CT-based severity assessment for COVID-19 using weakly supervised non-local CNN

A Simple Risk Formula for the Prediction of COVID-19 Hospital Mortality

SARS-CoV-2 respiratory infection is associated with significant morbidity and mortality in hospitalized patients. We aimed to assess the risk factors for hospital mortality in non-vaccinated patients during the 2021 spring wave in the Czech Republic. A total of 991 patients hospitalized between January 2021 and March 2021 with a PCR-confirmed SARS-CoV-2 acute respiratory infection in two university hospitals and five rural hospitals were included in this analysis. After excluding patients with unknown outcomes, 790 patients entered the final analyses. Out of 790 patients included in the analysis, 282/790 (35.7%) patients died in the hospital; 162/790 (20.5) were male and 120/790 (15.2%) were female. There were 141/790 (18%) patients with mild, 461/790 (58.3%) with moderate, and 187/790 (23.7%) with severe courses of the disease based mainly on the oxygenation status. The best-performing multivariate regression model contains only two predictors-age and the patient's state; both predictors were rendered significant (p < 0.0001). Both age and disease state are very significant predictors of hospital mortality. An increase in age by 10 years raises the risk of hospital mortality by a factor of 2.5, and a unit increase in the oxygenation status raises the risk of hospital mortality by a factor of 20.

Ensemble classification of integrated CT scan datasets in detecting COVID-19 using feature fusion from contourlet transform and CNN

The COVID-19 disease caused by coronavirus is constantly changing due to the emergence of different variants and thousands of people are dying every day worldwide. Early detection of this new form of pulmonary disease can reduce the mortality rate. In this paper, an automated method based on machine learning (ML) and deep learning (DL) has been developed to detect COVID-19 using computed tomography (CT) scan images extracted from three publicly available datasets (A total of 11,407 images; 7397 COVID-19 images and 4010 normal images). An unsupervised clustering approach that is a modified region-based clustering technique for segmenting COVID-19 CT scan image has been proposed. Furthermore, contourlet transform and convolution neural network (CNN) have been employed to extract features individually from the segmented CT scan images and to fuse them in one feature vector. Binary differential evolution (BDE) approach has been employed as a feature optimization technique to obtain comprehensible features from the fused feature vector. Finally, a ML/DL-based ensemble classifier considering bagging technique has been employed to detect COVID-19 from the CT images. A fivefold and generalization cross-validation techniques have been used for the validation purpose. Classification experiments have also been conducted with several pre-trained models (AlexNet, ResNet50, GoogleNet, VGG16, VGG19) and found that the ensemble classifier technique with fused feature has provided state-of-the-art performance with an accuracy of 99.98%.

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.

Predicting the Severity of COVID-19 from Lung CT Images Using Novel Deep Learning

Purpose

Coronavirus 2019 (COVID-19) had major social, medical, and economic impacts globally. The study aims to develop a deep-learning model that can predict the severity of COVID-19 in patients based on CT images of their lungs.

Methods

COVID-19 causes lung infections, and qRT-PCR is an essential tool used to detect virus infection. However, qRT-PCR is inadequate for detecting the severity of the disease and the extent to which it affects the lung. In this paper, we aim to determine the severity level of COVID-19 by studying lung CT scans of people diagnosed with the virus.

Results

We used images from King Abdullah University Hospital in Jordan; we collected our dataset from 875 cases with 2205 CT images. A radiologist classified the images into four levels of severity: normal, mild, moderate, and severe. We used various deep-learning algorithms to predict the severity of lung diseases. The results show that the best deep-learning algorithm used is Resnet101, with an accuracy score of 99.5% and a data loss rate of 0.03%.

Conclusion

The proposed model assisted in diagnosing and treating COVID-19 patients and helped improve patient outcomes.

Weakly supervised segmentation of COVID-19 infection with local lesion coherence on CT images

At the end of 2019, a novel coronavirus, COVID-19, was ravaging the world, wreaking havoc on public health and the global economy. Today, although Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is the gold standard for COVID-19 clinical diagnosis, it is a time-consuming and labor-intensive procedure. Simultaneously, an increasing number of individuals are seeking for better alternatives to RT-PCR. As a result, automated identification of COVID-19 lung infection in computed tomography (CT) images may help traditional diagnostic approaches in determining the severity of the disease. Unfortunately, a shortage of labeled training sets makes using AI deep learning algorithms to accurately segregate diseased regions in CT scan challenging. We design a simple and effective weakly supervised learning strategy for COVID-19 CT image segmentation to overcome the segmentation issue in the absence of adequate labeled data, namely LLC-Net. Unlike others weakly supervised work that uses a complex training procedure, our LLC-Net is relatively easy and repeatable. We propose a Local Self-Coherence Mechanism to accomplish label propagation based on lesion area labeling characteristics for weak labels that cannot offer comprehensive lesion areas, hence forecasting a more complete lesion area. Secondly, when the COVID-19 training samples are insufficient, the Scale Transform for Self-Correlation is designed to optimize the robustness of the model to ensure that the CT images are consistent in the prediction results from different angles. Finally, in order to constrain the segmentation accuracy of the lesion area, the Lesion Infection Edge Attention Module is used to improve the information expression ability of edge modeling. Experiments on public datasets demonstrate that our method is more effective than other weakly supervised methods and achieves a new state-of-the-art performance.

HT-Net: A Hybrid Transformer Network for Fundus Vessel Segmentation

Doctors usually diagnose a disease by evaluating the pattern of abnormal blood vessels in the fundus. At present, the segmentation of fundus blood vessels based on deep learning has achieved great success, but it still faces the problems of low accuracy and capillary rupture. A good vessel segmentation method can guide the early diagnosis of eye diseases, so we propose a novel hybrid Transformer network (HT-Net) for fundus imaging analysis. HT-Net can improve the vessel segmentation quality by capturing detailed local information and implementing long-range information interactions, and it mainly consists of the following blocks. The feature fusion block (FFB) is embedded in the shallow levels, and FFB enriches the feature space. In addition, the feature refinement block (FRB) is added to the shallow position of the network, which solves the problem of vessel scale change by fusing multi-scale feature information to improve the accuracy of segmentation. Finally, HT-Net's bottom-level position can capture remote dependencies by combining the Transformer and CNN. We prove the performance of HT-Net on the DRIVE, CHASE_DB1, and STARE datasets. The experiment shows that FFB and FRB can effectively improve the quality of microvessel segmentation by extracting multi-scale information. Embedding efficient self-attention mechanisms in the network can effectively improve the vessel segmentation accuracy. The HT-Net exceeds most existing methods, indicating that it can perform the task of vessel segmentation competently.

A Comprehensive Review of Machine Learning Used to Combat COVID-19

Coronavirus disease (COVID-19) has had a significant impact on global health since the start of the pandemic in 2019. As of June 2022, over 539 million cases have been confirmed worldwide with over 6.3 million deaths as a result. Artificial Intelligence (AI) solutions such as machine learning and deep learning have played a major part in this pandemic for the diagnosis and treatment of COVID-19. In this research, we review these modern tools deployed to solve a variety of complex problems. We explore research that focused on analyzing medical images using AI models for identification, classification, and tissue segmentation of the disease. We also explore prognostic models that were developed to predict health outcomes and optimize the allocation of scarce medical resources. Longitudinal studies were conducted to better understand COVID-19 and its effects on patients over a period of time. This comprehensive review of the different AI methods and modeling efforts will shed light on the role that AI has played and what path it intends to take in the fight against COVID-19.

Imaging Severity COVID-19 Assessment in Vaccinated and Unvaccinated Patients: Comparison of the Different Variants in a High Volume Italian Reference Center

Purpose: To analyze the vaccine effect by comparing five groups: unvaccinated patients with Alpha variant, unvaccinated patients with Delta variant, vaccinated patients with Delta variant, unvaccinated patients with Omicron variant, and vaccinated patients with Omicron variant, assessing the “gravity” of COVID-19 pulmonary involvement, based on CT findings in critically ill patients admitted to Intensive Care Unit (ICU). Methods: Patients were selected by ICU database considering the period from December 2021 to 23 March 2022, according to the following inclusion criteria: patients with proven Omicron variant COVID-19 infection with known COVID-19 vaccination with at least two doses and with chest Computed Tomography (CT) study during ICU hospitalization. Wee also evaluated the ICU database considering the period from March 2020 to December 2021, to select unvaccinated consecutive patients with Alpha variant, subjected to CT study, consecutive unvaccinated and vaccinated patients with Delta variant, subjected to CT study, and, consecutive unvaccinated patients with Omicron variant, subjected to CT study. CT images were evaluated qualitatively using a severity score scale of 5 levels (none involvement, mild: ≤25% of involvement, moderate: 26−50% of involvement, severe: 51−75% of involvement, and critical involvement: 76−100%) and quantitatively, using the Philips IntelliSpace Portal clinical application CT COPD computer tool. For each patient the lung volumetry was performed identifying the percentage value of aerated residual lung volume. Non-parametric tests for continuous and categorical variables were performed to assess statistically significant differences among groups. Results: The patient study group was composed of 13 vaccinated patients affected by the Omicron variant (Omicron V). As control groups we identified: 20 unvaccinated patients with Alpha variant (Alpha NV); 20 unvaccinated patients with Delta variant (Delta NV); 18 vaccinated patients with Delta variant (Delta V); and 20 unvaccinated patients affected by the Omicron variant (Omicron NV). No differences between the groups under examination were found (p value > 0.05 at Chi square test) in terms of risk factors (age, cardiovascular diseases, diabetes, immunosuppression, chronic kidney, cardiac, pulmonary, neurologic, and liver disease, etc.). A different median value of aerated residual lung volume was observed in the Delta variant groups: median value of aerated residual lung volume was 46.70% in unvaccinated patients compared to 67.10% in vaccinated patients. In addition, in patients with Delta variant every other extracted volume by automatic tool showed a statistically significant difference between vaccinated and unvaccinated group. Statistically significant differences were observed for each extracted volume by automatic tool between unvaccinated patients affected by Alpha variant and vaccinated patients affected by Delta variant of COVID-19. Good statistically significant correlations among volumes extracted by automatic tool for each lung lobe and overall radiological severity score were obtained (ICC range 0.71−0.86). GGO was the main sign of COVID-19 lesions on CT images found in 87 of the 91 (95.6%) patients. No statistically significant differences were observed in CT findings (ground glass opacities (GGO), consolidation or crazy paving sign) among patient groups. Conclusion: In our study, we showed that in critically ill patients no difference were observed in terms of severity of disease or exitus, between unvaccinated and vaccinated patients. The only statistically significant differences were observed, with regard to the severity of COVID-19 pulmonary parenchymal involvement, between unvaccinated patients affected by Alpha variant and vaccinated patients affected by Delta variant, and between unvaccinated patients with Delta variant and vaccinated patients with Delta variant.