Accurately Discriminating COVID-19 from Viral and Bacterial Pneumonia According to CT Images Via Deep Learning

Diagnostic Value of 99mTc-Ubiquicidin Scintigraphy in Differentiating Bacterial from Nonbacterial Pneumonia

Purpose: Differentiating purely viral from bacterial etiologies continues to be a challenging yet key step in the management of community-acquired pneumonia (CAP), further highlighted since the COVID-19 pandemic. This study aims to evaluate the utility of 99mTc-ubiquicidin (UBI) in the differentiation of bacterial from nonbacterial pneumonia. Methods: A total of 30 patients with CAP were allocated into groups A, bacterial (n = 15), and B, viral pneumonia (n = 15). All patients underwent 99mTc-UBI scan with planar and single-photon emission computed tomography (SPECT) images of thorax acquired at 30 and 180 min postinjection. Target-to-background (T/B) ratios were calculated with values >1.4 interpreted as positive for bacterial infection. Correlation was made with computed tomography (CT) scan and polymerase chain reaction (PCR) results. Results: UBI scan was positive in 43.3% (n = 13) of patients, with sensitivity, specificity, and accuracy of 86.7%, 100%, and 93.3%, respectively, and close correlation with chest CT scan and PCR results (p-value = 0.000). Planar images were generally not helpful. Receiver operating characteristic curve analysis indicated similar diagnostic performance for 30-min and 3-h SPECT images by implementing T/B thresholds of 1.2 and 1.33, respectively. Conclusions: 99mTc-UBI SPECT is a promising modality for differentiating purely viral from bacterial or superimposed bacterial pneumonia and provides reliable evidence either to mandate or withhold administration of antibiotics in patients with CAP.

The Medical Complexity of Newly Admitted Long-Term Care Residents Before and During the COVID-19 Pandemic in Ontario, British Columbia, and Alberta: A Serial Cross-Sectional Study

The COVID-19 pandemic had profound effects on the long-term care (LTC) setting worldwide, including changes in admission practices. We aimed to describe the characteristics and medical complexity of newly admitted LTC residents before (March 1, 2019 to February 29, 2020) and during (March 1, 2020 to March 31, 2021) the COVID-19 pandemic via a population-based serial cross-sectional study in Ontario, Alberta, and British Columbia, Canada. With data from the Minimum Data Set 2.0 we characterize the medical complexity of newly admitted LTC residents via the Geriatric 5Ms framework (mind, mobility, medication, multicomplexity, matters most) through descriptive statistics (counts, percentages), stratified by pandemic wave, month, and province. We included 45 756 residents admitted in the year prior to and 35 744 during the first year of the pandemic. We found an increased proportion of residents with depression, requiring extensive assistance with activities of daily living, hip fractures, antipsychotic use, expected to live <6 months, with pneumonia, low social engagement, and admitted from acute care. Our study confirms an increase in medical complexity of residents admitted to LTC during the pandemic and can be used to plan services and interventions and as a baseline for continued monitoring in changes in population characteristics over time.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

Artificial intelligence for segmentation and classification of lobar, lobular, and interstitial pneumonia using case-specific CT information

Background

Pneumonia can be anatomically classified into lobar, lobular, and interstitial types, with each type associated with different pathogens. Utilizing artificial intelligence (AI) to determine the anatomical classifications of pneumonia and assist in refining the differential diagnosis may offer a more viable and clinically relevant solution. This study aimed to develop a multi-classification model capable of identifying the occurrence of pneumonia in patients by utilizing case-specific computed tomography (CT) information, categorizing the pneumonia type (lobar, lobular, and interstitial pneumonia), and performing segmentation of the associated lesions.

Methods

A total of 61 lobar pneumonia patients, 60 lobular pneumonia patients, and 60 interstitial pneumonia patients were consecutively enrolled at our local hospital from June 2020 and May 2022. All selected cases were divided into a training cohort (n=135) and an independent testing cohort (n=46). To generate the ground truth labels for the training process, manual segmentation and labeling were performed by three junior radiologists. Subsequently, the segmentations were manually reviewed and edited by a senior radiologist. AI models were developed to automatically segment the infected lung regions and classify the pneumonia. The accuracy of pneumonia lesion segmentation was analyzed and evaluated using the Dice coefficient. Receiver operating characteristic curves were plotted, and the area under the curve (AUC), accuracy, precision, sensitivity, and specificity were calculated to assess the efficacy of pneumonia classification.

Results

Our AI model achieved a Dice coefficient of 0.743 [95% confidence interval (CI): 0.657-0.826] for lesion segmentation in the training set and 0.723 (95% CI: 0.602-0.845) in the test set. In the test set, our model achieved an accuracy of 0.927 (95% CI: 0.876-0.978), precision of 0.889 (95% CI: 0.827-0.951), sensitivity of 0.889 (95% CI: 0.827-0.951), specificity of 0.946 (95% CI: 0.902-0.990), and AUC of 0.989 (95% CI: 0.969-1.000) for pneumonia classification. We trained the model using labels annotated by senior physicians and compared it to a model trained using labels annotated by junior physicians. The Dice coefficient of the model's segmentation improved by 0.014, increasing from 0.709 (95% CI: 0.589-0.830) to 0.723 (95% CI: 0.602-0.845), and the AUC improved by 0.042, rising from 0.947 to 0.989.

Conclusions

Our study presents a robust multi-task learning model with substantial promise in enhancing the segmentation and classification of pneumonia in medical imaging.

Using risk factors and markers to predict bacterial respiratory co-/superinfections in COVID-19 patients: is the antibiotic steward's toolbox full or empty?

BACKGROUND

Adequate diagnosis of bacterial respiratory tract co-/superinfection (bRTI) in coronavirus disease (COVID-19) patients is challenging, as there is insufficient knowledge about the role of risk factors and (para)clinical parameters in the identification of bacterial co-/superinfection in the COVID-19 setting. Empirical antibiotic therapy is mainly based on COVID-19 severity and expert opinion, rather than on scientific evidence generated since the start of the pandemic.

PURPOSE

We report the best available evidence regarding the predictive value of risk factors and (para)clinical markers in the diagnosis of bRTI in COVID-19 patients.

METHODS

A multidisciplinary team identified different potential risk factors and (para)clinical predictors of bRTI in COVID-19 and formulated one or two research questions per topic. After a thorough literature search, research gaps were identified, and suggestions concerning further research were formulated. The quality of this narrative review was ensured by following the Scale for the Assessment of Narrative Review Articles.

RESULTS

Taking into account the scarcity of scientific evidence for markers and risk factors of bRTI in COVID-19 patients, to date, COVID-19 severity is the only parameter which can be associated with higher risk of developing bRTI.

CONCLUSIONS

Evidence on the usefulness of risk factors and (para)clinical factors as predictors of bRTI in COVID-19 patients is scarce. Robust studies are needed to optimise antibiotic prescribing and stewardship activities in the context of COVID-19.

A Pictorial Essay Describing the CT Imaging Features of COVID-19 Cases throughout the Pandemic with a Special Focus on Lung Manifestations and Extrapulmonary Vascular Abdominal Complications

With the Omicron wave, SARS-CoV-2 infections improved, with less lung involvement and few cases of severe manifestations. In this pictorial review, there is a summary of the pathogenesis with particular focus on the interaction of the immune system and gut and lung axis in both pulmonary and extrapulmonary manifestations of COVID-19 and the computed tomography (CT) imaging features of COVID-19 pneumonia from the beginning of the pandemic, describing the typical features of COVID-19 pneumonia following the Delta variant and the atypical features appearing during the Omicron wave. There is also an outline of the typical features of COVID-19 pneumonia in cases of breakthrough infection, including secondary lung complications such as acute respiratory distress disease (ARDS), pneumomediastinum, pneumothorax, and lung pulmonary thromboembolism, which were more frequent during the first waves of the pandemic. Finally, there is a description of vascular extrapulmonary complications, including both ischemic and hemorrhagic abdominal complications.

Morphological appearance of the B.1.1.7 mutation of the novel coronavirus 2 (SARS-CoV-2) in chest CT

Background

Diagnosing a coronavirus disease 2019 (COVID-19) infection with high specificity in chest computed tomography (CT) imaging is considered possible due to distinctive imaging features of COVID-19 pneumonia. Since other viral non-COVID pneumonia show mostly a different distribution pattern, it is reasonable to assume that the patterns observed caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are a consequence of its genetically encoded molecular properties when interacting with the respiratory tissue. As more mutations of the initial SARS-CoV-2 wild-type with varying aggressiveness have been detected in the course of 2021, it became obvious that its genome is in a state of transformation and therefore a potential modification of the specific morphological appearance in CT may occur. The aim of this study was to quantitatively analyze the morphological differences of the SARS-CoV-2-B.1.1.7 mutation and wildtype variant in CT scans of the thorax.

Methods

We analyzed a dataset of 140 patients, which was divided into pneumonias caused by n=40 wildtype variants, n=40 B.1.1.7 variants, n=20 bacterial pneumonias, n=20 viral (non-COVID) pneumonias, and a test group of n=20 unremarkable CT examinations of the thorax. Semiautomated 3D segmentation of the lung tissue was performed for quantification of lung pathologies. The extent, ratio, and specific distribution of inflammatory affected lung tissue in each group were compared in a multivariate group analysis.

Results

Lung segmentation revealed significant difference between the extent of ground glass opacities (GGO) or consolidation comparing SARS-CoV-2 wild-type and B.1.1.7 variant. Wildtype and B.1.1.7 variant showed both a symmetric distribution pattern of stage-dependent GGO and consolidation within matched COVID-19 stages. Viral non-COVID pneumonias had significantly fewer consolidations than the bacterial, but also than the COVID-19 B.1.1.7 variant groups.

Conclusions

CT based segmentation showed no significant difference between the morphological appearance of the COVID-19 wild-type variant and the SARS-CoV-2 B.1.1.7 mutation. However, our approach allowed a semiautomatic quantification of bacterial and viral lung pathologies. Quantitative CT image analyses, such as the one presented, appear to be an important component of pandemic preparedness considering an organism with ongoing genetic change, to describe a potential arising change in CT morphological appearance of possible new upcoming COVID-19 variants of concern.

Application of Machine Learning and Deep Learning Techniques for COVID-19 Screening Using Radiological Imaging: A Comprehensive Review

Lung, being one of the most important organs in human body, is often affected by various SARS diseases, among which COVID-19 has been found to be the most fatal disease in recent times. In fact, SARS-COVID 19 led to pandemic that spreads fast among the community causing respiratory problems. Under such situation, radiological imaging-based screening [mostly chest X-ray and computer tomography (CT) modalities] has been performed for rapid screening of the disease as it is a non-invasive approach. Due to scarcity of physician/chest specialist/expert doctors, technology-enabled disease screening techniques have been developed by several researchers with the help of artificial intelligence and machine learning (AI/ML). It can be remarkably observed that the researchers have introduced several AI/ML/DL (deep learning) algorithms for computer-assisted detection of COVID-19 using chest X-ray and CT images. In this paper, a comprehensive review has been conducted to summarize the works related to applications of AI/ML/DL for diagnostic prediction of COVID-19, mainly using X-ray and CT images. Following the PRISMA guidelines, total 265 articles have been selected out of 1715 published articles till the third quarter of 2021. Furthermore, this review summarizes and compares varieties of ML/DL techniques, various datasets, and their results using X-ray and CT imaging. A detailed discussion has been made on the novelty of the published works, along with advantages and limitations.

Diagnostic performance of corona virus disease 2019 chest computer tomography image recognition based on deep learning: Systematic review and meta-analysis

BACKGROUND

To analyze the diagnosis performance of deep learning model used in corona virus disease 2019 (COVID-19) computer tomography(CT) chest scans. The included sample contains healthy people, confirmed COVID-19 patients and unconfirmed suspected patients with corresponding symptoms.

METHODS

PubMed, Web of Science, Wiley, China National Knowledge Infrastructure, WAN FANG DATA, and Cochrane Library were searched for articles. Three researchers independently screened the literature, extracted the data. Any differences will be resolved by consulting the third author to ensure that a highly reliable and useful research paper is produced. Data were extracted from the final articles, including: authors, country of study, study type, sample size, participant demographics, type and name of AI software, results (accuracy, sensitivity, specificity, ROC, and predictive values), other outcome(s) if applicable.

RESULTS

Among the 3891 searched results, 32 articles describing 51,392 confirmed patients and 7686 non-infected individuals met the inclusion criteria. The pooled sensitivity, the pooled specificity, positive likelihood ratio, negative likelihood ratio and the pooled diagnostic odds ratio (OR) is 0.87(95%CI [confidence interval]: 0.85, 0.89), 0.85(95%CI: 0.82, 0.87), 6.7(95%CI: 5.7, 7.8), 0.14(95%CI: 0.12, 0.16), and 49(95%CI: 38, 65). Further, the AUROC (area under the receiver operating characteristic curve) is 0.94(95%CI: 0.91, 0.96). Secondary outcomes are specific sensitivity and specificity within subgroups defined by different models. Resnet has the best diagnostic performance, which has the highest sensitivity (0.91[95%CI: 0.87, 0.94]), specificity (0.90[95%CI: 0.86, 0.93]) and AUROC (0.96[95%CI: 0.94, 0.97]), according to the AUROC, we can get the rank Resnet > Densenet > VGG > Mobilenet > Inception > Effficient > Alexnet.

CONCLUSIONS

Our study findings show that deep learning models have immense potential in accurately stratifying COVID-19 patients and in correctly differentiating them from patients with other types of pneumonia and normal patients. Implementation of deep learning-based tools can assist radiologists in correctly and quickly detecting COVID-19 and, consequently, in combating the COVID-19 pandemic.

Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model

Due to the COVID-19 pandemic, computerized COVID-19 diagnosis studies are proliferating. The diversity of COVID-19 models raises the questions of which COVID-19 diagnostic model should be selected and which decision-makers of healthcare organizations should consider performance criteria. Because of this, a selection scheme is necessary to address all the above issues. This study proposes an integrated method for selecting the optimal deep learning model based on a novel crow swarm optimization algorithm for COVID-19 diagnosis. The crow swarm optimization is employed to find an optimal set of coefficients using a designed fitness function for evaluating the performance of the deep learning models. The crow swarm optimization is modified to obtain a good selected coefficient distribution by considering the best average fitness. We have utilized two datasets: the first dataset includes 746 computed tomography images, 349 of them are of confirmed COVID-19 cases and the other 397 are of healthy individuals, and the second dataset are composed of unimproved computed tomography images of the lung for 632 positive cases of COVID-19 with 15 trained and pretrained deep learning models with nine evaluation metrics are used to evaluate the developed methodology. Among the pretrained CNN and deep models using the first dataset, ResNet50 has an accuracy of 91.46% and a F1-score of 90.49%. For the first dataset, the ResNet50 algorithm is the optimal deep learning model selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5715.988 for COVID-19 computed tomography lung images case considered differential advancement. In contrast, the VGG16 algorithm is the optimal deep learning model is selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5758.791 for the second dataset. Overall, InceptionV3 had the lowest performance for both datasets. The proposed evaluation methodology is a helpful tool to assist healthcare managers in selecting and evaluating the optimal COVID-19 diagnosis models based on deep learning.

A Novel Benchmark Dataset for COVID-19 Detection during Third Wave in Pakistan

Coronavirus (COVID-19) is a highly severe infection caused by the severe acute respiratory coronavirus 2 (SARS-CoV-2). The polymerase chain reaction (PCR) test is essential to confirm the COVID-19 infection, but it has certain limitations, including paucity of reagents, is computationally time-consuming, and requires expert clinicians. Clinicians suggest that the PCR test is not a reliable automated COVID-19 patient detection system. This study proposed a machine learning-based approach to evaluate the PCR role in COVID-19 detection. We collect real data containing 603 COVID-19 samples from the Pakistan Institute of Medical Sciences (PIMS) Hospital in Islamabad, Pakistan, during the third COVID-19 wave. The experiments are separated into two sets. The first set comprises 24 features, including PCR test results, whereas the second comprises 24 features without PCR test. The findings demonstrate that the decision tree achieves the best detection rate for positive and negative COVID-19 patients in both scenarios. The findings reveal that PCR does not contribute to detecting COVID-19 patients. The findings also aid in the early detection of COVID-19, mainly when PCR test results are insufficient for diagnosing COVID-19 and help developing countries with a paucity of PCR tests and specialist facilities.

Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning

Coronavirus 2 (SARS-CoV-2), often known by the name COVID-19, is a type of acute respiratory syndrome that has had a significant influence on both economy and health infrastructure worldwide. This novel virus is diagnosed utilising a conventional method known as the RT-PCR (Reverse Transcription Polymerase Chain Reaction) test. This approach, however, produces a lot of false-negative and erroneous outcomes. According to recent studies, COVID-19 can also be diagnosed using X-rays, CT scans, blood tests and cough sounds. In this article, we use blood tests and machine learning to predict the diagnosis of this deadly virus. We also present an extensive review of various existing machine-learning applications that diagnose COVID-19 from clinical and laboratory markers. Four different classifiers along with a technique called Synthetic Minority Oversampling Technique (SMOTE) were used for classification. Shapley Additive Explanations (SHAP) method was utilized to calculate the gravity of each feature and it was found that eosinophils, monocytes, leukocytes and platelets were the most critical blood parameters that distinguished COVID-19 infection for our dataset. These classifiers can be utilized in conjunction with RT-PCR tests to improve sensitivity and in emergency situations such as a pandemic outbreak that might happen due to new strains of the virus. The positive results indicate the prospective use of an automated framework that could help clinicians and medical personnel diagnose and screen patients.

Overview of deep learning models for identification Covid-19

The well-being and health of global population is continuously and badly affected by COVID-19 pandemic. Thus, to prevent the spread the pandemic between individuals, there is high importance in implementing automatic detection systems as rapid alternative diagnosis. The virus is affecting the person's respiratory system as well as creating white patchy shadows in the X-ray images of the lungs of individuals experiencing COVID-19. Also, deep learning can be defined as a useful and efficient AI technique used for analyzing chest X-ray images for reliable and effective screening of COVID-19; therefore, distinguishing people infected with COVID-19 and normal persons, and after that the infected individuals will be isolated for mitigating the virus spread. This study provides an overview regarding a few of the modern deep learning-based COVID-19, with design steps and types, also it compares the diagnostic method of COVID-19 with other methods of deep learning created with the use of radiology images. After a comparison between the most recent methods used in the previous works, it was found that RestNet50 pre-trained and DCNN model gives accuracy of 98%, which is the highest reported so far from among other proposed models were discussed in this paper.