Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.
Ontology highlight
ABSTRACT:
SUBMITTER: Harmon SA
PROVIDER: S-EPMC7429815 | biostudies-literature | 2020 Aug
REPOSITORIES: biostudies-literature
Publications
Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.
Harmon Stephanie A SA Sanford Thomas H TH Xu Sheng S Turkbey Evrim B EB Roth Holger H Xu Ziyue Z Yang Dong D Myronenko Andriy A Anderson Victoria V Amalou Amel A Blain Maxime M Kassin Michael M Long Dilara D Varble Nicole N Walker Stephanie M SM Bagci Ulas U Ierardi Anna Maria AM Stellato Elvira E Plensich Guido Giovanni GG Franceschelli Giuseppe G Girlando Cristiano C Irmici Giovanni G Labella Dominic D Hammoud Dima D Malayeri Ashkan A Jones Elizabeth E Summers Ronald M RM Choyke Peter L PL Xu Daguang D Flores Mona M Tamura Kaku K Obinata Hirofumi H Mori Hitoshi H Patella Francesca F Cariati Maurizio M Carrafiello Gianpaolo G An Peng P Wood Bradford J BJ Turkbey Baris B
Nature communications 20200814 1
Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8 ...[more]
Similar Datasets
Project description:Recent studies show the potential of artificial intelligence (AI) as a screening tool to detect COVID-19 pneumonia based on chest x-ray (CXR) images. However, issues on the datasets and study designs from medical and technical perspectives, as well as questions on the vulnerability and robustness of AI algorithms have emerged. In this study, we address these issues with a more realistic development of AI-driven COVID-19 pneumonia detection models by generating our own data through a retrospective clinical study to augment the dataset aggregated from external sources. We optimized five deep learning architectures, implemented development strategies by manipulating data distribution to quantitatively compare study designs, and introduced several detection scenarios to evaluate the robustness and diagnostic performance of the models. At the current level of data availability, the performance of the detection model depends on the hyperparameter tuning and has less dependency on the quantity of data. InceptionV3 attained the highest performance in distinguishing pneumonia from normal CXR in two-class detection scenario with sensitivity (Sn), specificity (Sp), and positive predictive value (PPV) of 96%. The models attained higher general performance of 91-96% Sn, 94-98% Sp, and 90-96% PPV in three-class compared to four-class detection scenario. InceptionV3 has the highest general performance with accuracy, F1-score, and g-mean of 96% in the three-class detection scenario. For COVID-19 pneumonia detection, InceptionV3 attained the highest performance with 86% Sn, 99% Sp, and 91% PPV with an AUC of 0.99 in distinguishing pneumonia from normal CXR. Its capability of differentiating COVID-19 pneumonia from normal and non-COVID-19 pneumonia attained 0.98 AUC and a micro-average of 0.99 for other classes.
| S-EPMC8516252 | biostudies-literature
Project description:PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
| S-EPMC7674009 | biostudies-literature
Project description:Background The role and performance of chest CT in the diagnosis of the coronavirus disease 2019 (COVID-19) pandemic remains under active investigation. Purpose To evaluate the French national experience using Chest CT for COVID-19, results of chest CT and RT-PCR were compared together and with the final discharge diagnosis used as reference standard. Materials and Methods A structured CT scan survey (NCT04339686) was sent to 26 hospital radiology departments in France between March 2 and April 24 2020. These dates correspond to the peak of the national COVID-19 epidemic. Radiology departments were selected to reflect the estimated geographical prevalence heterogeneities of the epidemic. All symptomatic patients suspected of having a COVID-19 pneumonia who underwent within 48 hours both initial chest CT and at least one RT-PCR testing were included. The final discharge diagnosis, based on multiparametric items, was recorded. Data for each center were prospectively collected and gathered each week. Test efficacy was determined by using Mann-Whitney Test, Student's t-test, Chi-square test and Pearson's correlation. A p value <.05 determined statistical significance. Results Twenty-six of 26 hospital radiology departments responded to the survey with 7500 patients entered; 2652 did not have RT-PCR results or had unknown or excess delay between RT-PCR and CT. After exclusions, 4824 patients (mean age 64, ± 19 yrs, 2669 males) were included. Using final diagnosis as the reference, 2564 of the 4824 patients were positive for COVID-19 (53%). Sensitivity, specificity, NPV and PPV of chest CT for diagnosing COVID-19 were 2319/2564 (90%, 95% confidence interval [CI]: 89, 91), 2056/2260 (91%, 95%CI: 91, 92%), 2056/2300 (89%, 95%CI; 87, 90%) and 2319/2524 (92%, 95%CI 91, 93%) respectively. There was no significant difference for chest CT efficacy among the 26 geographically separate sites, each with varying amounts of disease prevalence. Conclusion Use of chest CT for the initial diagnosis and triage of suspected COVID-19 patients was successful.
| S-EPMC7465292 | biostudies-literature
Project description:ObjectivesTo study whether a trained convolutional neural network (CNN) can be of assistance to radiologists in differentiating Coronavirus disease (COVID)-positive from COVID-negative patients using chest X-ray (CXR) through an ambispective clinical study. To identify subgroups of patients where artificial intelligence (AI) can be of particular value and analyse what imaging features may have contributed to the performance of AI by means of visualisation techniques.MethodsCXR of 487 patients were classified into [4] categories-normal, classical COVID, indeterminate, and non-COVID by consensus opinion of 2 radiologists. CXR which were classified as "normal" and "indeterminate" were then subjected to analysis by AI, and final categorisation provided as guided by prediction of the network. Precision and recall of the radiologist alone and radiologist assisted by AI were calculated in comparison to reverse transcriptase-polymerase chain reaction (RT-PCR) as the gold standard. Attention maps of the CNN were analysed to understand regions in the CXR important to the AI algorithm in making a prediction.ResultsThe precision of radiologists improved from 65.9 to 81.9% and recall improved from 17.5 to 71.75 when assistance with AI was provided. AI showed 92% accuracy in classifying "normal" CXR into COVID or non-COVID. Analysis of attention maps revealed attention on the cardiac shadow in these "normal" radiographs.ConclusionThis study shows how deployment of an AI algorithm can complement a human expert in the determination of COVID status. Analysis of the detected features suggests possible subtle cardiac changes, laying ground for further investigative studies into possible cardiac changes.Key points• Through an ambispective clinical study, we show how assistance with an AI algorithm can improve recall (sensitivity) and precision (positive predictive value) of radiologists in assessing CXR for possible COVID in comparison to RT-PCR. • We show that AI achieves the best results in images classified as "normal" by radiologists. We conjecture that possible subtle cardiac in the CXR, imperceptible to the human eye, may have contributed to this prediction. • The reported results may pave the way for a human computer collaboration whereby the expert with some help from the AI algorithm achieves higher accuracy in predicting COVID status on CXR than previously thought possible when considering either alone.
| S-EPMC7816060 | biostudies-literature
Project description:The global pandemic of coronavirus disease (COVID-19) has caused millions of deaths and affected the livelihood of many more people. Early and rapid detection of COVID-19 is a challenging task for the medical community, but it is also crucial in stopping the spread of the SARS-CoV-2 virus. Prior substantiation of artificial intelligence (AI) in various fields of science has encouraged researchers to further address this problem. Various medical imaging modalities including X-ray, computed tomography (CT) and ultrasound (US) using AI techniques have greatly helped to curb the COVID-19 outbreak by assisting with early diagnosis. We carried out a systematic review on state-of-the-art AI techniques applied with X-ray, CT, and US images to detect COVID-19. In this paper, we discuss approaches used by various authors and the significance of these research efforts, the potential challenges, and future trends related to the implementation of an AI system for disease detection during the COVID-19 pandemic.
| S-EPMC8659534 | biostudies-literature
Project description:ObjectivesGround-glass opacity and consolidation are recognized typical features of Coronavirus disease-19 (COVID-19) pneumonia on Chest CT, yet ancillary findings have not been fully described. We aimed to describe ancillary findings of COVID-19 pneumonia on CT, to define their prevalence, and investigate their association with clinical data.MethodsWe retrospectively reviewed our CT chest cases with coupled reverse transcriptase polymerase chain reaction (rt-PCR). Patients with negative rt-PCR or without admission chest CT were excluded. Ancillary findings included: vessel enlargement, subpleural curvilinear lines, dependent subpleural atelectasis, centrilobular solid nodules, pleural and/or pericardial effusions, enlarged mediastinal lymph nodes. Continuous data were expressed as median and 95% confidence interval (95% CI) and tested by Mann-Whitney U test.ResultsAncillary findings were represented by 106/252 (42.1%, 36.1 to 48.2) vessel enlargement, 50/252 (19.8%, 15.4 to 25.2) subpleural curvilinear lines, 26/252 (10.1%, 7.1 to 14.7) dependent subpleural atelectasis, 15/252 (5.9%, 3.6 to 9.6) pleural effusion, 15/252 (5.9%, 3.6 to 9.6) mediastinal lymph nodes enlargement, 13/252 (5.2%, 3 to 8.6) centrilobular solid nodules, and 6/252 (2.4%, 1.1 to 5.1) pericardial effusion. Air space disease was more extensive in patients with vessel enlargement or centrilobular solid nodules (p < 0.001). Vessel enlargement was associated with longer history of fever (p = 0.035) and lower admission oxygen saturation (p = 0.014); dependent subpleural atelectasis with lower oxygen saturation (p < 0.001) and higher respiratory rate (p < 0.001); mediastinal lymph nodes with shorter history of cough (p = 0.046); centrilobular solid nodules with lower prevalence of cough (p = 0.023), lower oxygen saturation (p < 0.001), and higher respiratory rate (p = 0.032), and pericardial effusion with shorter history of cough (p = 0.015). Ancillary findings associated with longer hospital stay were subpleural curvilinear lines (p = 0.02), whereas centrilobular solid nodules were associated with higher rate of intensive care unit admission (p = 0.01).ConclusionTypical high-resolution CT findings of COVID-19 pneumonia are frequently associated with ancillary findings that variably associate with disease extent, clinical parameters, and disease severity.Advances in knowledgeAncillary findings might reflect the broad range of heterogeneous mechanisms in severe acute respiratory syndrome from viral pneumonia, and potentially help disease phenotyping.
| S-EPMC7934290 | biostudies-literature
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.
| S-EPMC8049482 | biostudies-literature
Project description:Background Despite its high sensitivity in diagnosing coronavirus disease 2019 (COVID-19) in a screening population, the chest CT appearance of COVID-19 pneumonia is thought to be nonspecific. Purpose To assess the performance of radiologists in the United States and China in differentiating COVID-19 from viral pneumonia at chest CT. Materials and Methods In this study, 219 patients with positive COVID-19, as determined with reverse-transcription polymerase chain reaction (RT-PCR) and abnormal chest CT findings, were retrospectively identified from seven Chinese hospitals in Hunan Province, China, from January 6 to February 20, 2020. Two hundred five patients with positive respiratory pathogen panel results for viral pneumonia and CT findings consistent with or highly suspicious for pneumonia, according to original radiologic interpretation within 7 days of each other, were identified from Rhode Island Hospital in Providence, RI. Three radiologists from China reviewed all chest CT scans (n = 424) blinded to RT-PCR findings to differentiate COVID-19 from viral pneumonia. A sample of 58 age-matched patients was randomly selected and evaluated by four radiologists from the United States in a similar fashion. Different CT features were recorded and compared between the two groups. Results For all chest CT scans (n = 424), the accuracy of the three radiologists from China in differentiating COVID-19 from non-COVID-19 viral pneumonia was 83% (350 of 424), 80% (338 of 424), and 60% (255 of 424). In the randomly selected sample (n = 58), the sensitivities of three radiologists from China and four radiologists from the United States were 80%, 67%, 97%, 93%, 83%, 73%, and 70%, respectively. The corresponding specificities of the same readers were 100%, 93%, 7%, 100%, 93%, 93%, and 100%, respectively. Compared with non-COVID-19 pneumonia, COVID-19 pneumonia was more likely to have a peripheral distribution (80% vs 57%, P < .001), ground-glass opacity (91% vs 68%, P < .001), fine reticular opacity (56% vs 22%, P < .001), and vascular thickening (59% vs 22%, P < .001), but it was less likely to have a central and peripheral distribution (14% vs 35%, P < .001), pleural effusion (4% vs 39%, P < .001), or lymphadenopathy (3% vs 10%, P = .002). Conclusion Radiologists in China and in the United States distinguished coronavirus disease 2019 from viral pneumonia at chest CT with moderate to high accuracy. ©?RSNA, 2020 Online supplemental material is available for this article. A translation of this abstract in Farsi is available in the supplement. ????? ????? ??? ????? ?? ?????? ?? ????? ????? ???.
| S-EPMC7233414 | biostudies-literature
Project description: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.
| S-EPMC7233473 | biostudies-literature
Project description: Not available
| S-EPMC7537264 | biostudies-literature