The value of artificial intelligence and imaging diagnosis in the fight against COVID-19.

The outbreak of the new type of coronavirus pneumonia (COVID-19) has caused a huge impact on the world. In this case, only by adhering to the prevention and control methods of early diagnosis, early isolation, and early treatment, can the spread of the virus be prevented to the greatest extent. This article uses artificial intelligence-assisted medical imaging diagnosis as the research object, combines artificial intelligence and CT medical imaging diagnosis, introduces an intelligent COVID-19 detection system, and uses it to achieve COVID-19 disease screening and lesion evaluation. CT examination has the advantages of fast speed and high accuracy, which can provide a favorable basis for clinical diagnosis. This article collected 32 lung CT scan images of patients with confirmed COVID-19. Two professional radiologists analyzed the CT images using traditional imaging diagnostic methods and artificial intelligence-assisted imaging diagnostic methods, and the comparison showed the gap between the two methods. According to experiments, CT imaging diagnosis assisted by artificial intelligence only takes 0.744 min on average, which can save a lot of time and cost compared with the average time of 3.623 min for conventional diagnosis. In terms of comprehensive test accuracy, it can be concluded that the combination of artificial intelligence and imaging diagnosis has extremely high application value in COVID-19 diagnosis.

Epicardial and pericoronary adipose tissue in severe COVID-19 infection.

OBJECTIVE: To investigate the association between epicardial and pericoronary adipose tissue thicknesses measured with computed tomography (CT) and severity of COVID-19 infection. METHODS: We recruited 504 patients admitted with RT-PCR-proven diagnosis of COVID-19 infection and underwent simultaneous Chest CT scanning. Epicardial adipose tissue thickness (EAT) and pericardial adipose tissue thickness (PCAT) were measured by CT. Comparisons were performed between ICU admitting and non-ICU admitting patients were performed. RESULTS: Of 504 patients, 423 patients were hospitalised in normal wards or followed as outpatient, and 81 patients were admitted to ICU. EAT and PCAT were significantly increased in ICU patients (5.98[5.06-7.13] mm vs. 8.05[6.90-9.89] mm, p < 0.001 and 9.3[7.4-11.5] mm vs. 11.2[10.3-13.2] mm, p < 0.001, respectively). In multiple logistic regression analyses, EAT and PCAT were independent predictors of ICU admission. A cut-off point of 6.64 mm EAT has a sensitivity of 82.7% and a specificity of 66.7% (AUC = 0.789, 95% CI: 0.744-0.833, p < 0.001) and a cut-off point of 9.85 mm PCAT has a sensitivity of 91.4% and a specificity of 61.2% (AUC = 0.744, 95% CI: 0.700-0.788, p < 0.001). CONCLUSION: We found that both increased EAT and PCAT were associated with the severity of COVID-19 infection defined as the need for ICU admission.

Covid-19 imaging: A narrative review.

BACKGROUND: The 2019 novel coronavirus disease (COVID-19) imaging data is dispersed in numerous publications. A cohesive literature review is to be assembled. OBJECTIVE: To summarize the existing literature on Covid-19 pneumonia imaging including precautionary measures for radiology departments, Chest CT's role in diagnosis and management, imaging findings of Covid-19 patients including children and pregnant women, artificial intelligence applications and practical recommendations. METHODS: A systematic literature search of PubMed/med line electronic databases. RESULTS: The radiology department's staff is on the front line of the novel coronavirus outbreak. Strict adherence to precautionary measures is the main defense against infection's spread. Although nucleic acid testing is Covid-19's pneumonia diagnosis gold standard; kits shortage and low sensitivity led to the implementation of the highly sensitive chest computed tomography amidst initial diagnostic tools. Initial Covid-19 CT features comprise bilateral, peripheral or posterior, multilobar ground-glass opacities, predominantly in the lower lobes. Consolidations superimposed on ground-glass opacifications are found in few cases, preponderantly in the elderly. In later disease stages, GGO transformation into multifocal consolidations, thickened interlobular and intralobular lines, crazy paving, traction bronchiectasis, pleural thickening, and subpleural bands are reported. Standardized CT reporting is recommended to guide radiologists. While lung ultrasound, pulmonary MRI, and PET CT are not Covid-19 pneumonia's first-line investigative diagnostic modalities, their characteristic findings and clinical value are outlined. Artificial intelligence's role in strengthening available imaging tools is discussed. CONCLUSION: This review offers an exhaustive analysis of the current literature on imaging role and findings in COVID-19 pneumonia.

Abnormality detection and intelligent severity assessment of human chest computed tomography scans using deep learning: a case study on SARS-COV-2 assessment.

Different respiratory infections cause abnormal symptoms in lung parenchyma that show in chest computed tomography. Since December 2019, the SARS-COV-2 virus, which is the causative agent of COVID-19, has invaded the world causing high numbers of infections and deaths. The infection with SARS-COV-2 virus shows an abnormality in lung parenchyma that can be effectively detected using Computed Tomography (CT) imaging. In this paper, a novel computer aided framework (COV-CAF) is proposed for classifying the severity degree of the infection from 3D Chest Volumes. COV-CAF fuses traditional and deep learning approaches. The proposed COV-CAF consists of two phases: the preparatory phase and the feature analysis and classification phase. The preparatory phase handles 3D-CT volumes and presents an effective cut choice strategy for choosing informative CT slices. The feature analysis and classification phase incorporate fuzzy clustering for automatic Region of Interest (RoI) segmentation and feature fusion. In feature fusion, automatic features are extracted from a newly introduced Convolution Neural Network (Norm-VGG16) and are fused with spatial hand-crafted features extracted from segmented RoI. Experiments are conducted on MosMedData: Chest CT Scans with COVID-19 Related Findings with COVID-19 severity classes and SARS-COV-2 CT-Scan benchmark datasets. The proposed COV-CAF achieved remarkable results on both datasets. On MosMedData dataset, it achieved an overall accuracy of 97.76% and average sensitivity of 96.73%, while on SARS-COV-2 CT-Scan dataset it achieves an overall accuracy and sensitivity 97.59% and 98.41% respectively.

Pectoralis muscle area measured at T4 level is closely associated with adverse COVID-19 outcomes in hospitalized patients.

OBJECTIVES: Skeletal muscle area (SMA) at T4 level on chest computed tomography (CT) is a newly available method that can be used as a surrogate sarcopenia marker. The objective of this study is to evaluate association of SMA with adverse COVID-19 outcomes in hospitalized patients. METHODS: Hospitalized COVID-19 patients were prospectively recorded in a database containing age, gender, date of admission, date of outcome (discharge, mortality, presence of intensive care unit (ICU) stay, additional coding information (comorbidities, superimposed conditions). Admission CT-scans were retrospectively evaluated for segmentation (bilateral pectoralis major/minor, erector spinae, levator scapulae, rhomboideus minor and major and transversospinalis muscles) and SMA calculation using 3-D slicer software. RESULTS: 167 cases were evaluated (68 male, 72 female, 140 survived, 27 dead). Muscle area was lower in patients with ICU stay (p=0.023, p=0.018, p=0.008) and mortality outcome (p=0.004, p=0.007, p=0.002) for pectoralis, back and SMA. In multivariate Cox-regression analysis, hazard ratio (HR) value for the pectoralis muscle area value below 2800 mm2 was found to be 3.138(95% CI: 1.171-8.413) for mortality and 2.361(95% CI: 1.012-5.505) for ICU. CONCLUSIONS: Pectoralis muscle area measured at T4 level with 3-D slicer was closely associated with adverse outcomes (mortality, ICU stay) in hospitalized COVID-19 patients. Since early treatment methods for COVID-19 are being evaluated, this method may be a useful adjunct to clinical decision making in regard to prioritization.

COVID-19 Detection using adopted convolutional neural networks and high-performance computing.

The COVID 19 pandemic is highly contagious disease is wreaking havoc on people's health and well-being around the world. Radiological imaging with chest radiography is one among the key screening procedure. This disease contaminates the respiratory system and impacts the alveoli, which are small air sacs in the lungs. Several artificial intelligence (AI)-based method to detect COVID-19 have been introduced. The recognition of disease patients using features and variation in chest radiography images was demonstrated using this model. In proposed paper presents a model, a deep convolutional neural network (CNN) with ResNet50 configuration, that really is freely-available and accessible to the common people for detecting this infection from chest radiography scans. The introduced model is capable of recognizing coronavirus diseases from CT scan images that identifies the real time condition of covid-19 patients. Furthermore, the database is capable of tracking detected patients and maintaining their database for increasing accuracy of the training model. The proposed model gives approximately 97% accuracy in determining the above-mentioned results related to covid-19 disease by employing the combination of adopted-CNN and ResNet50 algorithms.

A specific combination of laboratory data is associated with overweight lungs in patients with COVID-19 pneumonia at hospital admission: secondary cross-sectional analysis of a randomized clinical trial.

Background: Lung weight may be measured with quantitative chest computed tomography (CT) in patients with COVID-19 to characterize the severity of pulmonary edema and assess prognosis. However, this quantitative analysis is often not accessible, which led to the hypothesis that specific laboratory data may help identify overweight lungs. Methods: This cross-sectional study was a secondary analysis of data from SARITA2, a randomized clinical trial comparing nitazoxanide and placebo in patients with COVID-19 pneumonia. Adult patients (≥18 years) requiring supplemental oxygen due to COVID-19 pneumonia were enrolled between April 20 and October 15, 2020, in 19 hospitals in Brazil. The weight of the lungs as well as laboratory data [hemoglobin, leukocytes, neutrophils, lymphocytes, C-reactive protein, D-dimer, lactate dehydrogenase (LDH), and ferritin] and 47 additional specific blood biomarkers were assessed. Results: Ninety-three patients were included in the study: 46 patients presented with underweight lungs (defined by ≤0% of excess lung weight) and 47 patients presented with overweight lungs (>0% of excess lung weight). Leukocytes, neutrophils, D-dimer, and LDH were higher in patients with overweight lungs. Among the 47 blood biomarkers investigated, interferon alpha 2 protein was higher and leukocyte inhibitory factor was lower in patients with overweight lungs. According to CombiROC analysis, the combinations of D-dimer/LDH/leukocytes, D-dimer/LDH/neutrophils, and D-dimer/LDH/leukocytes/neutrophils achieved the highest area under the curve with the best accuracy to detect overweight lungs. Conclusion: The combinations of these specific laboratory data: D-dimer/LDH/leukocytes or D-dimer/LDH/neutrophils or D-dimer/LDH/leukocytes/neutrophils were the best predictors of overweight lungs in patients with COVID-19 pneumonia at hospital admission. Clinical trial registration: Brazilian Registry of Clinical Trials (REBEC) number RBR-88bs9x and ClinicalTrials.gov number NCT04561219.

Applying the Global Leadership Initiative on Malnutrition criteria in patients admitted with SARS-CoV-2 infection using computed tomography imaging.

BACKGROUND: Patients with low muscle mass and acute SARS-CoV-2 infection meet the Global Leadership Initiative on Malnutrition (GLIM) etiologic and phenotypic criteria to diagnose malnutrition, respectively. However, available cut-points to classify individuals with low muscle mass are not straightforward. Using computed tomography (CT) to determine low muscularity, we assessed the prevalence of malnutrition using the GLIM framework and associations with clinical outcomes. METHODS: A retrospective cohort was conducted gathering patient data from various clinical resources. Patients admitted to the COVID-19 unit (March 2020 to June 2020) with appropriate/evaluable CT studies (chest or abdomen/pelvis) within the first 5 days of admission were considered eligible. Sex- and vertebral-specific skeletal muscle indices (SMI; cm2 /m2 ) from healthy controls were used to determine low muscle mass. Injury-adjusted SMI were derived, extrapolated from cancer cut-points and explored. Descriptive statistics and mediation analyses were completed. RESULTS: Patients (n = 141) were 58.2 years of age and racially diverse. Obesity (46%), diabetes (40%), and cardiovascular disease (68%) were prevalent. Using healthy controls and injury-adjusted SMI, malnutrition prevalence was 26% (n = 36/141) and 50% (n = 71/141), respectively. Mediation analyses demonstrated a significant reduction in the effect of malnutrition on outcomes in the presence of Acute Physiology and Chronic Health Evaluation II, supporting the mediating effects of severity of illness intensive care unit (ICU) admission, ICU length of stay, mechanical ventilation, complex respiratory support, discharge status (all P values = 0.03), and 28-day mortality (P = 0.04). CONCLUSIONS: Future studies involving the GLIM criteria should consider these collective findings in their design, analyses, and implementation.

Comparison between original SARS-CoV-2 strain and omicron variant on thin-section chest CT imaging of COVID-19 pneumonia.

OBJECTIVES: We investigated different computed tomography (CT) features between Omicron-variant and original-strain SARS-CoV­2 pneumonia to facilitate the clinical management. MATERIALS AND METHODS: Medical records were retrospectively reviewed to select patients with original-strain SARS-CoV­2 pneumonia from February 22 to April 22, 2020, or Omicron-variant SARS-CoV­2 pneumonia from March 26 to May 31, 2022. Data on the demographics, comorbidities, symptoms, clinical types, and CT features were compared between the two groups. RESULTS: There were 62 and 78 patients with original-strain or Omicron-variant SARS-CoV­2 pneumonia, respectively. There were no differences between the two groups in terms of age, sex, clinical types, symptoms, and comorbidities. The main CT features differed between the two groups (p = 0.003). There were 37 (59.7%) and 20 (25.6%) patients with ground-glass opacities (GGO) in the original-strain and Omicron-variant pneumonia, respectively. A consolidation pattern was more frequently observed in the Omicron-variant than original-strain pneumonia (62.8% vs. 24.2%). There was no difference in crazy-paving pattern between the original-strain and Omicron-variant pneumonia (16.1% vs. 11.6%). Pleural effusion was observed more often in Omicron-variant pneumonia, while subpleural lesions were more common in the original-strain pneumonia. The CT score in the Omicron-variant group was higher than that in the original-strain group for critical-type (17.00, 16.00-18.00 vs. 16.00, 14.00-17.00, p = 0.031) and for severe-type (13.00, 12.00-14.00 vs 12.00, 10.75-13.00, p = 0.027) pneumonia. CONCLUSION: The main CT finding of the Omicron-variant SARS-CoV­2 pneumonia included consolidations and pleural effusion. By contrast, CT findings of original-strain SARS-CoV­2 pneumonia showed frequent GGO and subpleural lesions, but without pleural effusion. The CT scores were also higher in the critical and severe types of Omicron-variant than original-strain pneumonia.

Perforated Stress Ulcer of the Duodenum: a Case of an Unexpected Diagnosis in a COVID-19 Patient Following Dilatation and Curettage Procedure.

Background: Stress ulcers in the upper gastrointestinal tract can arise from pathologies related to erosive or inflammatory insults in critically ill patients. The relationship between stressful bodily events and the ischemia and perforation of stress ulcers is poorly understood. Objective: We present a case of perforated stress ulcer following an abortion that was treated by dilatation and curettage (D&C) and complicated by a coronavirus disease 2019 (COVID-19) infection. Case presentation: A 40-year-old lady presented to the emergency room complaining of diffuse abdominal pain, she was recently diagnosed with an incomplete abortion and managed via a D&C procedure in an external hospital. A computed tomography (CT) scan was done at our center for the abdomen and pelvis, showing extensive pneumoperitoneum, which brought the radiologist's attention to suspect a small bowel perforation presumably accompanying a uterine perforation secondary to the D&C. There were no obvious signs of pelvic small bowel perforation in the initial CT images. The perforated duodenal stress ulcer was diagnosed the next day by a new CT scan following oral contrast ingestion and managed surgically by repair and omental patch, and no other bowel perforations were found upon surgical exploration. After the surgery, the patient was diagnosed with COVID-19, and her clinical status deteriorated gradually during the following week, and she passed away from a cardiac arrest. Conclusion: It is unclear whether septic abortion or COVID-19 has resulted in stress ulcer perforation in our patient. This case report highlights the importance of raising early suspicion in the diagnosis of stress ulcer perforation in critically ill patients to reduce the risk of morbidity and mortality.

Diagnostic performance of standardized typical CT findings for COVID-19: a systematic review and meta-analysis.

OBJECTIVE: To meta-analyze diagnostic performance measures of standardized typical CT findings for COVID-19 and examine these measures by region and national income. METHODS: MEDLINE and Embase were searched from January 2020 to April 2022 for diagnostic studies using the Radiological Society of North America (RSNA) classification or the COVID-19 Reporting and Data System (CO-RADS) for COVID-19. Patient and study characteristics were extracted. We pooled the diagnostic performance of typical CT findings in the RSNA and CO-RADS systems and interobserver agreement. Meta-regression was performed to examine the effect of potential explanatory factors on the diagnostic performance of the typical CT findings. RESULTS: We included 42 diagnostic performance studies with 6777 PCR-positive and 9955 PCR-negative patients from 18 developing and 24 developed countries covering the Americas, Europe, Asia, and Africa. The pooled sensitivity was 70% (95% confidence interval [CI]: 65%, 74%; I2 = 92%), and the pooled specificity was 90% (95% CI 86%, 93%; I2 = 94%) for the typical CT findings of COVID-19. The sensitivity and specificity of the typical CT findings did not differ significantly by national income and the region of the study (p > 0.1, respectively). The pooled interobserver agreement from 19 studies was 0.72 (95% CI 0.63, 0.81; I2 = 99%) for the typical CT findings and 0.67 (95% CI 0.61, 0.74; I2 = 99%) for the overall CT classifications. CONCLUSION: The standardized typical CT findings for COVID-19 provided moderate sensitivity and high specificity globally, regardless of region and national income, and were highly reproducible between radiologists. CRITICAL RELEVANCE STATEMENT: Standardized typical CT findings for COVID-19 provided a reproducible high diagnostic accuracy globally. KEY POINTS: Standardized typical CT findings for COVID-19 provide high sensitivity and specificity. Typical CT findings show high diagnosability regardless of region or income. The interobserver agreement for typical findings of COVID-19 is substantial.

Role of Imaging in the Management of Patients with SARS-CoV-2 Lung Involvement Admitted to the Emergency Department: A Systematic Review.

During the waves of the coronavirus disease (COVID-19) pandemic, emergency departments were overflowing with patients suffering with suspected medical or surgical issues. In these settings, healthcare staff should be able to deal with different medical and surgical scenarios while protecting themselves against the risk of contamination. Various strategies were used to overcome the most critical issues and guarantee quick and efficient diagnostic and therapeutic charts. The use of saliva and nasopharyngeal swab Nucleic Acid Amplification Tests (NAAT) in the diagnosis of COVID-19 was one of the most adopted worldwide. However, NAAT results were slow to report and could sometimes create significant delays in patient management, especially during pandemic peaks. On these bases, radiology has played and continues to play an essential role in detecting COVID-19 patients and solving differential diagnosis between different medical conditions. This systematic review aims to summarize the role of radiology in the management of COVID-19 patients admitted to emergency departments by using chest X-rays (CXR), computed tomography (CT), lung ultrasounds (LUS), and artificial intelligence (AI).

Ankle Sprains in Athletes: Current Epidemiological, Clinical and Imaging Trends.

Purpose: Ankle injuries are frequent sports injuries. Despite optimizing treatment strategies during recent years, the percentage of chronification following an ankle sprain remains high. The purpose of this review article is, to highlight current epidemiological, clinical and novel advanced cross-sectional imaging trends that may help to evaluate ankle sprain injuries. Methods: Systematic PubMed literature research. Identification and review of studies (i) analyzing and describing ankle sprain and (ii) focusing on advanced cross-sectional imaging techniques at the ankle. Results: The ankle is one of the most frequently injured body parts in sports. During the COVID-19 pandemic, there was a change in sporting behavior and sports injuries. Ankle sprains account for about 16-40% of the sports-related injuries. Novel cross-sectional imaging techniques, including Compressed Sensing MRI, 3D MRI, ankle MRI with traction or plantarflexion-supination, quantitative MRI, CT-like MRI, CT arthrography, weight-bearing cone beam CT, dual-energy CT, photon-counting CT, and projection-based metal artifact reduction CT may be introduced for detection and evaluation of specific pathologies after ankle injury. While simple ankle sprains are generally treated conservatively, unstable syndesmotic injuries may undergo stabilization using suture-button-fixation. Minced cartilage implantation is a novel cartilage repair technique for osteochondral defects at the ankle. Conclusion: Applications and advantages of different cross-sectional imaging techniques at the ankle are highlighted. In a personalized approach, optimal imaging techniques may be chosen that best detect and delineate structural ankle injuries in athletes.

CRV-NET: Robust Intensity Recognition of Coronavirus in Lung Computerized Tomography Scan Images.

The early diagnosis of infectious diseases is demanded by digital healthcare systems. Currently, the detection of the new coronavirus disease (COVID-19) is a major clinical requirement. For COVID-19 detection, deep learning models are used in various studies, but the robustness is still compromised. In recent years, deep learning models have increased in popularity in almost every area, particularly in medical image processing and analysis. The visualization of the human body's internal structure is critical in medical analysis; many imaging techniques are in use to perform this job. A computerized tomography (CT) scan is one of them, and it has been generally used for the non-invasive observation of the human body. The development of an automatic segmentation method for lung CT scans showing COVID-19 can save experts time and can reduce human error. In this article, the CRV-NET is proposed for the robust detection of COVID-19 in lung CT scan images. A public dataset (SARS-CoV-2 CT Scan dataset), is used for the experimental work and customized according to the scenario of the proposed model. The proposed modified deep-learning-based U-Net model is trained on a custom dataset with 221 training images and their ground truth, which was labeled by an expert. The proposed model is tested on 100 test images, and the results show that the model segments COVID-19 with a satisfactory level of accuracy. Moreover, the comparison of the proposed CRV-NET with different state-of-the-art convolutional neural network models (CNNs), including the U-Net Model, shows better results in terms of accuracy (96.67%) and robustness (low epoch value in detection and the smallest training data size).

Automated screening of computed tomography using weakly supervised anomaly detection.

BACKGROUND: Current artificial intelligence studies for supporting CT screening tasks depend on either supervised learning or detecting anomalies. However, the former involves a heavy annotation workload owing to requiring many slice-wise annotations (ground truth labels); the latter is promising, but while it reduces the annotation workload, it often suffers from lower performance. This study presents a novel weakly supervised anomaly detection (WSAD) algorithm trained based on scan-wise normal and anomalous annotations to provide better performance than conventional methods while reducing annotation workload. METHODS: Based on surveillance video anomaly detection methodology, feature vectors representing each CT slice were trained on an AR-Net-based convolutional network using a dynamic multiple-instance learning loss and a center loss function. The following two publicly available CT datasets were retrospectively analyzed: the RSNA brain hemorrhage dataset (normal scans: 12,862; scans with intracranial hematoma: 8882) and COVID-CT set (normal scans: 282; scans with COVID-19: 95). RESULTS: Anomaly scores of each slice were successfully predicted despite inaccessibility to any slice-wise annotations. Slice-level area under the curve (AUC), sensitivity, specificity, and accuracy from the brain CT dataset were 0.89, 0.85, 0.78, and 0.79, respectively. The proposed method reduced the number of annotations in the brain dataset by 97.1% compared to an ordinary slice-level supervised learning method. CONCLUSION: This study demonstrated a significant annotation reduction in identifying anomalous CT slices compared to a supervised learning approach. The effectiveness of the proposed WSAD algorithm was verified through higher AUC than existing anomaly detection techniques.

Radiological Differences in COVID-19 Related Lung Manifestations Between Smokers and Non-smokers: A Single-Center Retrospective Study in Jordan.

Introduction Despite the fact that smoking has been identified as a risk factor for respiratory diseases and lung infections, the relationship between smoking and coronavirus severity remains ambiguous. It is believed that smoking is a risk factor for pulmonary infections. However, the effect of smoking on COVID-19 patients is still controversial. Objective The aim of the study was to identify and analyze the distinct radiological features in COVID-19 patients with different smoking statuses. Additionally, the study sought to examine the association between smoking and the severity of pulmonary changes. Methods A retrospective cohort study of 111 patients who were referred to Al-Salt/Hussein Hospital, Al-Salt, Jordan, from January to June 2021, with a confirmed COVID-19 diagnosis and smoking status recorded. Patients' demographics, medical history, age, gender, comorbidity, and length of hospitalization were obtained from their medical records. Results Study groups were similar in median age, prevalence of chosen chronic diseases, and median length of hospital stay. Based on the median scores of the radiological findings in each lung lobe, no statistically significant differences were found between the scores and smoking status (p-values of >0.05; Mann-Whitney test). Conclusion Smoking is an independent risk factor for the severity of COVID-19. Smoking has no noticeable impact on interstitial manifestation in COVID-19 patients.

A radiomics-based model for the outcome prediction in COVID-19 positive patients through deep learning with both longitudinal chest x-ray and chest computed tomography images

The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.

Research on the classification of CT images of COVID-19 by pre-training model based on self-attention mechanism

Nowadays, with the outbreak of COVID-19, the prevention and treatment of COVID-19 has gradually become the focus of social disease prevention, and most patients are also more concerned about the symptoms. COVID-19 has symptoms similar to the common cold, and it cannot be diagnosed based on the symptoms shown by the patient, so it is necessary to observe medical images of the lungs to finally determine whether they are COVID-19 positive. As the number of patients with symptoms similar to pneumonia increases, more and more medical images of the lungs need to be generated. At the same time, the number of physicians at this stage is far from meeting the needs of patients, resulting in patients unable to detect and understand their own conditions in time. In this regard, we have performed image augmentation, data cleaning, and designed a deep learning classification network based on the data set of COVID-19 lung medical images. accurate classification judgment. The network can achieve 95.76% classification accuracy for this task through a new fine-tuning method and hyperparameter tuning we designed, which has higher accuracy and less training time than the classic convolutional neural network model. © 2023 SPIE.

Mixup-Inf-Net: A data augmentation algorithm for segmentation of new coronary pneumonia infections

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

COVID-19: comparison lung CT signs and biochemical parameters in the groups of patients with three-time positive RT-PCR and with triple negative RT-PCR test during the period of hospitalization.

Research goal. Comparative characteristics of the dynamics of CT semiotics and biochemical parameters of two groups of patients: with positive RT-PCR and with triple negative RT-PCR. Reflection of the results by comparing them with the data already available in the literature. The aim of the study is to compare the dynamics of CT semiotics and biochemical parameters of blood tests in two groups of patients: with positive RT-PCR and with triple negative RT-PCR. We also reflect the results by comparing them with the data already available in the literature. Materials and methods. We have performed a retrospective analysis of CT images of 66 patients: group I (n1 = 33) consists of patients who had three- time negative RT-PCR (nasopharyngeal swab for SARS-CoV-2 RNA) during hospitalization, and group II (n2 = 33) includes patients with triple positive RT-PCR. An important selection criterion is the presence of three CT examinations (primary, 1st CT and two dynamic examinations - 2nd CT and 3rd CT) and at least two results of biochemistry (C-reactive protein (CRP), fibrinogen, prothrombin time, procalcitonin) performed in a single time interval of +/- 5 days from 1st CT, upon admission, and +/- 5 days from 3st CT. A total of 198 CT examinations of the lungs were analyzed (3 examinations per patient). Results. The average age of patients in the first group was 58 +/- 14.4 years, in the second - 64.9 +/- 15.7 years. The number of days from the moment of illness to the primary CT scan 6.21 +/- 3.74 in group I, 7.0 (5.0-8.0) in group II, until the 2nd CT scan - 12.5 +/- 4, 87 and 12.0 (10.0-15.0), before the 3rd CT scan - 22.0 (19.0-26.0) and 22.0 (16.0-26.0), respectively. In both groups, all 66 patients (100%), the primary study identified the double-sided ground-glass opacity symptom and 36 of 66 (55%) patients showed consolidation of the lung tissue. Later on, a first follow-up CT defined GGO not in all the cases: it was presented in 22 of 33 (67%) patients with negative RT-PCR (group I) and in 28 of 33 (85%) patients with the positive one (group II). The percentage of studies showing consolidation increased significantly: up to 30 of 33 (91%) patients in group I, and up to 32 of 33 (97%) patients in group II. For the first time, radiological symptoms of "involutional changes" appeared: in 17 (52%) patients of the first group and in 5 (15%) patients of the second one. On second follow-up CT, GGO and consolidations were detected less often than on previous CT: in 1 and 27 patients of group I (3% and 82%, respectively) and in 6 and 30 patients of group II (18% and 91%, respectively), although the consolidation symptom still prevailed significantly . The peak of "involutional changes" occurred on last CT: 31 (94%) and 25 (76%) patients of groups I and II, respectively.So, in the groups studied, the dynamics of changes in lung CT were almost equal. After analyzing the biochemistry parameters, we found out that CRP significantly decreased in 93% of patients (p < 0.001) in group I;in group II, there was a statistically significant decrease in the values of C-reactive protein in 81% of patients (p = 0.005). With an increase in CT severity of coronavirus infection by one degree, an increase in CRP by 41.8 mg/ml should be expected. In group I, a statistically significant (p = 0.001) decrease in fibrinogen was recorded in 77% of patients;and a similar dynamic of this indicator was observed in group II: fibrinogen values decreased in 66% of patients (p = 0.002). Such parameters as procalcitonin and prothrombin time did not significantly change during inpatient treatment of the patients of the studied groups (p = 0.879 and p = 0.135), which may indicate that it is inappropriate to use these parameters in assessing dynamics of patients with a similar course of the disease. When comparing the outcomes of the studied groups, there was a statistically significant higher mortality in group II - 30.3%, in group I - 21.2% (p = 0.043). Conclusion. According to our data, a course of the disease does not significantly differ in the groups o patients with positive RT-PCR and three-time negative RT-PCR. A negative RT-PCR analysis may be associated with an individual peculiarity of a patient such as a low viral load of SARS-CoV-2 in the upper respiratory tract. Therefore, with repeated negative results on the RNA of the virus in the oro- and nasopharynx, one should take into account the clinic, the X-ray picture and biochemical indicators in dynamics and not be afraid to make a diagnosis of COVID-19.Copyright © 2021 ALIES. All rights reserved.