjunction with RT-PCR testing to improve sensitivity, as well as in further pandemic outbreaks. © 2022 Institute of Physics Publishing. All rights reserved.

Data Augmentation using GAN for Sound based COVID 19 Diagnosis

The COVID 19 virus has been mutating at a rapid phase, due to which the golden standard of testing reverse transcription-polymerase chain reaction (RT-PCR) has been producing false negatives at an alarming rate. The inability of the test to detect the mutated strain of the COVID 19 virus using RT-PCR has made it very difficult for diagnosis and hence an alternative solution is needed. Sound-based diagnosis is one effective alternative diagnosis tool. The lack of a large dataset is one challenging aspect for the development of a sound-based diagnosis tool. We look forward to using dataset augmentation as a very effective technique for a selected classification problem: visual perception and also speech recognition tasks. The Generative Adversarial Networks (GANs) have been showing high success for applications in terms of synthesizing realistic images, they're seen rarely in audio generation-based applications Due to the lack of data sets available to develop an accurate model in this paper we showcase an application of WaveGAN, which is a variant of GAN which helps in raw audio synthesis during a supervised setting for the classification task, by developing a method showcasing one of the approaches for augmenting speech datasets by using Generative adversarial networks (GANs). We deploy the WaveGAN on the existing data sets collected from open-source collections to develop synthetic, larger data set to build an accurate sound-based diagnosis tool. © 2021 IEEE.

Optimization of Nucleic Acid Detection Method under the New Epidemic Situation in Macao based on Experimental and Mathematical Statistics Analysis

A large number of COVID-19 nucleic acid tests are performed every day in the world. If the testing is performed individually, the testing workload and testing cost would be high. In this paper, we proposed a simulated model to check the efficiency of group testing methods given four typical situations and find the best grouping number for different predicted infection rates. Maximum likelihood Estimation (MLE) is applied for model estimation and Inversion Method is used to generate pseudo random variables for simulation. The simulation results point to the conclusions: (1) Given a high infection rate (p>0.1), both the false-positive and the false-negative possibilities have a poor relation with the grouping number. (2) However, given a low infection rate (p<0.1), the false-positive and false-negative possibilities will become important factors to reduce the grouping number. Especially, if p is close to 0.01, the grouping number is significantly affected. (3) With a 10% infection rate, it is recommended to group 5 participants in one test given no false-positive or false-negative situations. (4) If p<0.3, the group testing approach has the potential to improve overall testing efficiency. © 2021 ACM.

Mesoscopic Evaluation of DNA Mismatches in PCR Primer-Target Hybridisation to Detect SARS-CoV-2 Variants of Concern

Mismatches are any type of base-pairs other than AT and CG. They are an expected occurrence in PCR primer-target hybridisation and may interfere with the amplification and in some cases even prevent the detection of viruses and other types of target. Given the natural occurrence of mutations it is expected that the number of primer-target mismatches increases which may result in a larger number of false-negative PCR diagnostics. However, mismatches may equally improve the primer-target hybridisation since some types of mismatches may stabilize the helix. Only very recently have thermodynamic parameters become available that would allow the prediction of mismatch effects at buffer conditions similar to that of PCR. Here we collected primers from WHO recommendation and aligned them to the genomes of the current variants of concern (VOC): Alpha, Beta, Gamma and Delta variants. We calculated the hybridisation temperatures taking into account up to three consecutive mismatches with the new parameters. We assumed that hybridisation temperatures to mismatched alignments within a range of 5 ∘ C of the non-mismatched temperature to still result in functional primers. In addition, we calculated strict and partial coverages for complete and mismatched alignments considering only single, double and triple consecutive mismatches. We found that if mismatches are taken into account, the coverage of WHO primers actually increase for VOCs and for the Delta variant it becomes 100%. This suggest that, at least for the moment, these primers should continue to be effective for the detection of VOCs. © 2021, Springer Nature Switzerland AG.

Optimal diagnostic test allocation strategy during the COVID-19 pandemic and beyond.

Timely diagnostic testing for active SARS-CoV-2 viral infections is key to controlling the spread of the virus and preventing severe disease. A central public health challenge is defining test allocation strategies with limited resources. In this paper, we provide a mathematical framework for defining an optimal strategy for allocating viral diagnostic tests. The framework accounts for imperfect test results, selective testing in certain high-risk patient populations, practical constraints in terms of budget and/or total number of available tests, and the purpose of testing. Our method is not only useful for detecting infections, but can also be used for long-time surveillance to detect new outbreaks. In our proposed approach, tests can be allocated across population strata defined by symptom severity and other patient characteristics, allowing the test allocation plan to prioritize higher risk patient populations. We illustrate our framework using historical data from the initial wave of the COVID-19 outbreak in New York City. We extend our proposed method to address the challenge of allocating two different types of diagnostic tests with different costs and accuracy, for example, the RT-PCR and the rapid antigen test (RAT), under budget constraints. We show how this latter framework can be useful to reopening of college campuses where university administrators are challenged with finite resources for community surveillance. We provide a R Shiny web application allowing users to explore test allocation strategies across a variety of pandemic scenarios. This work can serve as a useful tool for guiding public health decision-making at a community level and adapting testing plans to different stages of an epidemic. The conceptual framework has broader relevance beyond the current COVID-19 pandemic.

Rethinking COVID-19 test sensitivity-a strategy for improving the detection limit.

Numerous genetic tests for the detection of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, including those based on the ever-popular real-time polymerase chain reaction (RT-qPCR) technique, have been reported. These diagnostic tests give false negatives particularly during the early and late stages of COVID-19 clearly indicating inadequate test sensitivity. The entire COVID-19 diagnostic workflow is often overlooked and given very little attention. Herein, we propose that volumetric modifications to COVID-19 workflows would significantly improve detection limits. We would therefore encourage researchers to adopt a holistic approach, in which all the steps of a COVID-19 diagnostic workflow, are carefully scrutinised, particularly those upstream factors at the viral sampling and pre-analytical stages.

Performance of saliva as a specimen to detect SARS-CoV-2.

Massive testing to detect SARS-CoV-2 is an imperious need in times of epidemic but also presents challenges in terms of its concretization. The use of saliva as an alternative to nasopharyngeal swabs (NPS) has advantages, being more friendly to the patient and not requiring trained health workers, so much needed in other functions. This study used a total of 452 dual samples (saliva and NPS) of patients suspected of having COVID-19 to compare results obtained for the different specimens when using RT-PCR of RNA extracted from NPS and saliva, as well as saliva directly without RNA extraction. SARS-CoV-2 was not detected in 13 saliva (direct) of the 80 positive NPS samples and in 16 saliva (RNA) of a total of 76 NPS positive samples. Sensitivity of detection of viral genes ORF1ab, E and N in saliva is affected differently and detection of these genes in saliva samples presents great variability when NPS samples present Ct-values above approximately 20, with sensitivities ranging from 76.3% to 86.3%. On average an increase in 7.3 Ct-values (average standard deviation of 4.78) is observed in saliva samples when compared to NPS. The use of this specimen should be carefully considered due to the false negative rate and the system used for detection may be also very relevant since the different viral genes are affected differently in terms of detection sensitivity using saliva.