Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 1.192
Filter
Add filters

Document Type
Year range
1.
BMC Pulm Med ; 22(1): 1, 2022 Jan 03.
Article in English | MEDLINE | ID: covidwho-1608729

ABSTRACT

BACKGROUND: Quantitative evaluation of radiographic images has been developed and suggested for the diagnosis of coronavirus disease 2019 (COVID-19). However, there are limited opportunities to use these image-based diagnostic indices in clinical practice. Our aim in this study was to evaluate the utility of a novel visually-based classification of pulmonary findings from computed tomography (CT) images of COVID-19 patients with the following three patterns defined: peripheral, multifocal, and diffuse findings of pneumonia. We also evaluated the prognostic value of this classification to predict the severity of COVID-19. METHODS: This was a single-center retrospective cohort study of patients hospitalized with COVID-19 between January 1st and September 30th, 2020, who presented with suspicious findings on CT lung images at admission (n = 69). We compared the association between the three predefined patterns (peripheral, multifocal, and diffuse), admission to the intensive care unit, tracheal intubation, and death. We tested quantitative CT analysis as an outcome predictor for COVID-19. Quantitative CT analysis was performed using a semi-automated method (Thoracic Volume Computer-Assisted Reading software, GE Health care, United States). Lungs were divided by Hounsfield unit intervals. Compromised lung (%CL) volume was the sum of poorly and non-aerated volumes (- 500, 100 HU). We collected patient clinical data, including demographic and clinical variables at the time of admission. RESULTS: Patients with a diffuse pattern were intubated more frequently and for a longer duration than patients with a peripheral or multifocal pattern. The following clinical variables were significantly different between the diffuse pattern and peripheral and multifocal groups: body temperature (p = 0.04), lymphocyte count (p = 0.01), neutrophil count (p = 0.02), c-reactive protein (p < 0.01), lactate dehydrogenase (p < 0.01), Krebs von den Lungen-6 antigen (p < 0.01), D-dimer (p < 0.01), and steroid (p = 0.01) and favipiravir (p = 0.03) administration. CONCLUSIONS: Our simple visual assessment of CT images can predict the severity of illness, a resulting decrease in respiratory function, and the need for supplemental respiratory ventilation among patients with COVID-19.


Subject(s)
COVID-19/classification , COVID-19/diagnostic imaging , Tomography, X-Ray Computed , Adult , Aged , Amides/therapeutic use , Antiviral Agents/therapeutic use , Body Temperature , C-Reactive Protein/metabolism , COVID-19/drug therapy , COVID-19/physiopathology , Female , Fibrin Fibrinogen Degradation Products/metabolism , Humans , L-Lactate Dehydrogenase/blood , Lung/diagnostic imaging , Lymphocyte Count , Male , Middle Aged , Mucin-1/blood , Neutrophils , Predictive Value of Tests , Prognosis , Pyrazines/therapeutic use , Radiographic Image Interpretation, Computer-Assisted , Retrospective Studies , SARS-CoV-2 , Steroids/therapeutic use
2.
Lancet Neurol ; 20(9): 753-761, 2021 09.
Article in English | MEDLINE | ID: covidwho-1599333

ABSTRACT

BACKGROUND: The mechanisms by which any upper respiratory virus, including SARS-CoV-2, impairs chemosensory function are not known. COVID-19 is frequently associated with olfactory dysfunction after viral infection, which provides a research opportunity to evaluate the natural course of this neurological finding. Clinical trials and prospective and histological studies of new-onset post-viral olfactory dysfunction have been limited by small sample sizes and a paucity of advanced neuroimaging data and neuropathological samples. Although data from neuropathological specimens are now available, neuroimaging of the olfactory system during the acute phase of infection is still rare due to infection control concerns and critical illness and represents a substantial gap in knowledge. RECENT DEVELOPMENTS: The active replication of SARS-CoV-2 within the brain parenchyma (ie, in neurons and glia) has not been proven. Nevertheless, post-viral olfactory dysfunction can be viewed as a focal neurological deficit in patients with COVID-19. Evidence is also sparse for a direct causal relation between SARS-CoV-2 infection and abnormal brain findings at autopsy, and for trans-synaptic spread of the virus from the olfactory epithelium to the olfactory bulb. Taken together, clinical, radiological, histological, ultrastructural, and molecular data implicate inflammation, with or without infection, in either the olfactory epithelium, the olfactory bulb, or both. This inflammation leads to persistent olfactory deficits in a subset of people who have recovered from COVID-19. Neuroimaging has revealed localised inflammation in intracranial olfactory structures. To date, histopathological, ultrastructural, and molecular evidence does not suggest that SARS-CoV-2 is an obligate neuropathogen. WHERE NEXT?: The prevalence of CNS and olfactory bulb pathosis in patients with COVID-19 is not known. We postulate that, in people who have recovered from COVID-19, a chronic, recrudescent, or permanent olfactory deficit could be prognostic for an increased likelihood of neurological sequelae or neurodegenerative disorders in the long term. An inflammatory stimulus from the nasal olfactory epithelium to the olfactory bulbs and connected brain regions might accelerate pathological processes and symptomatic progression of neurodegenerative disease. Persistent olfactory impairment with or without perceptual distortions (ie, parosmias or phantosmias) after SARS-CoV-2 infection could, therefore, serve as a marker to identify people with an increased long-term risk of neurological disease.


Subject(s)
COVID-19/complications , COVID-19/diagnostic imaging , Olfaction Disorders/diagnostic imaging , Olfaction Disorders/etiology , Olfactory Mucosa/diagnostic imaging , Brain/diagnostic imaging , Brain/physiopathology , Brain/virology , COVID-19/physiopathology , Humans , Neurodegenerative Diseases/diagnostic imaging , Neurodegenerative Diseases/etiology , Neurodegenerative Diseases/physiopathology , Olfaction Disorders/physiopathology , Olfaction Disorders/virology , Olfactory Mucosa/physiopathology , Olfactory Mucosa/virology , Prospective Studies , Smell/physiology
3.
J Korean Med Sci ; 36(44): e309, 2021 Nov 15.
Article in English | MEDLINE | ID: covidwho-1593105

ABSTRACT

BACKGROUND: We assessed maternal and neonatal outcomes of critically ill pregnant and puerperal patients in the clinical course of coronavirus disease 2019 (COVID-19). METHODS: Records of pregnant and puerperal women with polymerase chain reaction positive COVID-19 virus who were admitted to our intensive care unit (ICU) from March 2020 to August 2021 were investigated. Demographic, clinical and laboratory data, pharmacotherapy, and neonatal outcomes were analyzed. These outcomes were compared between patients that were discharged from ICU and patients who died in ICU. RESULTS: Nineteen women were included in this study. Additional oxygen was required in all cases (100%). Eight patients (42%) were intubated and mechanically ventilated. All patients that were mechanically ventilated have died. Increased levels of C-reactive protein (CRP) was seen in all patients (100%). D-dimer values increased in 15 patients (78.9%); interleukin-6 (IL-6) increased in 16 cases (84.2%). Sixteen patients used antiviral drugs. Eleven patients were discharged from the ICU and eight patients have died due to complications of COVID-19 showing an ICU mortality rate of 42.1%. Mean number of hospitalized days in ICU was significantly lower in patients that were discharged (P = 0.037). Seventeen patients underwent cesarean-section (C/S) (89.4%). Mean birth week was significantly lower in patients who died in ICU (P = 0.024). Eleven preterm (57.8%) and eight term deliveries (42.1%) occurred. CONCLUSION: High mortality rate was detected among critically ill pregnant/parturient patients followed in the ICU. Main predictors of mortality were the need of invasive mechanical ventilation and higher number of days hospitalized in ICU. Rate of C/S operations and preterm delivery were high. Pleasingly, the rate of neonatal death was low and no neonatal COVID-19 occurred.


Subject(s)
COVID-19/mortality , Pregnancy Complications, Infectious/mortality , Puerperal Disorders/mortality , SARS-CoV-2 , Adult , Antiviral Agents/therapeutic use , COVID-19/blood , COVID-19/diagnostic imaging , COVID-19/therapy , Cesarean Section , Combined Modality Therapy , Critical Illness/mortality , Delivery, Obstetric/statistics & numerical data , Female , Hospital Mortality , Humans , Infant, Newborn , Intensive Care Units/statistics & numerical data , Length of Stay/statistics & numerical data , Lung/diagnostic imaging , Oxygen Inhalation Therapy , Pregnancy , Pregnancy Outcome , Respiration, Artificial , Retrospective Studies , Treatment Outcome , Young Adult
4.
Curr Med Imaging ; 17(12): 1487-1495, 2021.
Article in English | MEDLINE | ID: covidwho-1595319

ABSTRACT

PURPOSE: The purpose of this study was to investigate the influencing factors for chest CT hysteresis and severity of coronavirus disease 2019 (COVID-19). METHODS: The chest CT data of patients with confirmed COVID-19 in 4 hospitals were retrospectively analyzed. An independent assessment was performed by one clinician using the DEXIN FACT Workstation Analysis System, and the assessment results were reviewed by another clinician. Furthermore, the mean hysteresis time was calculated according to the median time from progression to the most serious situation to improve chest CT in patients after fever relief. The optimal scaling regression analysis was performed by including variables with statistical significance in univariate analysis. In addition, a multivariate regression model was established to investigate the relationship of the percentage of lesion/total lung volume with lymphocyte and other variables. RESULTS: In the included 166 patients with COVID-19, the average value of the most serious percentage of lesion/total lung volume was 6.62, of which 90 patients with fever had an average hysteresis time of 4.5 days after symptom relief, with a similar trend observed in those without fever. Multivariate analysis revealed that lymphocyte count in peripheral blood and transcutaneous oxygen saturation decreased with the increase of the percentage of lesion/total lung volume. CONCLUSION: There is a hysteresis effect in the improvement of chest CT image relative to fever relief in patients with COVID-19. The pulmonary lesions may be related to the severity as well as decreased lymphocyte count or percutaneous oxygen saturation.


Subject(s)
COVID-19 , Tomography, X-Ray Computed , COVID-19/diagnostic imaging , Humans , Lung/diagnostic imaging , Lung/physiopathology , Retrospective Studies , SARS-CoV-2
5.
Sci Rep ; 11(1): 24065, 2021 12 15.
Article in English | MEDLINE | ID: covidwho-1585806

ABSTRACT

COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images.


Subject(s)
COVID-19/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Algorithms , COVID-19 Testing/methods , Deep Learning , Heuristics , Humans , Neural Networks, Computer , Tomography, X-Ray Computed
6.
Semin Respir Crit Care Med ; 42(6): 737-746, 2021 12.
Article in English | MEDLINE | ID: covidwho-1585676

ABSTRACT

In December 2019, a new infectious disease called coronavirus disease 2019 (COVID-19) attributed to the new virus named severe scute respiratory syndrome coronavirus 2 (SARS-CoV-2) was detected. The gold standard for the diagnosis of SARS-CoV-2 infection is the viral identification in nasopharyngeal swab by real-time polymerase chain reaction. Few data on the role of imaging are available in the pediatric population. Similarly, considering that symptomatic therapy is adequate in most of the pediatric patients with COVID-19, few pediatric pharmacological studies are available. The main aim of this review is to describe and discuss the scientific literature on various imaging approaches and therapeutic management in children and adolescents affected by COVID-19. Clinical manifestations of COVID-19 are less severe in children than in adults and as a consequence the radiologic findings are less marked. If imaging is needed, chest radiography is the first imaging modality of choice in the presence of moderate-to-severe symptoms. Regarding therapy, acetaminophen or ibuprofen are appropriate for the vast majority of pediatric patients. Other drugs should be prescribed following an appropriate individualized approach. Due to the characteristics of COVID-19 in pediatric age, the importance of strengthening the network between hospital and territorial pediatrics for an appropriate diagnosis and therapeutic management represents a priority.


Subject(s)
COVID-19/diagnosis , COVID-19/therapy , Adolescent , COVID-19/diagnostic imaging , Child , Humans , SARS-CoV-2/drug effects
7.
IEEE J Transl Eng Health Med ; 10: 1100110, 2022.
Article in English | MEDLINE | ID: covidwho-1583803

ABSTRACT

Objective: Since its outbreak, the rapid spread of COrona VIrus Disease 2019 (COVID-19) across the globe has pushed the health care system in many countries to the verge of collapse. Therefore, it is imperative to correctly identify COVID-19 positive patients and isolate them as soon as possible to contain the spread of the disease and reduce the ongoing burden on the healthcare system. The primary COVID-19 screening test, RT-PCR although accurate and reliable, has a long turn-around time. In the recent past, several researchers have demonstrated the use of Deep Learning (DL) methods on chest radiography (such as X-ray and CT) for COVID-19 detection. However, existing CNN based DL methods fail to capture the global context due to their inherent image-specific inductive bias. Methods: Motivated by this, in this work, we propose the use of vision transformers (instead of convolutional networks) for COVID-19 screening using the X-ray and CT images. We employ a multi-stage transfer learning technique to address the issue of data scarcity. Furthermore, we show that the features learned by our transformer networks are explainable. Results: We demonstrate that our method not only quantitatively outperforms the recent benchmarks but also focuses on meaningful regions in the images for detection (as confirmed by Radiologists), aiding not only in accurate diagnosis of COVID-19 but also in localization of the infected area. The code for our implementation can be found here - https://github.com/arnabkmondal/xViTCOS. Conclusion: The proposed method will help in timely identification of COVID-19 and efficient utilization of limited resources.


Subject(s)
COVID-19 , Deep Learning , COVID-19/diagnostic imaging , Humans , Radiography, Thoracic , SARS-CoV-2 , X-Rays
9.
J Med Internet Res ; 23(2): e23693, 2021 02 10.
Article in English | MEDLINE | ID: covidwho-1575481

ABSTRACT

BACKGROUND: COVID-19 has spread very rapidly, and it is important to build a system that can detect it in order to help an overwhelmed health care system. Many research studies on chest diseases rely on the strengths of deep learning techniques. Although some of these studies used state-of-the-art techniques and were able to deliver promising results, these techniques are not very useful if they can detect only one type of disease without detecting the others. OBJECTIVE: The main objective of this study was to achieve a fast and more accurate diagnosis of COVID-19. This study proposes a diagnostic technique that classifies COVID-19 x-ray images from normal x-ray images and those specific to 14 other chest diseases. METHODS: In this paper, we propose a novel, multilevel pipeline, based on deep learning models, to detect COVID-19 along with other chest diseases based on x-ray images. This pipeline reduces the burden of a single network to classify a large number of classes. The deep learning models used in this study were pretrained on the ImageNet dataset, and transfer learning was used for fast training. The lungs and heart were segmented from the whole x-ray images and passed onto the first classifier that checks whether the x-ray is normal, COVID-19 affected, or characteristic of another chest disease. If it is neither a COVID-19 x-ray image nor a normal one, then the second classifier comes into action and classifies the image as one of the other 14 diseases. RESULTS: We show how our model uses state-of-the-art deep neural networks to achieve classification accuracy for COVID-19 along with 14 other chest diseases and normal cases based on x-ray images, which is competitive with currently used state-of-the-art models. Due to the lack of data in some classes such as COVID-19, we applied 10-fold cross-validation through the ResNet50 model. Our classification technique thus achieved an average training accuracy of 96.04% and test accuracy of 92.52% for the first level of classification (ie, 3 classes). For the second level of classification (ie, 14 classes), our technique achieved a maximum training accuracy of 88.52% and test accuracy of 66.634% by using ResNet50. We also found that when all the 16 classes were classified at once, the overall accuracy for COVID-19 detection decreased, which in the case of ResNet50 was 88.92% for training data and 71.905% for test data. CONCLUSIONS: Our proposed pipeline can detect COVID-19 with a higher accuracy along with detecting 14 other chest diseases based on x-ray images. This is achieved by dividing the classification task into multiple steps rather than classifying them collectively.


Subject(s)
Algorithms , COVID-19/diagnostic imaging , Deep Learning , Thoracic Diseases/diagnostic imaging , Humans , Neural Networks, Computer , Radiography, Thoracic , SARS-CoV-2 , Thorax
10.
PLoS One ; 16(3): e0247839, 2021.
Article in English | MEDLINE | ID: covidwho-1574949

ABSTRACT

As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based method to support COVID-19 diagnosis using convolutional neural networks (CNN). Because the availability of radiological data is rather limited due to the novelty of COVID-19, several methodologies consider reduced datasets, which may be inadequate, biasing the model. Here, we performed an analysis combining six different databases using chest X-ray images from open datasets to distinguish images of infected patients while differentiating COVID-19 and pneumonia from 'no-findings' images. In addition, the performance of models created from fewer databases, which may imperceptibly overestimate their results, is discussed. Two CNN-based architectures were created to process images of different sizes (512 × 512, 768 × 768, 1024 × 1024, and 1536 × 1536). Our best model achieved a balanced accuracy (BA) of 87.7% in predicting one of the three classes ('no-findings', 'COVID-19', and 'pneumonia') and a specific balanced precision of 97.0% for 'COVID-19' class. We also provided binary classification with a precision of 91.0% for detection of sick patients (i.e., with COVID-19 or pneumonia) and 98.4% for COVID-19 detection (i.e., differentiating from 'no-findings' or 'pneumonia'). Indeed, despite we achieved an unrealistic 97.2% BA performance for one specific case, the proposed methodology of using multiple databases achieved better and less inflated results than from models with specific image datasets for training. Thus, this framework is promising for a low-cost, fast, and noninvasive means to support the diagnosis of COVID-19.


Subject(s)
COVID-19/diagnostic imaging , Databases, Factual , Neural Networks, Computer , Pneumonia/diagnostic imaging , Algorithms , Bias , Deep Learning , Humans , Image Interpretation, Computer-Assisted , Radiography, Thoracic
11.
PLoS One ; 16(3): e0247686, 2021.
Article in English | MEDLINE | ID: covidwho-1574773

ABSTRACT

OBJECTIVES: The aim of this study was to investigate possible patterns of demand for chest imaging during the first wave of the SARS-CoV-2 pandemic and derive a decision aid for the allocation of resources in future pandemic challenges. MATERIALS AND METHODS: Time data of requests for patients with suspected or confirmed coronavirus disease 2019 (COVID-19) lung disease were analyzed between February 27th and May 27th 2020. A multinomial logistic regression model was used to evaluate differences in the number of requests between 3 time intervals (I1: 6am - 2pm, I2: 2pm - 10pm, I3: 10pm - 6am). A cosinor model was applied to investigate the demand per hour. Requests per day were compared to the number of regional COVID-19 cases. RESULTS: 551 COVID-19 related chest imagings (32.8% outpatients, 67.2% in-patients) of 243 patients were conducted (33.3% female, 66.7% male, mean age 60 ± 17 years). Most exams for outpatients were required during I2 (I1 vs. I2: odds ratio (OR) = 0.73, 95% confidence interval (CI) 0.62-0.86, p = 0.01; I2 vs. I3: OR = 1.24, 95% CI 1.04-1.48, p = 0.03) with an acrophase at 7:29 pm. Requests for in-patients decreased from I1 to I3 (I1 vs. I2: OR = 1.24, 95% CI 1.09-1.41, p = 0.01; I2 vs. I3: OR = 1.16, 95% CI 1.05-1.28, p = 0.01) with an acrophase at 12:51 pm. The number of requests per day for outpatients developed similarly to regional cases while demand for in-patients increased later and persisted longer. CONCLUSIONS: The demand for COVID-19 related chest imaging displayed distinct distribution patterns depending on the sector of patient care and point of time during the SARS-CoV-2 pandemic. These patterns should be considered in the allocation of resources in future pandemic challenges with similar disease characteristics.


Subject(s)
COVID-19/diagnostic imaging , Diagnostic Imaging/trends , Thorax/diagnostic imaging , Adult , Aged , COVID-19/epidemiology , Diagnostic Tests, Routine/trends , Female , Humans , Male , Middle Aged , Models, Theoretical , Pandemics , Pilot Projects , SARS-CoV-2/pathogenicity , Thorax/virology
13.
BMC Med Imaging ; 21(1): 192, 2021 12 13.
Article in English | MEDLINE | ID: covidwho-1571744

ABSTRACT

AIM: This study is to compare the lung image quality between shelter hospital CT (CT Ark) and ordinary CT scans (Brilliance 64) scans. METHODS: The patients who received scans with CT Ark or Brilliance 64 CT were enrolled. Their lung images were divided into two groups according to the scanner. The objective evaluation methods of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were used. The subjective evaluation methods including the evaluation of the fine structure under the lung window and the evaluation of the general structure under the mediastinum window were compared. Kappa method was used to assess the reliability of the subjective evaluation. The subjective evaluation results were analyzed using the Wilcoxon rank sum test. SNR and CNR were tested using independent sample t tests. RESULTS: There was no statistical difference in somatotype of enrolled subjects. The Kappa value between the two observers was between 0.68 and 0.81, indicating good consistency. For subjective evaluation results, the rank sum test P value of fine structure evaluation and general structure evaluation by the two observers was ≥ 0.05. For objective evaluation results, SNR and CNR between the two CT scanners were significantly different (P<0.05). Notably, the absolute values ​​of SNR and CNR of the CT Ark were larger than Brilliance 64 CT scanner. CONCLUSION: CT Ark is fully capable of scanning the lungs of the COVID-19 patients during the epidemic in the shelter hospital.


Subject(s)
COVID-19/diagnostic imaging , Lung/diagnostic imaging , Mobile Health Units/standards , Tomography, X-Ray Computed/instrumentation , Tomography, X-Ray Computed/standards , Adult , Aged , COVID-19/epidemiology , China/epidemiology , Female , Humans , Male , Middle Aged , Observer Variation , Pandemics , SARS-CoV-2 , Signal-To-Noise Ratio
14.
J Laryngol Otol ; 135(11): 1010-1018, 2021 Nov.
Article in English | MEDLINE | ID: covidwho-1569186

ABSTRACT

OBJECTIVE: The primary goal of this study was to evaluate the association between olfactory dysfunction or taste impairment and disease severity and radiological findings in coronavirus disease-2019. The secondary goal was to assess the prevalence, severity and course of olfactory dysfunction or taste impairment in patients with coronavirus disease 2019. METHOD: This prospective observational cohort study evaluated patients hospitalised with coronavirus disease 2019 between April 1 and 1 May 2020. Olfactory dysfunction and taste impairment were evaluated by two questionnaires. Chest computed tomography findings and coronavirus disease-2019 severity were assessed. RESULTS: Among 133 patients, 23.3 per cent and 30.8 per cent experienced olfactory dysfunction and taste impairment, respectively, and 17.2 per cent experienced both. The mean age was 56.03 years, and 64.7 per cent were male and 35.3 per cent were female. No statistically significant association was found between olfactory dysfunction (p = 0.706) and taste impairment (p = 0.35) with either disease severity or chest computed tomography grading. CONCLUSION: Olfactory dysfunction or taste impairment does not have prognostic importance in patients with coronavirus disease 2019.


Subject(s)
COVID-19/complications , Olfaction Disorders/epidemiology , SARS-CoV-2 , Severity of Illness Index , Taste Disorders/epidemiology , Adult , Aged , COVID-19/diagnostic imaging , Female , Hospitalization/statistics & numerical data , Humans , Male , Middle Aged , Olfaction Disorders/virology , Prevalence , Prognosis , Prospective Studies , Taste Disorders/virology , Tomography, X-Ray Computed
15.
Sci Rep ; 11(1): 23914, 2021 12 13.
Article in English | MEDLINE | ID: covidwho-1569278

ABSTRACT

Chest X-ray (CXR) images have been one of the important diagnosis tools used in the COVID-19 disease diagnosis. Deep learning (DL)-based methods have been used heavily to analyze these images. Compared to other DL-based methods, the bag of deep visual words-based method (BoDVW) proposed recently is shown to be a prominent representation of CXR images for their better discriminability. However, single-scale BoDVW features are insufficient to capture the detailed semantic information of the infected regions in the lungs as the resolution of such images varies in real application. In this paper, we propose a new multi-scale bag of deep visual words (MBoDVW) features, which exploits three different scales of the 4th pooling layer's output feature map achieved from VGG-16 model. For MBoDVW-based features, we perform the Convolution with Max pooling operation over the 4th pooling layer using three different kernels: [Formula: see text], [Formula: see text], and [Formula: see text]. We evaluate our proposed features with the Support Vector Machine (SVM) classification algorithm on four CXR public datasets (CD1, CD2, CD3, and CD4) with over 5000 CXR images. Experimental results show that our method produces stable and prominent classification accuracy (84.37%, 88.88%, 90.29%, and 83.65% on CD1, CD2, CD3, and CD4, respectively).


Subject(s)
COVID-19/diagnostic imaging , Radiographic Image Interpretation, Computer-Assisted/methods , Algorithms , Databases, Factual , Deep Learning , Humans , Support Vector Machine
16.
Br J Radiol ; 95(1129): 20210759, 2022 Jan 01.
Article in English | MEDLINE | ID: covidwho-1566545

ABSTRACT

OBJECTIVE: To determine the diagnostic accuracy of a deep-learning (DL)-based algorithm using chest computed tomography (CT) scans for the rapid diagnosis of coronavirus disease 2019 (COVID-19), as compared to the reference standard reverse-transcription polymerase chain reaction (RT-PCR) test. METHODS: In this retrospective analysis, data of COVID-19 suspected patients who underwent RT-PCR and chest CT examination for the diagnosis of COVID-19 were assessed. By quantifying the affected area of the lung parenchyma, severity score was evaluated for each lobe of the lung with the DL-based algorithm. The diagnosis was based on the total lung severity score ranging from 0 to 25. The data were randomly split into a 40% training set and a 60% test set. Optimal cut-off value was determined using Youden-index method on the training cohort. RESULTS: A total of 1259 patients were enrolled in this study. The prevalence of RT-PCR positivity in the overall investigated period was 51.5%. As compared to RT-PCR, sensitivity, specificity, positive predictive value, negative predictive value and accuracy on the test cohort were 39.0%, 80.2%, 68.0%, 55.0% and 58.9%, respectively. Regarding the whole data set, when adding those with positive RT-PCR test at any time during hospital stay or "COVID-19 without virus detection", as final diagnosis to the true positive cases, specificity increased from 80.3% to 88.1% and the positive predictive value increased from 68.4% to 81.7%. CONCLUSION: DL-based CT severity score was found to have a good specificity and positive predictive value, as compared to RT-PCR. This standardized scoring system can aid rapid diagnosis and clinical decision making. ADVANCES IN KNOWLEDGE: DL-based CT severity score can detect COVID-19-related lung alterations even at early stages, when RT-PCR is not yet positive.


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , Adult , Aged , COVID-19/diagnosis , COVID-19/pathology , False Negative Reactions , False Positive Reactions , Female , Humans , Image Processing, Computer-Assisted , Male , Radiography, Thoracic , Reproducibility of Results , Retrospective Studies , Sensitivity and Specificity , Severity of Illness Index , Tomography, X-Ray Computed
17.
Br J Radiol ; 95(1129): 20210570, 2022 Jan 01.
Article in English | MEDLINE | ID: covidwho-1566544

ABSTRACT

OBJECTIVE: Multisystem inflammatory syndrome in children (MIS-C) is seen as a serious delayed complication of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. The aim of this study was to describe the most common imaging features of MIS-C associated with SARS-CoV-2. METHODS: A retrospective review was made of the medical records and radiological imaging studies of 47 children (26 male, 21 female) in the age range of 25 months-15 years who were diagnosed with MIS-C between August 2020 and March 2021. Chest radiographs were available for all 47 patients, thorax ultrasound for 6, chest CT for 4, abdominal ultrasound for 42, abdomen CT for 9, neck ultrasound for 4, neck CT for 2, brain CT for 1, and brain MRI for 3. RESULTS: The most common finding on chest radiographs was perihilar-peribronchial thickening (46%). The most common findings on abdominal ultrasonography were mesenteric inflammation (42%), and hepatosplenomegaly (38%, 28%). Lymphadenopathy was determined in four patients who underwent neck ultrasound, one of whom had deep neck infection on CT. One patient had restricted diffusion and T2 hyperintensity involving the corpus callosum splenium on brain MRI, and one patient had epididymitis related with MIS-C. CONCLUSION: Pulmonary manifestations are uncommon in MIS-C. In the abdominal imaging, mesenteric inflammation, hepatosplenomegaly, periportal edema, ascites and bowel wall thickening are the most common findings. ADVANCES IN KNOWLEDGE: The imaging findings of MIS-C are non-specific and can mimic many other pathologies. Radiologists should be aware that these findings may indicate the correct diagnosis of MIS-C.


Subject(s)
COVID-19/complications , Systemic Inflammatory Response Syndrome/diagnostic imaging , Adolescent , Brain/diagnostic imaging , COVID-19/diagnostic imaging , Child , Child, Preschool , Female , Humans , Magnetic Resonance Imaging , Male , Neck/diagnostic imaging , Neuroimaging , Radiography, Abdominal , Radiography, Thoracic , Retrospective Studies , Tomography, X-Ray Computed , Ultrasonography
18.
Sci Rep ; 11(1): 8304, 2021 04 15.
Article in English | MEDLINE | ID: covidwho-1545653

ABSTRACT

COVID-19, a viral infection originated from Wuhan, China has spread across the world and it has currently affected over 115 million people. Although vaccination process has already started, reaching sufficient availability will take time. Considering the impact of this widespread disease, many research attempts have been made by the computer scientists to screen the COVID-19 from Chest X-Rays (CXRs) or Computed Tomography (CT) scans. To this end, we have proposed GraphCovidNet, a Graph Isomorphic Network (GIN) based model which is used to detect COVID-19 from CT-scans and CXRs of the affected patients. Our proposed model only accepts input data in the form of graph as we follow a GIN based architecture. Initially, pre-processing is performed to convert an image data into an undirected graph to consider only the edges instead of the whole image. Our proposed GraphCovidNet model is evaluated on four standard datasets: SARS-COV-2 Ct-Scan dataset, COVID-CT dataset, combination of covid-chestxray-dataset, Chest X-Ray Images (Pneumonia) dataset and CMSC-678-ML-Project dataset. The model shows an impressive accuracy of 99% for all the datasets and its prediction capability becomes 100% accurate for the binary classification problem of detecting COVID-19 scans. Source code of this work can be found at GitHub-link .


Subject(s)
COVID-19/diagnostic imaging , Neural Networks, Computer , Radiography, Thoracic/methods , Tomography, X-Ray Computed/methods , COVID-19/virology , Datasets as Topic , Humans , SARS-CoV-2/isolation & purification
19.
J Med Virol ; 93(12): 6619-6627, 2021 Dec.
Article in English | MEDLINE | ID: covidwho-1544307

ABSTRACT

Both severe acute respiratory syndrome coronavirus 2 and influenza viruses cause similar clinical presentations. It is essential to assess severely ill patients presenting with a viral syndrome for diagnostic and prognostic purposes. We aimed to compare clinical and biochemical features between pneumonia patients with coronavirus disease 2019 (COVID-19) and H1N1. Sixty patients diagnosed with COVID-19 pneumonia and 61 patients diagnosed with influenza pneumonia were hospitalized between October 2020-January 2021 and October 2017-December 2019, respectively. All the clinical data and laboratory results, chest computed tomography scans, intensive care unit admission, invasive mechanical ventilation, and outcomes were retrospectively evaluated. The median age was 65 (range 32-96) years for patients with a COVID-19 diagnosis and 58 (range 18-83) years for patients with influenza (p = 0.002). The comorbidity index was significantly higher in patients with COVID-19 (p = 0.010). Diabetes mellitus and hypertension were statistically significantly more common in patients with COVID-19 (p = 0.019, p = 0.008, respectively). The distribution of severe disease and mortality was not significantly different among patients with COVID-19 than influenza patients (p = 0.096, p = 0.049).). In comparison with inflammation markers; C-reactive protein (CRP) levels were significantly higher in influenza patients than patients with COVID-19 (p = 0.033). The presence of sputum was predictive for influenza (odds ratio [OR] 0.342 [95% confidence interval [CI], 2.1.130-0.899]). CRP and platelet were also predictive for COVID-19 (OR 4.764 [95% CI, 1.003-1.012] and OR 0.991 [95% CI 0.984-0.998], respectively. We conclude that sputum symptoms by itself are much more detected in influenza patients. Besides that, lower CRP and higher PLT count would be discriminative for COVID-19.


Subject(s)
COVID-19/pathology , Influenza, Human/pathology , Adolescent , Adult , Aged , Aged, 80 and over , C-Reactive Protein/analysis , COVID-19/diagnostic imaging , COVID-19/therapy , Female , Hospitalization , Humans , Influenza A Virus, H1N1 Subtype , Influenza, Human/diagnostic imaging , Influenza, Human/therapy , Intensive Care Units/statistics & numerical data , Length of Stay/statistics & numerical data , Male , Middle Aged , Radiography, Thoracic , Respiration, Artificial/statistics & numerical data , Retrospective Studies , Tomography, X-Ray Computed , Young Adult
20.
J Med Virol ; 93(12): 6582-6587, 2021 Dec.
Article in English | MEDLINE | ID: covidwho-1544305

ABSTRACT

The purpose of this study was to evaluate the SARS-CoV-2 immunoglobulin M/immunoglobulin G (IgM/IgG) rapid antibody test results in symptomatic patients with COVID-19 and their chest computed tomography (CT) data. A total of 320 patients admitted to our hospital for different durations due to COVID-19 were included in the study. Serum samples were obtained within 0-7 days from COVID-19 patients confirmed by reverse-transcription polymerase chain reaction (RT-PCR) and chest CT scan. According to the SARS-CoV-2 RT-PCR results, the patients included in the study were divided into two groups: PCR positive group (n = 46) and PCR negative group (n = 274). The relationship between chest CT and rapid antibody test results were compared statistically. Of the 320 COVID-19 serum samples, IgM, IgG, and IgM/IgG were detected in 8.4%, 0.3%, and 11.6% within 1 week, respectively. IgG/IgM antibodies were not detected in 79.7% of the patients. In the study, 249 (77.8%) of 320 patients had positive chest CT scans. Four (5.6%) of 71 patients with negative chest CT scans had IgM and two (2.8%) were both IgM/IgG positive. IgM was detected in 23 (9.2%), IgG in one (0.4%), and IgM/IgG in 35 (14%) of chest CT scan positive patients. The rate of CT findings in patients with antibody positivity was found to be significantly higher than those with antibody negativity. The results of the present study show the accurate and equivalent performance of serological antibody assays and chest CT in detecting SARS-CoV-2 within 0-7 days from the onset of COVID19 symptoms. When RT-PCR is not available, we believe that the combination of immunochromatographic test and chest CT scan can increase diagnostic sensitivity for COVID-19.


Subject(s)
Antibodies, Viral/blood , COVID-19 Testing/methods , COVID-19/diagnosis , Reverse Transcriptase Polymerase Chain Reaction/methods , Adolescent , Adult , Aged , Aged, 80 and over , Antibodies, Viral/immunology , COVID-19/diagnostic imaging , Female , Humans , Immunoglobulin G/blood , Immunoglobulin G/immunology , Immunoglobulin M/blood , Immunoglobulin M/immunology , Male , Middle Aged , Radiography, Thoracic , Retrospective Studies , Tomography, X-Ray Computed , Young Adult
SELECTION OF CITATIONS
SEARCH DETAIL
...