Contribution of transthoracic echocardiography in post Covid-19 patients

Introduction The coronavirus is a major emerging public health problem. This virus induces a respiratory disease as well as extra-respiratory diseases, mainly of the heart. The evolution of the cardiac damage caused by Covid-19 is still unknown and poorly studied. Objective Our objective is to study the cardiac repercussions of the Covid-19 virus by transthoracic echocardiography (TTE) in post-infection patients. Method We conducted a prospective study of patients diagnosed with Covid-19 pneumopathy, who were hospitalized at Fattouma Bourguiba Hospital in Monastir during the period from January 2021 to June 2021.TTE was performed after discharge from the hospital, in the echocardiography laboratory of the Cardiology Department B of the Fattouma Bourguiba University Hospital of Monastir. Demographic characteristics, scanographic and biological data, intra-hospital evolution were collected from the patients' medical records. Results In our study, we included 61 patients. TTE was performed in a mean of 61.3 days after Covid infection. For left ventricular (LV) study, the mean LV ejection fraction (LVEF) was 63.2±6.7%. The LV was dilated in 03 (4.9%) cases. LV end-diastolic diameter averaged 44.5±5.7mm. Global longitudinal LV Strain averaged −17±3.6% and was impaired in 27 (44.3%) patients. For the right ventricular (RV) study, RV systolic dysfunction was observed in 03 (4.9%) cases. The RV was dilated in 04 (6.6%) cases. Pulmonary hypertension (PAH) was found in 21 (34.4%) cases. The longitudinal Strain of the free wall of the VD was on average −19.4±5.2% and impaired in 32 (52%) patients. For the analytical study, the alteration of the LV Strain was correlated with male gender (P=0.007), ventral decubitus (VD) positioning (P=0.019) and hospitalization in an intensive care unit (P=0.045) (protective effect in the latter two cases). The presence of PAH was correlated with the antecedent of arterial hypertension (P=0.014) and the VD positioning (P=0.008). Impaired RV Strain was correlated with male gender (P<0.001). Conclusion In post-Covid-19 patients, LV and DV Strain functions are altered on average, despite normal LVEF and RV systolic function in the majority of patients.

Fast Unsupervised Residual Attention GAN for COVID-19 Detection

Recently, deep unsupervised learning methods based on Generative Adversarial Networks (GANs) have shown great potential for detecting anomalies. These last can appear both in global and local areas of an image. Consequently, ignoring these local information may lead to unreliable detection of anomalies. In this paper, we propose a residual GAN-based unsupervised learning approach capable of detecting anomalies at both image and pixel levels. Our method is applied for COVID-19 detection, it is based on the BigGAN model to ensure high-quality generated images, also it adds attention modules to capture spatial and channel-wise features to enhance salient regions and extract more detailed features. The proposed model is composed of three components: a generator, a discriminator, and an encoder. The encoder enables a fast mapping from images to the latent space, which facilitates the evaluation of unseen images. We evaluate the proposed method with by real-world benchmarking datasets and a public COVID-19 dataset and we illustrate the performance improvement at image and pixel levels.

Efficient Pneumonia Detection Method and Implementation in Chest X-ray Images Based on a Neuromorphic Spiking Neural Network

Deep Learning has solved numerous problems in image recognition and information processing, and is currently being employed in tackling the coronavirus disease (COVID-19) which has become a pandemic. Incisively, deep learning models are utilized in diagnosis systems as a method to detect COVID-19 related pneumonia by analyzing lung X-ray images of patients. The accuracy of this method is in the range of 80-90%. However, it is computationally complex, requires high power, and has low energy efficiency. Consequently, it is not suitable a diagnosis/detection method to be deployed on the edge. In this paper, we propose an efficient pneumonia (COVID-19) detection method and implementation in chest x-ray images based on a neuromorphic spiking neural network. This method is implemented on our previously proposed AI-enabled real-time biomedical system AIRBiS (AIRBiS project: u-aizu.ac.jp/misc/benablab/airbis.html) which is based on a high-performance low-power re-configurable AI-chip for inference, and an interactive user interface for effective operation and monitoring. The evaluation results show that the proposed method achieves 92.1%, and 80.7% detection accuracy of pneumonia (i.e., COVID-19) over-collected test data.

Automatic evaluation of 3D volume infection rates: Application to the Covid-19 context

Covid-19 is a highly contagious respiratory syndrome, officially declared a global pandemic on 11 March 2020. Due to its rapid spread and the exponential increase in the number of infected and deceased patients, manual diagnosis in the healthcare sector is insufficient to manage each patient individually, even the assessment of lesions by clinicians is approximate. Moreover, to date, no end-to-end tool is proposed for automatic volumetric quantification of Covid lesions. Hence, in this paper we report the implementation of a complete chain for automatic assessment of the degree of Covid-19 lesions. It includes (i) preparation of the private database, (ii) image pre-processing, (iii) automatic segmentation based on U-NET and evaluation of its results by the usual metrics, (iv) 3D reconstruction and finally (v) volumetric quantification of Covid-19 lesions using the digitised images as input. For validation, the process is applied to our own private database that we have created for this purpose. The results obtained are very encouraging. The evaluation of the segmentation for the lung by the metrics DICE, IOU, Precision, Recall and Accuracy yielded respectively: 0.81, 0.90, 0.93, 0.82 and 0.92. Similarly for lesions these values are: 0.89, 0.93, 0.93, 0.81 and 0.93 respectively. © 2022 IEEE.

A Novel Deep Learning Model for COVID-19 Detection from Combined Heterogeneous X-ray and CT Chest Images

COVID-19 originally started in Wuhan city in China. The disease rapidly became a worldwide pandemic, causing a respiratory illness with symptoms such as coughing, fever, and in more severe cases difficulty in breathing. With the current testing processes, it is very difficult and sometimes impossible to manage and provide the necessary treatment to suspected patients since the number of the infected is rapidly increasing. Hence, the availability of an artificial intelligent driven system can be an assistive tool to provide accurate diagnosis using radiology imaging techniques. In this paper, we put forward a new deep learning architecture, which integrates the Nested Residual Connections (NRCs) in a DarkCovidNet model, called DarkCovidNet-NRC, in order to classify chest images and to detect COVID-19 cases. The proposed architecture is validated with the K-fold cross-validation technique on X-ray and CT chest datasets separately and then combined. The experimental results reveal that the suggested model performs very well in the medical classification task and it competes with the state of the art in multiple performance metrics by respectively achieving an accuracy and precision of 0.9609 and 0.978 on the combined dataset. © 2021, Springer Nature Switzerland AG.