Dataset Information

From community-acquired pneumonia to COVID-19: a deep learning-based method for quantitative analysis of COVID-19 on thick-section CT scans.

ABSTRACT: OBJECTIVE:To develop a fully automated AI system to quantitatively assess the disease severity and disease progression of COVID-19 using thick-section chest CT images. METHODS:In this retrospective study, an AI system was developed to automatically segment and quantify the COVID-19-infected lung regions on thick-section chest CT images. Five hundred thirty-one CT scans from 204 COVID-19 patients were collected from one appointed COVID-19 hospital. The automatically segmented lung abnormalities were compared with manual segmentation of two experienced radiologists using the Dice coefficient on a randomly selected subset (30 CT scans). Two imaging biomarkers were automatically computed, i.e., the portion of infection (POI) and the average infection HU (iHU), to assess disease severity and disease progression. The assessments were compared with patient status of diagnosis reports and key phrases extracted from radiology reports using the area under the receiver operating characteristic curve (AUC) and Cohen's kappa, respectively. RESULTS:The dice coefficient between the segmentation of the AI system and two experienced radiologists for the COVID-19-infected lung abnormalities was 0.74 ± 0.28 and 0.76 ± 0.29, respectively, which were close to the inter-observer agreement (0.79 ± 0.25). The computed two imaging biomarkers can distinguish between the severe and non-severe stages with an AUC of 0.97 (p value < 0.001). Very good agreement (? = 0.8220) between the AI system and the radiologists was achieved on evaluating the changes in infection volumes. CONCLUSIONS:A deep learning-based AI system built on the thick-section CT imaging can accurately quantify the COVID-19-associated lung abnormalities and assess the disease severity and its progressions. KEY POINTS:• A deep learning-based AI system was able to accurately segment the infected lung regions by COVID-19 using the thick-section CT scans (Dice coefficient ? 0.74). • The computed imaging biomarkers were able to distinguish between the non-severe and severe COVID-19 stages (area under the receiver operating characteristic curve 0.97). • The infection volume changes computed by the AI system were able to assess the COVID-19 progression (Cohen's kappa 0.8220).

SUBMITTER: Li Z

PROVIDER: S-EPMC7368602 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

From community-acquired pneumonia to COVID-19: a deep learning-based method for quantitative analysis of COVID-19 on thick-section CT scans.

Li Zhang Z Zhong Zheng Z Li Yang Y Zhang Tianyu T Gao Liangxin L Jin Dakai D Sun Yue Y Ye Xianghua X Yu Li L Hu Zheyu Z Xiao Jing J Huang Lingyun L Tang Yuling Y

European radiology 20200718 12

<h4>Objective</h4>To develop a fully automated AI system to quantitatively assess the disease severity and disease progression of COVID-19 using thick-section chest CT images.<h4>Methods</h4>In this retrospective study, an AI system was developed to automatically segment and quantify the COVID-19-infected lung regions on thick-section chest CT images. Five hundred thirty-one CT scans from 204 COVID-19 patients were collected from one appointed COVID-19 hospital. The automatically segmented lung ...[more]

PMID: 32683550

Similar Datasets

Project description:BackgroundCorona Virus Disease 2019 (COVID-19) is currently a worldwide pandemic and has a huge impact on public health and socio-economic development. The purpose of this study is to explore the diagnostic value of the quantitative computed tomography (CT) method by using different threshold segmentation techniques to distinguish between patients with or without COVID-19 pneumonia.MethodsA total of 47 patients with suspected COVID-19 were retrospectively analyzed, including nine patients with positive real-time fluorescence reverse transcription polymerase chain reaction (RT-PCR) test (confirmed case group) and 38 patients with negative RT-PCR test (excluded case group). An improved 3D convolutional neural network (VB-Net) was used to automatically extract lung lesions. Eight different threshold segmentation methods were used to define the ground glass opacity (GGO) and consolidation. The receiver operating characteristic (ROC) curves were used to compare the performance of various parameters with different thresholds for diagnosing COVID-19 pneumonia.ResultsThe volume of GGO (VOGGO) and GGO percentage in the whole lung (GGOPITWL) were the most effective values for diagnosing COVID-19 at a threshold of - 300 HU, with areas under the curve (AUCs) of 0.769 and 0.769, sensitivity of 66.67 and 66.67%, specificity of 94.74 and 86.84%. Compared with VOGGO or GGOPITWL at a threshold of - 300 Hounsfield units (HU), the consolidation percentage in the whole lung (CPITWL) with thresholds at - 400 HU, - 350 HU, and - 250 HU were statistically different. There were statistical differences in the infection volume and percentage of the whole lung, right lung, and lobes between the two groups. VOGGO, GGOPITWL, and volume of consolidation (VOC) were also statistically different at the threshold of - 300 HU.ConclusionsQuantitative CT provides an image quantification method for the auxiliary diagnosis of COVID-19 and is expected to assist in confirming patients with COVID-19 pneumonia in suspected cases.

Project description:BackgroundIt is difficult to distinguish subtle differences shown in computed tomography (CT) images of coronavirus disease 2019 (COVID-19) and bacterial pneumonia patients, which often leads to an inaccurate diagnosis. It is desirable to design and evaluate interpretable feature extraction techniques to describe the patient's condition.MethodsThis is a retrospective cohort study of 170 confirmed patients with COVID-19 or bacterial pneumonia acquired at Yeungnam University Hospital in Daegu, Korea. The Lung and lesion regions were segmented to crop the lesion into 2D patches to train a classifier model that could differentiate between COVID-19 and bacterial pneumonia. The K-means algorithm was used to cluster deep features extracted by the trained model into 20 groups. Each lesion patch cluster was described by a characteristic imaging term for comparison. For each CT image containing multiple lesions, a histogram of lesion types was constructed using the cluster information. Finally, a Support Vector Machine classifier was trained with the histogram and radiomics features to distinguish diseases and severity.ResultsThe 20 clusters constructed from 170 patients were reviewed based on common radiographic appearance types. Two clusters showed typical findings of COVID-19, with two other clusters showing typical findings related to bacterial pneumonia. Notably, there is one cluster that showed bilateral diffuse ground-glass opacities (GGOs) in the central and peripheral lungs and was considered to be a key factor for severity classification. The proposed method achieved an accuracy of 91.2% for classifying COVID-19 and bacterial pneumonia patients with 95% reported for severity classification. The CT quantitative parameters represented by the values of cluster 8 were correlated with existing laboratory data and clinical parameters.ConclusionDeep chest CT analysis with constructed lesion clusters revealed well-known COVID-19 CT manifestations comparable to manual CT analysis. The constructed histogram features improved accuracy for both diseases and severity classification, and showed correlations with laboratory data and clinical parameters. The constructed histogram features can provide guidance for improved analysis and treatment of COVID-19.

Dataset Information

From community-acquired pneumonia to COVID-19: a deep learning-based method for quantitative analysis of COVID-19 on thick-section CT scans.

Publications

From community-acquired pneumonia to COVID-19: a deep learning-based method for quantitative analysis of COVID-19 on thick-section CT scans.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets