A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images

Ni, Qianqian; Sun, Zhi; Li, Qi; Chen, Wen; Yang, Yi; Wang, Li; Zhang, Mengjie; Liu, Yang; Fang, Yi; Xing, Zijian; Zhou, Zhen; Yu, Yizhou; Lu, Guang Ming; Zhang, Long Jiang

doi:10.1007/s00330-020-07044-9

Cited by 179 publications

(134 citation statements)

References 31 publications

Supporting

Mentioning

128

Contrasting

Unclassified

Order By: Relevance

“…Ni et al utilized a deep learning model for automatic detection of abnormalities in chest CT images of COVID-19 patients. They demonstrated the deep-learning model performed exceptionally in detecting COVID-19 pneumonia on chest CT and could assist radiologists in making quicker diagnoses with superior diagnostic performance [20]. Further research will be needed to compare the diagnostic performance of deep learning algorithms with human readers, and to verify whether deep learning can assist radiologists and improve their accuracy and efficiency in the diagnosis of COVID-19.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of the Usefulness of CO-RADS for Chest CT in Patients Suspected of Having COVID-19

et al. 2020

View full text Add to dashboard Cite

The purpose of this study was to use the Coronavirus Disease 2019 (COVID-19) Reporting and Data System (CO-RADS) to evaluate the chest computed tomography (CT) images of patients suspected of having COVID-19, and to investigate its diagnostic performance and interobserver agreement. The Dutch Radiological Society developed CO-RADS as a diagnostic indicator for assessing suspicion of lung involvement of COVID-19 on a scale of 1 (very low) to 5 (very high). We investigated retrospectively 154 adult patients with clinically suspected COVID-19, between April and June 2020, who underwent chest CT and reverse transcription-polymerase chain reaction (RT-PCR). The patients’ average age was 61.3 years (range, 21–93), 101 were male, and 76 were RT-PCR positive. Using CO-RADS, four radiologists evaluated the chest CT images. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Interobserver agreement was calculated using the intraclass correlation coefficient (ICC) by comparing the individual reader’s score to the median of the remaining three radiologists. The average sensitivity was 87.8% (range, 80.2–93.4%), specificity was 66.4% (range, 51.3–84.5%), and AUC was 0.859 (range, 0.847–0.881); there was no significant difference between the readers (p > 0.200). In 325 (52.8%) of 616 observations, there was absolute agreement among observers. The average ICC of readers was 0.840 (range, 0.800–0.874; p < 0.001). CO-RADS is a categorical taxonomic evaluation scheme for COVID-19 pneumonia, using chest CT images, that provides outstanding performance and from substantial to almost perfect interobserver agreement for predicting COVID-19.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of the Usefulness of CO-RADS for Chest CT in Patients Suspected of Having COVID-19

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Chest CT has played a pivotal diagnostic role in the assessment of the disease severity according to the number, extent, density of patchy ground-glass opacities (GGOs), and consolidation [11]. Differential diagnosis, severity rating, and prognosis prediction about COVID-19 have been investigated using a quantitative CT combined with artificial intelligence (AI) technology [12][13][14]. However, quantitative CT study about the effect of comorbidity on patients with COVID-19 has not been reported, which may provide the radiological evidence of the severity of pneumonia.…”

mentioning

confidence: 99%

Development of a quantitative segmentation model to assess the effect of comorbidity on patients with COVID-19

et al. 2020

View full text Add to dashboard Cite

Background The coronavirus disease 2019 (COVID-19) has brought a global disaster. Quantitative lesions may provide the radiological evidence of the severity of pneumonia and further to assess the effect of comorbidity on patients with COVID-19. Methods 294 patients with COVID-19 were enrolled from February, 24, 2020 to June, 1, 2020 from six centers. Multi-task Unet network was used to segment the whole lung and lesions from chest CT images. This deep learning method was pre-trained in 650 CT images (550 in primary dataset and 100 in test dataset) with COVID-19 or community-acquired pneumonia and Dice coefficients in test dataset were calculated. 50 CT scans of 50 patients (15 with comorbidity and 35 without comorbidity) were random selected to mark lesions manually. The results will be compared with the automatic segmentation model. Eight quantitative parameters were calculated based on the segmentation results to evaluate the effect of comorbidity on patients with COVID-19. Results Quantitative segmentation model was proved to be effective and accurate with all Dice coefficients more than 0.85 and all accuracies more than 0.95. Of the 294 patients, 52 (17.7%) patients were reported having at least one comorbidity; 14 (4.8%) having more than one comorbidity. Patients with any comorbidity were older (P < 0.001), had longer incubation period (P < 0.001), were more likely to have abnormal laboratory findings (P < 0.05), and be in severity status (P < 0.001). More lesions (including larger volume of lesion, consolidation, and ground-glass opacity) were shown in patients with any comorbidity than patients without comorbidity (all P < 0.001). More lesions were found on CT images in patients with more comorbidities. The median volumes of lesion, consolidation, and ground-glass opacity in diabetes mellitus group were largest among the groups with single comorbidity that had the incidence rate of top three. Conclusions Multi-task Unet network can make quantitative CT analysis of lesions to assess the effect of comorbidity on patients with COVID-19, further to provide the radiological evidence of the severity of pneumonia. More lesions (including GGO and consolidation) were found in CT images of cases with comorbidity. The more comorbidities patients have, the more lesions CT images show.

show abstract

“…Chest CT has played a pivotal diagnostic role in the assessment of the disease severity according to the number, extent, density of patchy ground-glass opacities (GGOs) and consolidation [11]. Differential diagnosis, severity rating, and prognosis prediction about COVID-19 have been investigated using a quantitative CT combined with arti cial intelligence (AI) technology [12][13][14]. However, quantitative CT study about the effect of comorbidity on patients with COVID-19 has not been reported, which may provide the radiological evidence of the severity of pneumonia.…”

Section: Introductionmentioning

confidence: 99%

Development a quantitative segmentation model to assess the effect of comorbidity on patients with COVID-19

Zhang

Yang

Cai

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The coronavirus disease 2019 (COVID-19) has brought a global disaster. Quantitative lesions may provide the radiological evidence of the severity of pneumonia and further to assess the effect of comorbidity on patients with COVID-19.Methods: 294 patients with COVID-19 were enrolled from February, 24, 2020 to June, 1, 2020 from six centers. Multi-task Unet network was used to segment the whole lung and lesions from chest CT images. This deep learning method was pre-trained in 650 CT images (550 in primary dataset and 100 in test dataset) with COVID-19 or community acquired pneumonia and Dice coefficients in test dataset were calculated. 50 CT scans of 50 patients (15 with comorbidity and 35 without comorbidity) were random selected to mark lesions manually. The results will be compared with the automatic segmentation model. Eight quantitative parameters were calculated based on the segmentation results to evaluate the effect of comorbidity on patients with COVID-19.Results: Quantitative segmentation model was proved to be effective and accurate with all Dice coefficients more than 0.85 and all accuracies more than 0.95. Of the 294 patients, 52 (17.7%) patients were reported having at least one comorbidity, 14 (4.8%) having more than one comorbidity. Patients with any comorbidity were older (P<0.001), had longer incubation period (P<0.001), were more likely to have abnormal laboratory findings (P<0.05) and be in severity status (P<0.001). More lesions (including larger volume of lesion, consolidation and ground-glass opacity) were shown in patients with any comorbidity than patients without comorbidity (all P<0.001). More lesions were found on CT images in patients with more comorbidities. The median volumes of lesion, consolidation and ground-glass opacity in diabetes mellitus group were largest among the groups with single comorbidity that had the incidence rate of top three.Conclusions: Multi-task Unet network can make quantitative CT analysis of lesions to assess the effect of comorbidity on patients with COVID-19, further to provide the radiological evidence of the severity of pneumonia. More lesions (including GGO and consolidation) were found in CT images of cases with comorbidity. The more comorbidities patients have, the more lesions CT images show.

show abstract

A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images

Cited by 179 publications

References 31 publications

Evaluation of the Usefulness of CO-RADS for Chest CT in Patients Suspected of Having COVID-19

Evaluation of the Usefulness of CO-RADS for Chest CT in Patients Suspected of Having COVID-19

Development of a quantitative segmentation model to assess the effect of comorbidity on patients with COVID-19

Development a quantitative segmentation model to assess the effect of comorbidity on patients with COVID-19

Contact Info

Product

Resources

About