Normal Chest Computed Tomography Research Articles

DENG ENTROPY AND INFORMATION DIMENSION FOR COVID-19 AND COMMON PNEUMONIA CLASSIFICATION

Motivated by previous authors’ work, where Shannon entropy, box covering and information dimension were applied to quantify pulmonary lesions, this paper extends such a contribution in two fashions: (i) Following the approach to quantify pulmonary lesions with Deng entropy and Deng information dimension obtained through box covering method; (ii) exploiting the Shannon and Deng lesion quantification for pulmonary illnesses classification with a bidirectional Long Short Term Memory (bLSTM). The referred pulmonary illnesses are Common Pneumonia (CP) and COVID-19. Shannon entropy and information dimension are performed here and called the Shannon sequence. Then, Deng entropy and Deng information dimension are computed for chest Computed Tomography (CT) images to obtain and combine two data sequences to quantify the pulmonary lesions. The data sequence resulting from the data combination is called the Deng sequence. Both Shannon and Deng sequences are independently used as input for the bLSTM. CT lung scans of 531 healthy subjects, 497 confirmed COVID-19 diagnoses and 516 with CP were analyzed to obtain the Shannon and Deng sequences. The results demonstrate that Deng entropy and Deng information dimension of CT images can differentiate similar lung lesions between COVID-19 and CP. Besides, a statistical analysis shows that: (a) Classification by the bLSTM is better when using the Deng sequence than the Shannon sequence; (b) Deng sequences plus bLSTM significantly outperform DenseNet-201, GoogLeNet and MobileNet-v2 in classifying COVID-19, CP and Normal CT (healthy subjects) in time and accuracy. Hence, the Deng sequence and bLSTM are fast and accurate tools for helping in diagnosing CP and COVID-19.

Temporal Evolution of CT Findings in COVID-19 Patients: An Observational Study

Introduction: Coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), presents a broad spectrum of clinical manifestations, from asymptomatic cases to severe pneumonia and acute respiratory distress syndrome (ARDS). Chest computed tomography (CT) has become a critical diagnostic tool, especially in regions with high disease prevalence. This study aims to assess the common CT findings, patterns of lung involvement, and severity of disease in RT-PCR positive COVID-19 patients to better understand and manage this pervasive disease. Materials and Methods: This observational cross-sectional study was conducted at Dr. Kamakshi Memorial Hospital, Chennai, from 2020 to 2021. The study included RT-PCR positive COVID-19 patients aged 18 to 95 years who presented to the fever clinic or COVID casualty and were referred to the radiology department for chest CT evaluation. Exclusion criteria included pregnancy, age under 18 years, and refusal to consent. Non-contrast chest CT scans were performed using a TOSHIBA Aquilion Lightening 16-slice CT machine. Scans were acquired in a single inspiratory breath-hold from the lung apex to the costophrenic angle. CT findings were analyzed and reported by two experienced radiologists, with discrepancies resolved through consensus. Results: Out of 349 patients, 213 (61%) were male and 136 (39%) were female, with a mean age of 47.7 years. The distribution of CT findings showed significant variability among the four groups. Group A had the highest percentage of normal CT scans (22%) and ground-glass opacities (52%). Group B exhibited a reduction in normal CT scans (9%) and an increase in ground-glass opacities (57%). Group C showed further decrease in normal CT scans (10.6%) with increased crazy paving (17.3%) and reticulation (14.6%). Group D had similar normal CT scans (10.8%) but significantly higher incidences of reticulation (24.3%) and ground-glass opacities (64%). Conclusion: This study highlights the critical role of chest CT in monitoring the progression of COVID-19 pneumonia. The findings demonstrate a clear temporal evolution of lung involvement, from ground-glass opacities in the early stages to more complex patterns such as crazy paving and reticulation in later stages.

Clinical characteristics of juvenile systemic sclerosis in Korea: 31-year single-center study.

To evaluate the clinical and laboratory characteristics, therapeutic drugs, and prognosis of juvenile systemic sclerosis (JSSc) at a single center in Korea. This study was a retrospective analysis of patients with JSSc aged <16 years at disease onset and who were treated at our hospital between January 1992 and April 2023. All patients met the Pediatric Rheumatology European Society/American College of Rheumatology/European League against Rheumatism provisional classification criteria for JSSc, and those with localized scleroderma (morphea) were excluded. Among the 13 patients, proximal skin sclerosis (100%), Raynaud's phenomenon (RP) (84.6%), and sclerodactyly (69.2%) were present at the time of diagnosis. The most common symptom before diagnosis was RP, which was present in 10 patients (76.9%), whereas proximal skin sclerosis was observed in only five patients (38.5%). Thirteen patients had positive anti-nuclear antibody (ANA). At the time of diagnosis, five individuals had findings suggestive of interstitial lung disease (ILD) on a pulmonary function test (PFT) or chest computed tomography (CT), two of whom were asymptomatic. During follow-up, three patients developed ILD, one developed renal dysfunction, one developed heart disease, and none died. This study was the first descriptive analysis of clinical features of JSSc in South Korea. Clinical suspicion is essential for diagnosing JSSc in patients with RP, especially if ANA is positive; however, proximal skin sclerosis, which is crucial for diagnosing JSSc, was unrecognized in the early phase of the disease. PFT should be considered even if a patient is asymptomatic or has normal chest CT.

Full Body Screening Computed Tomography Prior to Allogeneic Hematopoietic Stem Cell Transplantation: A Single Institution Experience from an Academic Center

Background: The extent of pretransplant workup for allogeneic hematopoietic stem cell transplant (HSCT) differs considerably among transplant centers. Current practice at the University of Wisconsin is for all recipients to undergo screening CT (computed tomography) of the sinuses, chest, abdomen, and pelvis prior to HSCT which can reveal several incidental radiographic findings. Here, we examined the impact of this procedure on discovery of clinically meaningful incidental findings, on time to transplant, on detecting post-COVID-19 infection related complications and on overall clinical outcomes post-HSCT in the current era of novel treatments for malignant hematologic disorders. Methods: After IRB approval, all consecutive patients &amp;gt; age 18 years at the University of Wisconsin who underwent full body screening CT prior to HSCT, from January 2019 to August 2022 were studied. Imaging abnormalities were defined as any finding reported by the radiologist apart from isolated mucosal thickening on sinus CT scans. Post-transplant pulmonary complications were defined as abnormal chest CT scans within 6 months post-transplant. Patient and disease characteristics were tabulated, and descriptive statistics are reported. Progression free survival (PFS) is defined as the time from transplant to first identification of relapsed disease. Results: Table 1 shows clinical characteristics of the study cohort. Median follow up is 22.55 months (95% CI 12.04-34.78). A total of 205 patients underwent 577 screening CT scans prior to HSCT, of which 82% (n=169) had at least one abnormal finding and 52% (n=107) had an incidental finding. Of the patients with incidental findings, 53% (n=57) received no additional workup or intervention while 47% (n=50) underwent further workup, yet only 18% (n=19) had a change in management as depicted in figure 2. Therapeutic interventions included treatment with antifungals (n=11), antibiotics (n=5), thoracentesis (n=1), thoracotomy (n=1) and anticoagulation (n=1). Although 50% of all chest CT scans identified an abnormality, only 5% revealed an incidental finding that influenced management including pulmonary nodules (n=7), bronchiolitis (n=1) and pulmonary emboli (n=1), compared to just 3% for both sinus and abdominal CT scans including sinusitis (n=4), periapical abscesses (n=3) and abdominopelvic masses of the bladder (n=1), iliac fossa (n=1), pancreas (n=1) and ovary (n=1). Post-HSCT complications were identified in 23% (n=21) vs 16% (n=15) in those with abnormal and normal pre-HSCT chest CT, respectively. In the subset of patients who underwent therapeutic interventions resulting from abnormal screening chest CT, 28% (n=5) still experienced post-transplant complications. Finally, the incidence of post-transplant pulmonary complications was similar, 27% (n=4), in patients with and without documented COVID infection prior to transplant. Median time to HSCT after scan completion was similar in patients with normal vs abnormal imaging without additional workup at 23 days (range 11-47), compared to 24 days (range 8-62), respectively. In contrast, median time to HSCT was longer at 30 days (range 11-173) and 48 days (range 13-208) for those who received additional work up and a therapeutic intervention, respectively (p=0.0001). One year post HSCT non-relapse mortality was 9% and 12 % among patients with normal screening CT, and those with at least one abnormal finding, respectively. 2-year PFS was similar in patients with abnormal vs normal screening chest CT scans at 60% vs 58% respectively (p=0.98). Conclusions: We observed high rates of incidental findings leading to additional work up in over 40% of patients, though less than half of them led to changes in management. As expected, we noted a substantial risk of delay to HSCT in most recipients needing intervention. Chest CT scans had the highest prevalence of clinically significant incidental findings and meaningful impact on management, whereas routine sinus and abdomen-pelvic CT showed lower clinical benefit. No additional advantage of CT chest was found in asymptomatic patients who had a COVID-19 infection pre-HSCT. Our findings provide basis to re-evaluate current practice of pre HSCT screening, and identify at-risk patients who would benefit from screening. Additional analyses are needed to minimize risks of unnecessary interventions, delays and burden on patients and healthcare utilization.

CT quantitative analysis of pulmonary changes in rheumatoid arthritis.

To explore the application of quantitative computed tomography (CT) in analyses of lung changes in patients with rheumatoid arthritis (RA). A total of 150 clinically diagnosed RA patients underwent chest CT and 150 matched non-smokers subjects with normal chest CT are enrolled. A CT software is applied to analyze CT obtained from both groups. The quantitative indices of emphysema are expressed as the percentage of lung area with attenuation < -950HU to the total lung volume (LAA-950%), and pulmonary fibrosis was expressed as the percentage of lung area with a attenuation of -200 to -700HU to the total lung volume (LAA-200--700%), quantitative indicators of pulmonary vascular include aortic diameter (AD), pulmonary artery diameter (PAD), the ratio of PAD to AD (PAD/AD ratio), the number of blood vessels (TNV), and the cross area of blood vessels (TAV). The receiver operating characteristic (ROC) curve is used to evaluate the ability of these indexes in identifying the changes in the lung in RA patients. Compared to the control group, the RA group has significantly lower TLV, larger AD, and smaller TNV and TAV (3921±1101 vs. 4490±1046, 33.26±4.20 vs. 32.95±3.76, 13.14±4.93 vs. 17.53±3.34, and 96.89±40.62 vs. 163.32±34.97, respectively, with all p < 0.001). Peripheral vascular indicator TAV has the better ability to identify lung changes in RA patients (area under ROC curve AUC = 0.894) than TNV (AUC = 0.780) or LAA-200&sim-700% (AUC = 0.705). Quantitative CT can detect changes in lung density distribution and peripheral vascular injury in patients with RA and assess the severity.

Screening Chest CT Prior to Allogenic Hematopoietic Stem Cell Transplantation

Pulmonary complications constitute a major cause of morbidity and mortality in the post-allogenic hematopoietic stem cell transplant (alloHSCT) period. While Chest X-ray (CXR) is customarily used for screening, we have utilized chest computed tomography (CT). To characterize the prevalence of abnormalities and explore their impact on alloHSCT eligibility and outcomes post-transplant, we conducted a retrospective analysis utilizing real-world data collected at our center for adult patients who were evaluated for alloHSCT from January 2013 through December 2020 and identified 511 eligible patients. The most common primary disease was acute myeloid leukemia in 49% of patients, followed by myelodysplastic syndrome in 23%, lymphoma in 11%, and acute lymphocytic leukemia in 10%. Abnormal screening chest CT was found in 199 patients (39%). The most frequent detected abnormality was pulmonary nodule in 78 patients (35%), followed by consolidation in 42 (19%), ground-glass opacification in 33 (15%), bronchitis and bronchiolitis in 25 (11%), pleural effusions in 14 (6%), and new primary cancer in 7 (2%). CXR detected abnormalities in only about half of the patients (48%) with an abnormal chest CT. Among 199 patients with abnormal chest CT, 98 patients (49%) underwent further assessment and/or intervention before transplant. The most common work up was pulmonary consultation in 32%, infectious diseases consultation in 24%. Lung biopsy was obtained in 20% and antimicrobial therapy was initiated after confirming an infection diagnosis in 20% of patients. Patients with abnormal chest CT demonstrated worse overall survival (P= 0.032), non-relapse mortality (P=0.015), and pulmonary related death (P < 0.001) compared to those who had normal chest CT. Our study suggests that pre-transplant screening chest CT is beneficial in uncovering invasive infections and underlying malignancies and allows appropriate interventions before alloHSCT to prevent potentially serious post-transplant complications without causing a delay in alloHSCT. Nevertheless, abnormal CT findings prior to transplant may be associated with overall worse prognosis.

Twelve-month clinical, functional and radiological outcomes in patients hospitalized for SARS-CoV-2 pneumonia.

To assess long-term clinical, radiological and functional follow-up of patients hospitalized for SARS-CoV-2 pneumonia of different grade of severity. Two-hundred-thirty-three patients (Group 1, patients needed invasive mechanical ventilation -IMV-, n=69; Group 2, patients needed NIMV, n=78; Group 3, patients needed < 12 l/min of O2 supply, n=96) with a post-discharge follow-up>12 months were studied. Follow-up visits, chest CT scan and pulmonary function tests (DLCO, 6-minutes walking tests -6MWT-, spirometry) were done at 3, 6 and 12 months after discharge. Male sex was more frequent in Group 1 (n=50, 72.5%) compared to Group 2 (n=49, 62.5%) and Group 3 (n=44, 51.2%), p=0.024. Group 2 patients had more co-morbidities and higher BMI compared to others. At month 12, the main reported symptoms were fatigue (mainly in Group 3) and dyspnea; most symptoms resolved during follow-up, except brain fog, memory loss and anosmia/dysgeusia that, when present at month 3, usually persisted at month 12. DLCO and 6MWT normalized at month 12 in almost all patients. Only 9 patients (13%) in Group 1 had a normal chest CT at month 12, whilst 20 (29%) had >3 abnormalities, compared to 14 (17.9%) in Group 2 and 11 (11.4%) in Group 3, respectively (p=0.04). Different clinical symptoms persist up to 12 months in patients hospitalized for SARS-CoV-2 pneumonia. Despite the persistence of abnormalities at chest CT scan after 12 months, an impairment of pulmonary function persists only in a minority of subjects. A longer follow-up is needed to assess the evolution of radiological abnormalities in COVID-19 population. This article is protected by copyright. All rights reserved.

Asynchronous changes of normal lung lobes during respiration based on quantitative computed tomography (CT).

This study aimed to explore the coordinated and independent actions of lung lobes during respiration using quantitative computed tomography (CT) in order to increase our in vivo understanding of pulmonary anatomy. Cases for whom test results showed normal pulmonary function tests (PFTs) results, and normal paired inspiratory-expiratory chest CT findings, as assessed by 2 radiologists, were retrospectively included in this study. From the chest CT results, we measured quantitative indices of lung volume (LV) and mean lung density (MLD) for the total lung (TL), left lung (LL), right lung (RL), and 5 lobes in inspiratory and expiratory phases. The differences of these measures between bilateral lungs and among the lobes were evaluated to study whether they were consistent or different during respiration. A total of 70 cases were included {median age of 49.5 [interquartile range (IQR), 38.0 to 60.3] years; 32 males; 38 females}. Overall, the inspiratory and expiratory volumes of the LL were smaller than those of the RL (both P<0.001). For the ventilation workload (λ, which indicates the ratio of lobar volume to total LV), the end-expiratory volume ratio (λex ) of the LL was 0.44 (IQR, 0.43 to 0.46), while the end-inspiratory volume ratio (λin ) had risen to 0.46 (IQR, 0.45 to 0.47) (P<0.001). Comparing the 5 lobes, not all lobes shared the same LV. However, the left lower lobe (LLL) and right lower lobe (RLL) showed some similarities. The λin-LLL and λin-RLL was higher than λex-LLL and λex-RLL , respectively (both P<0.001), while the ratios of the other lobes reduced. The pairwise mean absolute difference (PMAD) on λin and λex of the bilateral lower lobes was low in inspiration (0.0288) and expiration (0.0346). The MLD of bilateral lower lobes showed consistency in inspiration or in expiration (inspiration: P>0.999; expiration: P=0.975). In addition, the PMADs between the right middle lobe (RML) and other lobes were significantly larger than the PMAD between other pairs of lobes in both inspiration and expiration. Beyond that, the expiratory MLD of RML [-789.6 (IQR, -814 to -762.05) HU] was the lowest among the 5 lobes. We found that the LL assumes a higher workload during ventilation than it does during respiration. The 5 normal lobes were non-synchronous during respiration and contributed differently to ventilation. The bilateral lower lobes showed similarities and had a high-ventilation function, while and the LV and MLD of the RML showed the least changes within a respiration cycle.

Chest computed tomography severity score and its correlation with age group, sex, and laboratory test results among coronavirus disease 2019 health-care workers

Background Detection of the viral nucleic acid is the cornerstone to diagnose the novel coronavirus disease 2019 (COVID-19). Due to the limited resources, the clinical and laboratory biomarkers will help in the early and differential diagnosis of severe acute respiratory syndrome coronavirus 2 infection and predict the prognosis of the disease. These findings in patients with pneumonia include fatigue, dry cough, low-grade fever, along with normal white blood cell count, decreased lymphocyte count, and high C-reactive protein (CRP) and D-dimer levels. Chest computed tomography (CT) severity score relies on the opacification of lungs as a proof for disease extension. Several studies have settled the importance of CT chest in the diagnosis and follow up of COVID-19 patients. Otherwise, many scientific societies have disclaimed the routine CT screening of these patients. Hence, it is important to correlate the CT severity score in positive PCR COVID-19 patients to their laboratory findings to minimize the need of frequent CT chest as a tool of follow-up.Patients and methods The study included 198 positive PCR for COVID-19 health-care workers including physicians, nurses, employees, and workers of Ain Shams University Hospitals, who sought medical advice at the Chest OPC or the ER triage or through teleconsultations. Patients underwent history taking, laboratory workup including complete blood count with differential, serum ferritin, CRP, D-dimer levels, and high-resolution CT chest.Results The study included 198 health-care workers including physicians, nurses, employees, and workers of Ain Shams University Hospitals with 106 of them being females and 92 males. The age range of the included patients is from 21 years up to 85 years. The cases were classified according to their CT severity score into normal CT chest with 47.5% of cases, mild CT findings representing 21.2%, 34 patients with moderate findings in CT, and those with severe score were 28 patients. A significant relation was found between the age and CT severity score with P value less than 0.001. The severity score was higher in cases with lower total leukocyte count and lymphocytes with significant relation and the P value was less than 0.001. The median CRP and ferritin level show a highly significant relation with the CT severity score. A highly significant relationship was found between severity score and D-dimer level of patients with a P value of less than 0.001.Conclusion This work sets a semiquantitative framework to assess and follow up the severity of COVID-19 disease. This score could be possibly used to facilitate the clinical triage of COVID-19 moderate to severe patients, requiring admission in hospitals in relation to laboratory findings. Also, it could be used to evaluate the severity of lung involvement in patients objectively and quickly. However, it was proposed that the use of laboratory results is of value in the follow up of the cases to limit the exposure to radiations.

HRCT Spectrum in Initially COVID-19 RT-PCR Negative Patients

Objective: To analyze radiological spectrum of HRCT in COVID-19 patients, clinically symptomatic but initially having negative RT-PCR.&#x0D; Study Design: Prospective cross sectional descriptive study.&#x0D; Place and Duration of Study: Radiology and Medicine Department, DHQ Hospital Rawalpindi, from June to November 2020&#x0D; Methodology: The study included 90 patients presenting with clinical symptoms of COVID-19 but with negative RT-PCR. All patients underwent chest computed tomography (CT). Patients with positive COVID-19 RT-PCR test or serology on subsequent repeat test were included in the study. Patients having non COVID-19 HRCT features with negative RT-PCR were excluded from the study.&#x0D; Results: Out of 90 symptomatic, RT-PCR negative patients, 7 had normal chest CT. According to BSTI classification, 50 patients showed classic, 11 had probable and 22 had indeterminate features. Despite supportive clinical and CT features, 17 (18.89%) patients had negative RT-PCR tests on subsequent testing. Unilateral changes were in 8 (8.9%) and bilateral in 75 (83.3%). Most common finding was mixed pattern of peripherally distributed GGN and bronchocentric nodules in 37 (41.1%) patients. Consolidations were in 19 (21.1%), pure ground glass haze in 13 (14.4%), crazy paving in 4 (4.4%), fuzzy bands and arcades in 7 (7.8%), and subtle gravitational GGH in 3 (3.3%) patients. CT-SS classified 69 (76.7%) patients as mild, 10 (11.1%) as moderate and 4 (4.4%) as severe disease.&#x0D; Conclusions: HRCT with CTSS is an important tool for diagnosing and prognosticating COVID-19 infection despite negative RT-PCR, timely identifying and isolating COVID-19 cohorts preventing cross infection and also aiding in prompt symptomatic management.

Critical analysis of spirometric patterns in correlation to chest computed tomography among adult Indigenous Australians with chronic airway diseases

ABSTRACT Background: There is sparse literature evidence in the spirometric patterns of adult Indigenous Australians with and without chest computed tomography (CT)-proven chronic airway diseases (CADs).Methods: Participants spirometry testing graded as acceptable for quality and had a chest CT scan showing radiographic evidence of CADs were included for analysis.Results: Of the 1350 spirometric tests performed between 2012 and 2020, a total of 212 patients with a mean age of 53 years and 54% females were eligible to be included. One-third (30%) had normal chest CT (without CADs), 35% had predominant COPD, 19% bronchiectasis and 16% combined COPD and bronchiectasis. Percentage predicted values for forced vital capacity (FVC) and forced expiratory volume in one second (FEV1) both pre- and post- bronchodilator were significantly reduced for all participants – FVC: CT-normal 64%, 65%; COPD 58%, 62%; bronchiectasis 54%, 54%; combined COPD and bronchiectasis 50%, 53%. FEV1: CT-normal 62%, 65%; COPD 46%, 49%; bronchiectasis 48%,51%; combined COPD and bronchiectasis 36%,40%. FEV1/FVC was only reduced for CT abnormality patients – CT-normal 96%,98%; COPD 77%,77%; bronchiectasis 87%,89%; combined COPD and bronchiectasis 71%,72%.Conclusions: Restrictive spirometric pattern is common and an obstructive pattern with COPD, in isolation or when COPD coexists with bronchiectasis.

Can laboratory findings predict pulmonary involvement in children with COVID-19 infection?

BackgroundStudies investigating clinical and imaging findings of coronavirus disease 2019 (COVID‐19) pneumonia and predictors for lung injury mostly focus on adults. In this study, we aimed to evaluate the role of laboratory findings in predicting lung involvement in children with COVID‐19.MethodsChildren with COVID‐19 confirmed by reverse‐transcription polymerase chain reaction or COVID‐19 IgM and who underwent chest computed tomography (CT) scans were reviewed retrospectively. Admission absolute neutrophil count (ANC), absolute lymphocyte count (ALC), ANC/ALC ratio, platelet count, d‐dimer, fibrinogen, ferritin, procalcitonin, C‐reactive protein (CRP), and lactate dehydrogenase levels were compared in patients with normal and abnormal CT scans.ResultsA total of 101 children were included. Among the patients, 68 (67.3%) had normal CT scans, and 33 (32.7%) had pulmonary involvement. The median CRP, ferritin, and fibrinogen levels were significantly higher in children with abnormal CT findings. The model of binary logistic regression based on the presence of cough, shortness of breath, fibrinogen, ferritin, and CRP levels showed that the possibility of having abnormal CT was 1.021 times more likely for every one unit increase in fibrinogen levels.ConclusionFibrinogen might be useful to predict pulmonary involvement of COVID‐19 in children. Restricting radiological imaging to patients with significant symptoms and high fibrinogen levels might be helpful in children with COVID‐19 infections.

Deep CNN models for predicting COVID-19 in CT and x-ray images.

.Purpose: Coronavirus disease 2019 (COVID-19) is a new infection that has spread worldwide and with no automatic model to reliably detect its presence from images. We aim to investigate the potential of deep transfer learning to predict COVID-19 infection using chest computed tomography (CT) and x-ray images.Approach: Regions of interest (ROI) corresponding to ground-glass opacities (GGO), consolidations, and pleural effusions were labeled in 100 axial lung CT images from 60 COVID-19-infected subjects. These segmented regions were then employed as an additional input to six deep convolutional neural network (CNN) architectures (AlexNet, DenseNet, GoogleNet, NASNet-Mobile, ResNet18, and DarkNet), pretrained on natural images, to differentiate between COVID-19 and normal CT images. We also explored the model’s ability to classify x-ray images as COVID-19, non-COVID-19 pneumonia, or normal. Performance on test images was measured with global accuracy and area under the receiver operating characteristic curve (AUC).Results: When using raw CT images as input to the tested models, the highest accuracy of 82% and AUC of 88.16% is achieved. Incorporating the three ROIs as an additional model inputs further boosts performance to an accuracy of 82.30% and an AUC of 90.10% (DarkNet). For x-ray images, we obtained an outstanding AUC of 97% for classifying COVID-19 versus normal versus other. Combing chest CT and x-ray images, DarkNet architecture achieves the highest accuracy of 99.09% and AUC of 99.89% in classifying COVID-19 from non-COVID-19. Our results confirm the ability of deep CNNs with transfer learning to predict COVID-19 in both chest CT and x-ray images.Conclusions: The proposed method could help radiologists increase the accuracy of their diagnosis and increase efficiency in COVID-19 management.

Post-discharge chest CT findings and pulmonary function tests in severe COVID-19 patients

PurposeTo evaluate chest computed tomography (CT) and pulmonary function test (PFT) findings in severe COVID-19 patients after discharge and correlate CT pulmonary involvement with PFT results. MethodsCOVID-19 patients admitted to our hospital between February 25 and May 2, 2020, were retrospectively included according to the following criteria: (a) COVID-19 defined as severe based on the WHO interim guidance (i.e., clinical signs of pneumonia plus respiratory rate > 30 breaths/min, severe respiratory distress, and/or SpO2 < 90 % on room air); (b) chest radiograph in the acute setting; (c) post-discharge unenhanced chest CT; and (d) post-discharge comprehensive PFT. Imaging findings were retrospectively evaluated in consensus by two readers, and volume of abnormal lung was measured on CT using 3D Slicer software. Differences between demographics, comorbidities, acute radiographic findings, PFT, and post-discharge clinical and laboratory data of patients with normal and abnormal CT findings were assessed by Mann-Whitney or Fisher tests, and the compromised lung volume-PFT association by Pearson correlation after removing possible outliers. ResultsAt a median of 105 days from symptom onset, 74/91 (81 %) patients had CT abnormalities. The most common CT pattern was combined ground-glass opacity and reticular pattern (46/74, 62 %) along with architectural distortion (68/74, 92 %) and bronchial dilatation (66/74, 89 %). Compromised lung volume had a median value of 15 % [11–23], was higher in dyspneic patients, and negatively correlated with the percentage of predicted DLCO, VA, and FVC values (r = -0.39, -0.5, and -0.42, respectively). These PFT parameters were significantly lower in patients with CT abnormalities. Impairment of DLCO and KCO was found in 12 (13 %) cases, possibly implying an underlying pulmonary vasculopathy in this subgroup of patients. ConclusionsMost severe COVID-19 survivors still had physiologically relevant CT abnormalities about three months after the disease onset, with an impairment of diffusion capacity on PFT. A pulmonary vasculopathy was suggested in a minor proportion of patients.

Clinical Application of Chest Computed Tomography (CT) in Detection and Characterization of Coronavirus (Covid-19) Pneumonia in Adults.

To analyze diagnostic accuracy of chest computed tomography (CT) and RT-PCR (real-time polymerase chain reaction) for COVID-19 (coronavirus disease 19) pneumonia in early and progressive stages. To evaluate if combination of chest CT with RT-PCR can supplement the shortage of RT-PCR in diagnosis of COVID-19 pneumonia. We conducted a prospective study on 103 male patients. The study population were divided into two groups; early COVID-19 stage (number = 50 patients, with positive RT-PCR but mild symptoms) and progressive COVID-19 stage (number = 53, positive RT-PCR and sever symptoms including fever > 37.5 °C, cough, and shortness of breath). All patients underwent CT imaging. The early stage included typical category; 34% (17 out of 50 cases), 6% indeterminate category (3 cases), 10% atypical category (5 cases) and 50% (25 cases) were normal CT imaging. The progressive stage included typical category that was further divided to five subgroups; (i) peripheral bilateral lower lobe ground-glass opacity (GGO) in (37.7%), (ii) peripheral bilateral lower lobes GGO with peribronchovascular consolidation and bronchiolar dilatation in (18.8%), (iii) peripheral bilateral lower lobes GGO with crazy paving appearance in (15%), (iv) bilateral diffuse GGO in (18.8%), and (v) peripheral bilateral GGO with mediastinal lymph node enlargement (9.4%). Chest CT imaging could aid to supplement the shortages of PCR for clinically suspected patients of COVID-19 in the epidemic area as CT was positive in 50% of patients. Chest CT is very effective in detecting pulmonary parenchymal abnormalities in the progressive stage of COVID-19 patients in 100%.

Diagnostic accuracy and false-positive rate of chest CT as compared to RT-PCR in coronavirus disease 2019 (COVID-19) pneumonia: A prospective cohort of 612 cases from India and review of literature.

Background:At present, the diagnosis of COVID-19 depends on real-time reverse transcriptase polymerase chain reaction (RT-PCT). On imaging, computed tomography (CT) manifestations resemble those seen in viral pneumonias, with multifocal ground-glass opacities and consolidation in a peripheral distribution being the most common findings. Although these findings lack specificity for COVID-19 diagnosis on imaging grounds, CT could be used to provide objective assessment about the extension of the lung opacities, which could be used as an imaging surrogate for disease burden. Chest CT scan may be helpful in early diagnosing of COVID-19.Objective:The current study investigated the diagnostic accuracy and false-positive rate of chest CT in detecting COVID-19 pneumoniain a population with clinical suspicion using RT-PCR testing as reference standard.Materials and Methods:In this prospective single centerstudy performed on 612 cases with clinical suspicion of COVID-19, all adult symptomatic ED patients had both a CT scan and a PCR upon arrival at the hospital. CT results were compared with PCR test (s) and diagnostic accuracy was calculated.Results:Between February 15, 2020 to July 15, 2020, 612 symptomatic ED patients were included. In total, 78.5% of patients had a positive PCR and 82.8% a positive CT, resulting in a sensitivity of 94.2%, specificity 76.4%, likelihood ratio (LR) + 2.94 and (LR) - 0.18. The PPV was 76.7% and NPV 94.1%. The sensitivity of the CT tended to be higher (100.0%) in those with severe risk pneumonia than in patients with low/medium risk pneumonia (90.3%, P = 0.42). In patients with sepsis, sensitivity was significantly higher than in those without sepsis (99.5 vs. 63.5%, P < 0.001). The diagnostic ability of chest CT was found to be rather high with 92.1%, concordance rate between findings of CT and PCR. In 48 (7.8%) patients discordant findings between CT and PCR were observed. The positive predictive values (PPV) and accuracy of chest CT in diagnosing COVID-19 were higher in patients ≥60 years than that in patients <60 years (P = 0.001 and 0.004, respectively). The specificity and NPV of chest CT in diagnosing COVID-19 were greater for women than that for men (P = 0.007 and 0.03, respectively); and no difference existed for sensitivity, PPV and accuracy (P = 0.43, 0.69 and 0.31, respectively). In most cases, the CT scan was considered suspicious for COVID-19, while the PCR was negative (37/48, 70.8%). In the majority of these, the diagnosis at discharge was pulmonary infection (n = 26; 74.3%). The current study included repeated PCRs and explored discordant test results, which showed that in about 45.9% of patients with false-positive CT scans, other viral pathogens were detected. The false-positive rate of CT findings in the diagnosis of COVID-19 pneumonia was 7.2%.Conclusion:High diagnostic accuracy of chest CT findings with typical and relatively atypical CT manifestations of COVID-19 leads to a low rate of missed diagnosis. Normal chest CT can be found in RT-PCR positive COVID-19 cases, and typical CT manifestations can be found in RT-PCR negative cases. Therefore, a combination of both CT and RT-PCR for future follow-up, management and medical surveillance is recommended considering the false-positive results of chest CT in the diagnosis of COVID-19 pneumonia.

Relationship between acute phase reactants and prognosis in patients with or without COVID-19 pneumonia.

ABSTRACTIn December 2019, several cases of pneumonia of unknown origin were reported in the city of Wuhan, province of Hubei, China. The pathogen was named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the disease was named coronavirus disease 2019 (COVID-19). Acute phase reactans (APRs) are critical in the early diagnosis, treatment, and for monitoring the progression of COVID-19. Seventy two patients were included in the study and infections confirmed by real-time reverse transcription polymerase chain reaction. Clinical parameters, the level of APFs and D-dimer were assessed and results were retrived from the patients’ medical records. Chest computed tomography (CT) findings were described for each patient and they were divided into two groups, with or without COVID-19 pneumonia. The correlation between APRs and CT findings and the patients’ prognosis were evaluated. Twenty eight (38.8%) of the 72 patients were female and 44 (61.2%) were male. The most common symptom was cough (43%) and the most common associated chronic disease was hypertension (12.5%). Thirty (41.6%) patients had completely normal chest CT, while 42 (58.4%) patients had typical findings in terms of COVID-19 pneumonia. C reactive protein (CRP), lactate dehydrogenase (LDH), erythrocyte sedimentation rate (ESR), ferritin, procalcitonin and D-Dimer levels were statistically significantly higher in patients with pneumonia than in those without pneumonia and these parameters were also statistically significantly higher in patients with severe illness. In conclusion, CRP, LDH, ESR, ferritin, and D-Dimer were associated with severe COVID-19 pneumonia. These biomarkers can be used to evaluate the prognosis to predict the clinical course of disease, allowing a proper management and treatment of the patients.

Prognostic Implications of CT Feature Analysis in Patients with COVID-19: a Nationwide Cohort Study.

BackgroundFew studies have classified chest computed tomography (CT) findings of coronavirus disease 2019 (COVID-19) and analyzed their correlations with prognosis. The present study aimed to evaluate retrospectively the clinical and chest CT findings of COVID-19 and to analyze CT findings and determine their relationships with clinical severity.MethodsChest CT and clinical features of 271 COVID-19 patients were assessed. The presence of CT findings and distribution of parenchymal abnormalities were evaluated, and CT patterns were classified as bronchopneumonia, organizing pneumonia (OP), or diffuse alveolar damage (DAD). Total extents were assessed using a visual scoring system and artificial intelligence software. Patients were allocated to two groups based on clinical outcomes, that is, to a severe group (requiring O2 therapy or mechanical ventilation, n = 55) or a mild group (not requiring O2 therapy or mechanical ventilation, n = 216). Clinical and CT features of these two groups were compared and univariate and multivariate logistic regression analyses were performed to identify independent prognostic factors.ResultsAge, lymphocyte count, levels of C-reactive protein, and procalcitonin were significantly different in the two groups. Forty-five of the 271 patients had normal chest CT findings. The most common CT findings among the remaining 226 patients were ground-glass opacity (98%), followed by consolidation (53%). CT findings were classified as OP (93%), DAD (4%), or bronchopneumonia (3%) and all nine patients with DAD pattern were included in the severe group. Uivariate and multivariate analyses showed an elevated procalcitonin (odds ratio [OR], 2.521; 95% confidence interval [CI], 1.001–6.303, P = 0.048), and higher visual CT scores (OR, 1.137; 95% CI, 1.042–1.236; P = 0.003) or higher total extent by AI measurement (OR, 1.048; 95% CI, 1.020–1.076; P < 0.001) were significantly associated with a severe clinical course.ConclusionCT findings of COVID-19 pneumonia can be classified into OP, DAD, or bronchopneumonia patterns and all patients with DAD pattern were included in severe group. Elevated inflammatory markers and higher CT scores were found to be significant predictors of poor prognosis in patients with COVID-19 pneumonia.

Classification of COVID-19 CT Scans via Extreme Learning Machine

Here, we use multi-type feature fusion and selection to predict COVID-19 infections on chest computed tomography (CT) scans. The scheme operates in four steps. Initially, we prepared a database containing COVID-19 pneumonia and normal CT scans. These images were retrieved from the Radiopaedia COVID-19 website. The images were divided into training and test sets in a ratio of 70:30. Then, multiple features were extracted from the training data. We used canonical correlation analysis to fuse the features into single vectors; this enhanced the predictive capacity. We next implemented a genetic algorithm (GA) in which an Extreme Learning Machine (ELM) served to assess GA fitness. Based on the ELM losses, the most discriminatory features were selected and saved as an ELM Model. Test images were sent to the model, and the best-selected features compared to those of the trained model to allow final predictions. Validation employed the collected chest CT scans. The best predictive accuracy of the ELM classifier was 93.9%; the scheme was effective.

The Efficacy of Chest Computed Tomography in Pediatric Patients With Suspected COVID-19.

The aim of the study was to investigate chest computed tomography (CT) findings and the value of CT in the diagnosis in children with suspected coronavirus disease 2019 (COVID-19). Chest CT images of pediatric patients with suspected COVID-19 were retrospectively evaluated. Computed tomography findings were divided into 3 groups: normal, consistent, and inconsistent with COVID-19. The sensitivity and specificity of CT were calculated by reference to reverse transcriptase polymerase chain reaction. The study included patients with a mean age of 11.1 years (1 month-17 years). Of the patients, 43 (40.19%) had normal CT, 34 (31.77%) had CT findings consistent with COVID-19, and 30 (28.04%) had CT findings inconsistent with COVID-19. The sensitivity, specificity, positive predictive value, and negative predictive value of CT were 47.92%, 81.36%, 67.65%, and 65.75%, respectively. Because the sensitivity of CT in the pediatric age group is low, it should be used cautiously for the evaluation of COVID-19 in the pediatric age group.