Dataset Information

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

ABSTRACT: Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. ©?RSNA, 2020 Online supplemental material is available for this article.

SUBMITTER: Li L

PROVIDER: S-EPMC7233473 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

Li Lin L Qin Lixin L Xu Zeguo Z Yin Youbing Y Wang Xin X Kong Bin B Bai Junjie J Lu Yi Y Fang Zhenghan Z Song Qi Q Cao Kunlin K Liu Daliang D Wang Guisheng G Xu Qizhong Q Fang Xisheng X Zhang Shiqin S Xia Juan J Xia Jun J

Radiology 20200319 2

Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volu ...[more]

PMID: 32191588

Similar Datasets

Project description:IntroductionCommunity-acquired pneumonia (CAP) requires prompt treatment, but its diagnosis is complex. Improvement of bacterial CAP diagnosis by biomarkers has been evaluated using chest X-ray infiltrate as the CAP gold standard, producing conflicting results. We analyzed the diagnostic accuracy of biomarkers in suspected CAP adults visiting emergency departments for whom CAP diagnosis was established by an adjudication committee which founded its judgment on a systematic multidetector thoracic CT scan.MethodsIn an ancillary study of a multi-center prospective study evaluating the impact of systematic thoracic CT scan on CAP diagnosis, sensitivity and specificity of C-reactive protein (CRP) and procalcitonin (PCT) were evaluated. Systematic nasopharyngeal multiplex respiratory virus PCR was performed at inclusion. An adjudication committee classified CAP diagnostic probability on a 4-level Likert scale, based on all available data.ResultsTwo hundred patients with suspected CAP were analyzed. The adjudication committee classified 98 patients (49.0 %) as definite CAP, 8 (4.0 %) as probable, 23 (11.5 %) as possible and excluded in 71 (35.5 %, including 29 patients with pulmonary infiltrates on chest X-ray). Among patients with radiological pulmonary infiltrate, 23 % were finally classified as excluded. Viruses were identified by PCR in 29 % of patients classified as definite. Area under the curve was 0.787 [95 % confidence interval (95 % CI), 0.717 to 0.857] for CRP and 0.655 (95 % CI, 0.570 to 0.739) for PCT to detect definite CAP. CRP threshold at 50 mg/L resulted in a positive predictive value of 0.76 and a negative predictive value of 0.75. No PCT cut-off resulted in satisfactory positive or negative predictive values. CRP and PCT accuracy was not improved by exclusion of the 25 (25.5 %) definite viral CAP cases.ConclusionsFor patients with suspected CAP visiting emergency departments, diagnostic accuracy of CRP and PCT are insufficient to confirm the CAP diagnosis established using a gold standard that includes thoracic CT scan. Diagnostic accuracy of these biomarkers is also insufficient to distinguish bacterial CAP from viral CAP.Trial registrationClinicalTrials.gov registry NCT01574066 (February 7, 2012).

Project description:ObjectiveThe chest X-ray (CXR) is the most readily available and common imaging modality for the assessment of pneumonia. However, detecting pneumonia from chest radiography is a challenging task, even for experienced radiologists. An artificial intelligence (AI) model might help to diagnose pneumonia from CXR more quickly and accurately. We aim to develop an AI model for pneumonia from CXR images and to evaluate diagnostic performance with external dataset.MethodsTo train the pneumonia model, a total of 157,016 CXR images from the National Institutes of Health (NIH) and the Korean National Tuberculosis Association (KNTA) were used (normal vs. pneumonia = 120,722 vs.36,294). An ensemble model of two neural networks with DenseNet classifies each CXR image into pneumonia or not. To test the accuracy of the models, a separate external dataset of pneumonia CXR images (n = 212) from a tertiary university hospital (Gachon University Gil Medical Center GUGMC, Incheon, South Korea) was used; the diagnosis of pneumonia was based on both the chest CT findings and clinical information, and the performance evaluated using the area under the receiver operating characteristic curve (AUC). Moreover, we tested the change of the AI probability score for pneumonia using the follow-up CXR images (7 days after the diagnosis of pneumonia, n = 100).ResultsWhen the probability scores of the models that have a threshold of 0.5 for pneumonia, two models (models 1 and 4) having different pre-processing parameters on the histogram equalization distribution showed best AUC performances of 0.973 and 0.960, respectively. As expected, the ensemble model of these two models performed better than each of the classification models with 0.983 AUC. Furthermore, the AI probability score change for pneumonia showed a significant difference between improved cases and aggravated cases (Δ = -0.06 ± 0.14 vs. 0.06 ± 0.09, for 85 improved cases and 15 aggravated cases, respectively, P = 0.001) for CXR taken as a 7-day follow-up.ConclusionsThe ensemble model combined two different classification models for pneumonia that performed at 0.983 AUC for an external test dataset from a completely different data source. Furthermore, AI probability scores showed significant changes between cases of different clinical prognosis, which suggest the possibility of increased efficiency and performance of the CXR reading at the diagnosis and follow-up evaluation for pneumonia.

Project description:BackgroundArtificial intelligence (AI)-aided analysis of chest CT expedites the quantification of abnormalities and may facilitate the diagnosis and assessment of the prognosis of subjects with COVID-19.ObjectivesThis study investigates the performance of an AI-aided quantification model in predicting the clinical outcomes of hospitalized subjects with COVID-19 and compares it with radiologists' performance.Subjects and methodsA total of 90 subjects with COVID-19 (men, n = 59 [65.6%]; age, 52.9±16.7 years) were recruited in this cross-sectional study. Quantification of the total and compromised lung parenchyma was performed by two expert radiologists using a volumetric image analysis software and compared against an AI-assisted package consisting of a modified U-Net model for segmenting COVID-19 lesions and an off-the-shelf U-Net model augmented with COVID-19 data for segmenting lung volume. The fraction of compromised lung parenchyma (%CL) was calculated. Based on clinical results, the subjects were divided into two categories: critical (n = 45) and noncritical (n = 45). All admission data were compared between the two groups.ResultsThere was an excellent agreement between the radiologist-obtained and AI-assisted measurements (intraclass correlation coefficient = 0.88, P < 0.001). Both the AI-assisted and radiologist-obtained %CLs were significantly higher in the critical subjects (P = 0.009 and 0.02, respectively) than in the noncritical subjects. In the multivariate logistic regression analysis to distinguish the critical subjects, an AI-assisted %CL ≥35% (odds ratio [OR] = 17.0), oxygen saturation level of <88% (OR = 33.6), immunocompromised condition (OR = 8.1), and other comorbidities (OR = 15.2) independently remained as significant variables in the models. Our proposed model obtained an accuracy of 83.9%, a sensitivity of 79.1%, and a specificity of 88.6% in predicting critical outcomes.ConclusionsAI-assisted measurements are similar to quantitative radiologist-obtained measurements in determining lung involvement in COVID-19 subjects.

Project description:Community-acquired pneumonia (CAP) remains one of the most common indications for pediatric hospitalization in the United States, and it is frequently the focus of research and quality studies. Use of administrative data is increasingly common for these purposes, although proper validation is required to ensure valid study conclusions.To validate administrative billing data for hospitalizations owing to childhood CAP.Case-control study of 4 tertiary care, freestanding children’s hospitals in the United States.A total of 998 medical records of a 25% random sample of 3646 children discharged in 2010 with at least 1 International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) code representing possible pneumonia were reviewed. Discharges (matched on date of admission) without a pneumonia-related discharge code were also examined to identify potential missed pneumonia cases. Two reference standards, based on provider diagnosis alone (provider confirmed) or in combination with consistent clinical and radiographic evidence of pneumonia (definite), were used to identify CAP.Twelve ICD-9-CM–based coding strategies, each using a combination of primary or secondary codes representing pneumonia or pneumonia-related complications. Six algorithms excluded children with complex chronic conditions.Sensitivity, specificity, and negative and positive predictive values (NPV and PPV, respectively) of the 12 identification strategies.For provider-confirmed CAP (n?=?680), sensitivity ranged from 60.7% to 99.7%; specificity, 75.7% to 96.4%; PPV, 67.9% to 89.6%; and NPV, 82.6% to 99.8%. For definite CAP (n?=?547), sensitivity ranged from 65.6% to 99.6%; specificity, 68.7% to 93.0%; PPV, 54.6% to 77.9%; and NPV, 87.8% to 99.8%. Unrestricted use of the pneumonia-related codes was inaccurate, although several strategies improved specificity to more than 90% with a variable effect on sensitivity. Excluding children with complex chronic conditions demonstrated the most favorable performance characteristics. Performance of the algorithms was similar across institutions.Administrative data are valuable for studying pediatric CAP hospitalizations. The strategies presented here will aid in the accurate identification of relevant and comparable patient populations for research and performance improvement studies.

Dataset Information

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

Publications

Using Artificial Intelligence to Detect COVID-19 and Community-acquired Pneumonia Based on Pulmonary CT: Evaluation of the Diagnostic Accuracy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets