A fast point-of-care PCR test for infectious diseases, based on aerosol capturing

The COVID-19 pandemic quickly revealed the limitations of existing monitoring and diagnostic capabilities. While rapid antigen tests are not sufficiently reliable, PCR turn-around-time (TAT) typically ranges from hours to days. Standard swab-based tests are also cumbersome and invasive and, worse yet, they detect infection and not transmissibility. A reliable diagnostic test able to discern the infectious phase of COVID-19 could interrupt transmission while limiting isolation requirements. We developed a non-invasive, impaction-based method for capturing aerosols from human breath in one minute of sampling. A proof-of-principle system was used for the detection of viral RNA in breath samples from confirmed positive subjects (=29). A lab setup demonstrated compatibility with on-chip PCR, reducing the TAT to 15-20 minutes. Positive percentage agreement (PPA) between a breath- and nasopharyngeal PCR is 75% overall and 92% in the first 7 days of infection, after which the breath does not contain measurable virus anymore. Breath positivity corresponds to the infectious window. No false positives were noted. Diagnostic accuracy is superior to nasopharyngeal rapid antigen tests. This novel concept of aerosol capturing combined with ultra-fast PCR is proven to be effective to detect SARS-CoV-2 in breath, rivalling the standard nasopharyngeal PCR tests. Combined with a TAT on par with rapid antigen tests, the technology has the potential to become a standard test in the coming years, for COVID-19 or other infectious diseases. A validation study with an advanced setup is currently ongoing, first data should be available during the presentation.

Epidemiology, virology, clinical features, diagnosis, and treatment of SARS-CoV-2 infection

Since December 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has emerged and spread quickly worldwide. The disease is generally mild in adult people but in any with comorbidities may proceed to acute respiratory distress syndrome (ARDS), pneumonia, and multi-organ dysfunction. By performing molecular tests on respiratory secretions can diagnose the virus. Elevated C-reactive protein (CRP) and normal/low white cell counts are common laboratory diagnoses of COVID-19 while the tomographic chest scan is usually irregular for many infected people. Some patients progress to respiratory failure, pneumonia, and finally death by the end of the first week of illness because of the sharp rise in inflammatory cytokines such as IL7, IL2, GCSF, IL10, MIP1A, MCP1, IP10, and TNFα. Various approaches to the COVID- 19 are being performed by scientists. Use of chemical medical drugs that are effective for other viral infections. Among them, remdesivir was approved by FDA on 1th May 2020 because of its impact to treat patients. Also, several studies have revealed that many Chinese herbal remedies have a remarkable impact on the healing process when simultaneously were used along with pharmacological drugs. In the meantime, many efforts have been made to produce an effective vaccine, and so far, the Ad5-vectored COVID-19 vaccine has been successful and has entered phase 2 in the human trial. The current review focus on epidemiology, virology, clinical features, diagnosis, and available treatment of coronavirus that might assist researchers and clinicians in establishing action options for timely against this infection.

Chest X-ray Images Analysis with Deep Convolutional Neural Networks (CNN) for COVID-19 Detection

The latest advances of deep learning and particularly convolutional neural networks (CNNs) have proven more than once their high accuracy in disease detection. In this chapter, we propose a new deep learning-based approach for COVID-19 detection from chest X-ray images. The proposed approach applies, in an efficient way, the techniques of transfer learning and fine-tuning from pre-trained CNN models (InceptionV3, VGG16, MobileNet, EfficientNet, etc.). The dataset used for our experiments has three classes: normal, COVID-19, and other pathologies. The dataset is split into three sub-sets as follows: 70% for training, 15% for validation, and 15% for the final test. To avoid underfitting or overfitting problems during the training process, we apply regularization techniques (L1 & L2 regularizations, dropout, data augmentation, early stopping, cross-validation, etc.), which help in learning and providing a generalizable solution. As a result, we demonstrate the high efficiency of the proposed CNNs for the detection of COVID-19 from chest X-ray images. A comparison of different architectures shows that VGG16 and MobileNet provide the highest scores: 97.5% and 99.3% of accuracy respectively, 98.7% and 99.3% of sensitivity respectively. In addition, both models provide the scores of 96.3% and 99.2% respectively for specificity. The proposed solution is deployed in the cloud to provide high availability in real time, thanks to a responsive website, and this without the need to download, install, and configure the required libraries. © 2022, Springer Nature Switzerland AG.

Explainable Deep Learning for Covid-19 Detection Using Chest X-ray and CT-Scan Images

Recently, Artificial Intelligence (AI) and more particularly Deep Learning (DL) applications gained significant importance in several domains such as computer vision, robotics, medical imaging, etc. Despite the excellent results of AI models, in terms of precision and performance, their decisions are not always interpretable and explainable, which makes from them a black box. Since May 2018, the general data protection regulation (GDPR) requires a right of explanation for the output of an algorithm, which is necessary and justified for several examples such as autonomous cars and computer-aided diagnosis (CAD) systems. As a result, a high interest in terms of research has been given recently to the domain of Explainable Artificial Intelligence (XAI). In this book chapter, we propose an approach for explaining Deep Learning algorithms when applied to image classification and segmentation. The proposed approach allows to provide the most appropriate explanation method and the most accurate and explainable DL model. As a use case, we applied our approach for explaining DL models used Covid-19 image classification and segmentation with two modalities: X-ray and CT-scan images. Experimental results showed the interest of our explanation approach within three facts: (1) identification of the most interpretable DL model;(2) measurement of positive and negative contributions of input parameters (image pixels) in the decision of DL models;(3) detection of data (training and validation datasets) biases, where the deep neural networks are focusing on image regions that are not supposed to be important. The provided explanations were evaluated by doctors and physicians who confirmed the accuracy of our results. © 2022, Springer Nature Switzerland AG.

A New Collaborative Platform for Covid-19, Benchmark Datasets

Fast and efficient collaboration among researchers is a crucial task to advance effectively in Covid-19 research. In this chapter, we present a new collaborative platform allowing to exchange and share both medical benchmark datasets and developed applications rapidly and securely between research teams. This platform aims to facilitate and encourage the exploration of new fields of research. This platform implements proven data security techniques allowing to guarantee confidentiality, mainly Argon2id password hashing algorithm, anonymization, expiration of forms, and datasets double encryption and decryption with AES 256-GCM and XChaCha20Poly1305 algorithms. Our platform has been successfully tested as part of a project aiming to develop artificial intelligence algorithms for imagery based on the detection of Covid-19. Indeed, this current paltform help us to advance more quickly on the development of some artificial intelligence algorithms which mainly achieve both segmentation and classification of CT-scan and X-ray images of patients’ lungs and chests. © 2022, Springer Nature Switzerland AG.

Explainable Deep Learning Model for COVID-19 Screening in Chest CT Images

In this work, we proposed an Explainable model based on Deep Learning for fast COVID-19 screening in chest CT images. We first collected a database of 360 COVID and Non-COVID images at the Tlemcen hospital in Algeria. This database was merged with two other public datasets (the first one has been collected from several articles published on medRxiv, bioRxiv, NEJM, JAMA, Lancet, etc. The second one was obtained from infected cases in hospitals in Sao Paulo, Brazil). We also conducted a comparative study between Deep Learning classification models that are widely used in the state of the art such as VGG16, VGG19, Inception v3, ResNet50, and DenseNet121. We also proposed an interpretable architecture based on the ResNet50 model and the GradCam explanation algorithm. Experimentations showed promising results and prove that the introduced model can be very useful for the diagnosis and follow-up of patients with COVID-19. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A review on the diagnostic approaches of COVID-19 infection;features and limitations

Detection of coronavirus disease 2019 (COVID-19) in early stage is indispensible for outcome improvement and interruption of transmission chain. Clear understanding of the nature of the diagnostic tests for severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and their challenges, collecting the most diagnostically valuable specimen at the right time from the right anatomic site, and interpretation of their findings is important. This review scrutinizes current challenges and interpretation of reverse transcriptase polymerase chain reaction (RT-PCR), as the reference method, loop-mediated isothermal amplification (LAMP), antibody and antigen detection, typical lung imaging characteristics and prominent abnormal changes in laboratory findings of patients with proven COVID-19, and describes how the results may vary over time. Bronchoalveolar lavage fluid and sputum specimens demonstrate the highest positive rates (93% and 72%, respectively) in molecular diagnosis of COVID-19. Alternatively, repeated RT-PCR assays can be performed;as over time, it is an increase in the likelihood of the SARS-CoV-2 being present in the nasopharynx. Combining clinical evidence with results of chest computed tomography (CT) and RT-PCR can minimize the risk of diagnostic errors. Elevated levels of interleukin 6 (IL-6) and D-dimer are thought to be closely associated with the occurrence of severe COVID-19 in adults, and their combined detection can serve as early factors predicting the severity of COVID-19. Moreover, elevated acute phase proteins are associated with a poor outcome in COVID-19. Serological diagnosis also is an important tool to understand the extent of COVID-19 in the community, and to identify individuals, who are immune. Antibodies begin to increase from the second week of symptom onset.

Atypical and novel presentations of Coronavirus Disease 2019: a case series of three children.

Typical presentations of Coronavirus Disease 2019 (Covid-19) including respiratory symptoms (cough, respiratory distress and hypoxia), fever and dyspnoea are considered main symptoms in adults, but atypical presentation in children could be a diagnostic challenge. We report three children whose initial presentation was gastrointestinal, and in whom Covid-19 infection was found, concluding that cases of acute appendicitis, mesenteric adenitis and flank tenderness may mask an infection with this virus, and should therefore be investigated.

Fulminant hepatic failure: A rare and devastating manifestation of Coronavirus disease 2019 in an 11-year-old boy.

Although several typical manifestation of novel coronavirus disease 2019 (COVID-19) including respiratory symptoms, weakness, fever, and fatigue have been reported, some rare and novel manifestations have also been observed, particularly in children. We report a pediatric case of fulminant hepatic failure associated with COVID-19. Although the patient was treated for acute fulminant hepatic failure in the context of COVID-19, he died following the progression of the disease to stage 4 hepatic failure with encephalopathy and brain death.