Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 8 de 8
Filter
1.
Displays ; : 102144, 2021.
Article in English | ScienceDirect | ID: covidwho-1587952

ABSTRACT

Radiomics based on lesion segmentation has been widely accepted for disease diagnosis;however, it is difficult to precisely determine the boundary for pneumonia due to its diffuse characteristics. In this study, we aimed to propose an automatic radiomics method using whole-lung segmentation in pneumonia discrimination and assist clinical practitioners in fast and accurate diagnosis. In the discovery set, data from 151 participants diagnosed with type A or B influenza virus pneumonia, 63 diagnosed with coronavirus disease 2019 (COVID-19) and 50 healthy participants were collected. The three groups of data were compared in pairs. A total of 117 radiomics features were extracted from whole-lung images segmented by a four-layer U-net. We then utilized a logistic regression model to train the model and used the area under the receiver operating characteristic curve (AUC) to assess its performance. The L1 regularization term was used in feature selection, and 10-fold cross-validation was used to tune the hyperparameters. Fourteen radiomics features were selected to classify influenza pneumonia and health, and the AUC was 0.957 (95% confidential interval (CI): 0.939, 0.976) in the training set and 0.914 (95% CI: 0.866, 0.963) in the testing set. Eighteen features were selected for COVID-19 and health, and the AUC was 0.949 (95% CI: 0.926, 0.973)in the training set and 0.911 (95% CI: 0.859, 0.963) in the testing set. Twenty-eight features were selected for influenza virus pneumonia and COVID-19, and the AUC was 0.895 (95% CI: 0.870, 0.920) in the training set and 0.839 (95% CI: 0.791, 0.887) in the testing set. The results show that the automatic radiomics model based on whole lung segmentation is effective in distinguishing influenza virus pneumonia, COVID-19 and health, and may assist in the diagnosis of influenza virus pneumonia and COVID-19.

2.
Chin J Acad Radiol ; 4(4): 241-247, 2021.
Article in English | MEDLINE | ID: covidwho-1107922

ABSTRACT

PURPOSE: To analyze the initial CT features of different clinical categories of COVID-19. MATERIAL AND METHODS: A total of 86 patients with COVID-19 were analyzed, including the clinical, laboratory and imaging features. The following imaging features were analyzed, the lesion amount, location, density, lung nodule, halo sign, reversed-halo sign, distribution pattern, inner structures and changes of adjacent structures. Chi-square test, Fisher's exact test, or Mann-Whitney U test was used for the enumeration data. Binary logistic regression analysis was performed to draw a regression equation to estimate the likelihood of severe and critical category. The forward conditional method was employed for variable selection. RESULTS: Significant statistical differences were found in age (p = 0.001) and sex (p = 0.028) between mild and moderate and severe and critical category. No significant difference was found in clinical symptoms and WBC count between the two groups. The majority of cases (91.8%) showed multifocal lesions. The presence of GGO was higher in severe and critical category than in the mild and moderate category. (57.8% vs.31.7%, p = 0.015). Lymphocyte count was important indicator for the severe and critical category. CONCLUSION: The initial CT features of the different clinical category overlapped. Combining with laboratory test, especially the lymphocyte count, could help to predict the severity of COVID-19. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s42058-021-00056-4.

3.
Acta Radiol ; 63(3): 291-310, 2022 Mar.
Article in English | MEDLINE | ID: covidwho-1105634

ABSTRACT

Quick screening patients with COVID-19 is the most important way of controlling transmission by isolation and medical treatment. Chest computed tomography (CT) has been widely used during the initial screening process, including pneumonia diagnosis, severity assessment, and differential diagnosis of COVID-19. The course of COVID-19 changes rapidly. Serial CT imaging could observe the distribution, density, and range of lesions dynamically, monitor the changes, and then guide towards appropriate treatment. The aim of the review was to explore the chest CT findings and dynamic CT changes of COVID-19 using systematic evaluation methods, instructing the clinical imaging diagnosis. A systematic literature search was performed. The quality of included literature was evaluated with a quality assessment tool, followed by data extraction and meta-analysis. Homogeneity and publishing bias were analyzed. A total of 109 articles were included, involving 2908 adults with COVID-19. The lesions often occurred in bilateral lungs (74%) and were multifocal (77%) with subpleural distribution (81%). Lesions often showed ground-glass opacity (GGO) (68%), followed by GGO with consolidation (48%). The thickening of small vessels (70%) and thickening of intralobular septum (53%) were also common. The dynamic changes of chest CT manifestations showed that lesions were absorbed and improved gradually after reaching the peak (80%), had progressive deterioration (55%), were absorbed and improved gradually (46%), fluctuated (22%), or remained stable (26%). The review showed the common and key CT features and the dynamic imaging change patterns of COVID-19, helping with timely management during COVID-19 pandemic.


Subject(s)
COVID-19/diagnostic imaging , Lung/diagnostic imaging , Tomography, X-Ray Computed , Adolescent , Adult , Aged , Aged, 80 and over , COVID-19/therapy , Confidence Intervals , Diagnosis, Differential , Disease Progression , Female , Humans , Male , Middle Aged , Publication Bias , Young Adult
5.
Eur Radiol ; 30(9): 5214-5216, 2020 09.
Article in English | MEDLINE | ID: covidwho-186584
6.
7.
Eur J Radiol ; 127: 109008, 2020 Jun.
Article in English | MEDLINE | ID: covidwho-72262

ABSTRACT

Coronavirus disease 2019 (COVID-19) is highly contagious, mainly causing inflammatory lesions in the lungs, and can also cause damage to the intestine and liver. The rapid spread of the virus that causes coronavirus disease 2019 (COVID-19) pneumonia has posed complex challenges to global public health. Early detection, isolation, diagnosis, and treatment are the most effective means of prevention and control. At present, the epidemic situation of new coronavirus infection has tended to be controlled in China, and it is still in a period of rapid rise in much of the world. The current gold standard for the diagnosis of COVID-19 is the detection of coronavirus nucleic acids, but imaging has an important role in the detection of lung lesions, stratification, evaluation of treatment strategies, and differentiation of mixed infections. This Chinese expert consensus statement summarizes the imaging features of COVID-19 pneumonia and may help radiologists across the world to understand this disease better.


Subject(s)
Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Artificial Intelligence , Betacoronavirus , COVID-19 , China/epidemiology , Consensus , Coronavirus Infections/epidemiology , Coronavirus Infections/pathology , Diagnosis, Differential , Early Diagnosis , Humans , Pandemics , Pneumonia, Viral/epidemiology , Pneumonia, Viral/pathology , Radiography, Thoracic , Radiologists , SARS-CoV-2
8.
Chin J Acad Radiol ; : 1-10, 2020 Mar 18.
Article in English | MEDLINE | ID: covidwho-47416

ABSTRACT

COVID-19 has become a public health emergency due to its rapid transmission. The appearance of pneumonia is one of the major clues for the diagnosis, progress and therapeutic evaluation. More and more literatures about imaging manifestations and related research have been reported. In order to know about the progress and prospective on imaging of COVID-19, this review focus on interpreting the CT findings, stating the potential pathological basis, proposing the challenge of patients with underlying diseases, differentiating with other diseases and suggesting the future research and clinical directions, which would be helpful for the radiologists in the clinical practice and research.

SELECTION OF CITATIONS
SEARCH DETAIL