Dataset Information

COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

ABSTRACT: OBJECTIVES:CT findings of COVID-19 look similar to other atypical and viral (non-COVID-19) pneumonia diseases. This study proposes a clinical computer-aided diagnosis (CAD) system using CT features to automatically discriminate COVID-19 from non-COVID-19 pneumonia patients. METHODS:Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesions of patients in both groups. All significant CT features were fed in five classifiers namely decision tree, K-nearest neighbor, naïve Bayes, support vector machine, and ensemble to evaluate the best performing CAD system in classifying COVID-19 and non-COVID-19 cases. RESULTS:Location and distribution pattern of involvement, number of the lesion, ground-glass opacity (GGO) and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features to classify COVID-19 from non-COVID-19 groups. Our proposed CAD system obtained the sensitivity, specificity, and accuracy of 0.965, 93.54%, 90.32%, and 91.94%, respectively, using ensemble (COVIDiag) classifier. CONCLUSIONS:This study proposed a COVIDiag model obtained promising results using CT radiological routine features. It can be considered an adjunct tool by the radiologists during the current COVID-19 pandemic to make an accurate diagnosis. KEY POINTS:• Location and distribution of involvement, number of lesions, GGO and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features between COVID-19 from non-COVID-19 groups. • The proposed CAD system, COVIDiag, could diagnose COVID-19 pneumonia cases with an AUC of 0.965 (sensitivity?=?93.54%; specificity?=?90.32%; and accuracy?=?91.94%). • The AUC, sensitivity, specificity, and accuracy obtained by radiologist diagnosis are 0.879, 87.10%, 88.71%, and 87.90%, respectively.

SUBMITTER: Abbasian Ardakani A

PROVIDER: S-EPMC7395802 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

Abbasian Ardakani Ali A Acharya U Rajendra UR Habibollahi Sina S Mohammadi Afshin A

European radiology 20200801 1

<h4>Objectives</h4>CT findings of COVID-19 look similar to other atypical and viral (non-COVID-19) pneumonia diseases. This study proposes a clinical computer-aided diagnosis (CAD) system using CT features to automatically discriminate COVID-19 from non-COVID-19 pneumonia patients.<h4>Methods</h4>Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesi ...[more]

PMID: 32740817

Similar Datasets

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.

Project description:Background: As global healthcare system is overwhelmed by novel coronavirus disease (COVID-19), early identification of risks of adverse outcomes becomes the key to optimize management and improve survival. This study aimed to provide a CT-based pattern categorization to predict outcome of COVID-19 pneumonia. Methods: One hundred and sixty-five patients with COVID-19 (91 men, 4-89 years) underwent chest CT were retrospectively enrolled. CT findings were categorized as Pattern 0 (negative), Pattern 1 (bronchopneumonia pattern), Pattern 2 (organizing pneumonia pattern), Pattern 3 (progressive organizing pneumonia pattern), and Pattern 4 (diffuse alveolar damage pattern). Clinical findings were compared across different categories. Time-dependent progression of CT patterns and correlations with clinical outcomes, i.e." discharge or adverse outcome (admission to ICU, requiring mechanical ventilation, or death), with pulmonary sequelae (complete absorption or residuals) on CT after discharge were analyzed. Results: Of 94 patients with outcome, 81 (86.2%) were discharged, 3 (3.2%) were admitted to ICU, 4 (4.3%) required mechanical ventilation, 6 (6.4%) died. 31 (38.3%) had complete absorption at median day 37 after symptom onset. Significant differences between pattern-categories were found in age, disease severity, comorbidity and laboratory results (all P < 0.05). Remarkable evolution was observed in Pattern 0-2 and Pattern 3-4 within 3 and 2 weeks after symptom-onset, respectively; most of patterns remained thereafter. After controlling for age, CT pattern significantly correlated with adverse outcomes [Pattern 4 vs. Pattern 0-3 [reference]; hazard-ratio [95% CI], 18.90 [1.91-186.60], P = 0.012]. CT pattern [Pattern 3-4 vs. Pattern 0-2 [reference]; 0.26 [0.08-0.88], P = 0.030] and C-reactive protein [>10 vs. ≤ 10 mg/L [reference]; 0.31 [0.13-0.72], P = 0.006] were risk factors associated with pulmonary residuals. Conclusion: CT pattern categorization allied with clinical characteristics within 2 weeks after symptom onset would facilitate early prognostic stratification in COVID-19 pneumonia.

Project description:Our aim was to develop practical models built with simple clinical and radiological features to help diagnosing Coronavirus disease 2019 [COVID-19] in a real-life emergency cohort. To do so, 513 consecutive adult patients suspected of having COVID-19 from 15 emergency departments from 2020-03-13 to 2020-04-14 were included as long as chest CT-scans and real-time polymerase chain reaction (RT-PCR) results were available (244 [47.6%] with a positive RT-PCR). Immediately after their acquisition, the chest CTs were prospectively interpreted by on-call teleradiologists (OCTRs) and systematically reviewed within one week by another senior teleradiologist. Each OCTR reading was concluded using a 5-point scale: normal, non-infectious, infectious non-COVID-19, indeterminate and highly suspicious of COVID-19. The senior reading reported the lesions' semiology, distribution, extent and differential diagnoses. After pre-filtering clinical and radiological features through univariate Chi-2, Fisher or Student t-tests (as appropriate), multivariate stepwise logistic regression (Step-LR) and classification tree (CART) models to predict a positive RT-PCR were trained on 412 patients, validated on an independent cohort of 101 patients and compared with the OCTR performances (295 and 71 with available clinical data, respectively) through area under the receiver operating characteristics curves (AUC). Regarding models elaborated on radiological variables alone, best performances were reached with the CART model (i.e., AUC = 0.92 [versus 0.88 for OCTR], sensitivity = 0.77, specificity = 0.94) while step-LR provided the highest AUC with clinical-radiological variables (AUC = 0.93 [versus 0.86 for OCTR], sensitivity = 0.82, specificity = 0.91). Hence, these two simple models, depending on the availability of clinical data, provided high performances to diagnose positive RT-PCR and could be used by any radiologist to support, modulate and communicate their conclusion in case of COVID-19 suspicion. Practically, using clinical and radiological variables (GGO, fever, presence of fibrotic bands, presence of diffuse lesions, predominant peripheral distribution) can accurately predict RT-PCR status.

Project description:Background CT may play a central role in the diagnosis and management of coronavirus disease 2019 (COVID-19) pneumonia. Purpose To perform a longitudinal study to analyze the serial CT findings over time in patients with COVID-19 pneumonia. Materials and Methods During January 16 to February 17, 2020, 90 patients (33 men, 57 women; mean age, 45 years) with COVID-19 pneumonia were prospectively enrolled and followed up until being discharged, death, or the end of the study. A total of 366 CT scans were acquired and reviewed by two groups of radiologists for the patterns and distribution of lung abnormalities, total CT scores, and number of zones involved. Those features were analyzed for temporal change. Results CT scores and number of zones involved progressed rapidly, peaked during illness days 6-11 (median CT score, 5; median number of zones involved, five), and were followed by persistence of high levels. The predominant pattern of abnormalities after symptom onset was ground-glass opacity (35 of 78 scans [45%] to 49 of 79 scans [62%] in different periods). The percentage of mixed pattern peaked on illness days 12-17 (30 of 78 scans [38%]) and became the second most predominant pattern thereafter. Pure ground-glass opacity was the most prevalent subtype of ground-glass opacity after symptom onset (20 of 50 scans [40%] to 20 of 28 scans [71%]). The percentage of ground-glass opacity with irregular linear opacity peaked on illness days 6-11 (14 of 50 scans [28%]) and became the second most prevalent subtype thereafter. The distribution of lesions was predominantly bilateral and subpleural. Sixty-six of the 70 patients discharged (94%) had residual disease on final CT scans (median CT score, 4; median number of zones involved, four), with ground-glass opacity (42 of 70 patients [60%]) and pure ground-glass opacity (31 of 42 patients [74%]) the most common pattern and subtype. Conclusion The extent of lung abnormalities at CT peaked during illness days 6-11. The temporal changes of the diverse CT manifestations followed a specific pattern, which might indicate the progression and recovery of the illness. © RSNA, 2020 Online supplemental material is available for this article.

Project description:The main objective of this work is to develop and evaluate an artificial intelligence system based on deep learning capable of automatically identifying, quantifying, and characterizing COVID-19 pneumonia patterns in order to assess disease severity and predict clinical outcomes, and to compare the prediction performance with respect to human reader severity assessment and whole lung radiomics. We propose a deep learning based scheme to automatically segment the different lesion subtypes in nonenhanced CT scans. The automatic lesion quantification was used to predict clinical outcomes. The proposed technique has been independently tested in a multicentric cohort of 103 patients, retrospectively collected between March and July of 2020. Segmentation of lesion subtypes was evaluated using both overlapping (Dice) and distance-based (Hausdorff and average surface) metrics, while the proposed system to predict clinically relevant outcomes was assessed using the area under the curve (AUC). Additionally, other metrics including sensitivity, specificity, positive predictive value and negative predictive value were estimated. 95% confidence intervals were properly calculated. The agreement between the automatic estimate of parenchymal damage (%) and the radiologists' severity scoring was strong, with a Spearman correlation coefficient (R) of 0.83. The automatic quantification of lesion subtypes was able to predict patient mortality, admission to the Intensive Care Units (ICU) and need for mechanical ventilation with an AUC of 0.87, 0.73 and 0.68 respectively. The proposed artificial intelligence system enabled a better prediction of those clinically relevant outcomes when compared to the radiologists' interpretation and to whole lung radiomics. In conclusion, deep learning lesion subtyping in COVID-19 pneumonia from noncontrast chest CT enables quantitative assessment of disease severity and better prediction of clinical outcomes with respect to whole lung radiomics or radiologists' severity score.

Project description:Coronavirus (COVID-19) was first observed in Wuhan, China, and quickly propagated worldwide. It is considered the supreme crisis of the present era and one of the most crucial hazards threatening worldwide health. Therefore, the early detection of COVID-19 is essential. The common way to detect COVID-19 is the reverse transcription-polymerase chain reaction (RT-PCR) test, although it has several drawbacks. Computed tomography (CT) scans can enable the early detection of suspected patients, however, the overlap between patterns of COVID-19 and other types of pneumonia makes it difficult for radiologists to diagnose COVID-19 accurately. On the other hand, deep learning (DL) techniques and especially the convolutional neural network (CNN) can classify COVID-19 and non-COVID-19 cases. In addition, DL techniques that use CT images can deliver an accurate diagnosis faster than the RT-PCR test, which consequently saves time for disease control and provides an efficient computer-aided diagnosis (CAD) system. The shortage of publicly available datasets of CT images, makes the CAD system's design a challenging task. The CAD systems in the literature are based on either individual CNN or two-fused CNNs; one used for segmentation and the other for classification and diagnosis. In this article, a novel CAD system is proposed for diagnosing COVID-19 based on the fusion of multiple CNNs. First, an end-to-end classification is performed. Afterward, the deep features are extracted from each network individually and classified using a support vector machine (SVM) classifier. Next, principal component analysis is applied to each deep feature set, extracted from each network. Such feature sets are then used to train an SVM classifier individually. Afterward, a selected number of principal components from each deep feature set are fused and compared with the fusion of the deep features extracted from each CNN. The results show that the proposed system is effective and capable of detecting COVID-19 and distinguishing it from non-COVID-19 cases with an accuracy of 94.7%, AUC of 0.98 (98%), sensitivity 95.6%, and specificity of 93.7%. Moreover, the results show that the system is efficient, as fusing a selected number of principal components has reduced the computational cost of the final model by almost 32%.

Dataset Information

COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

Publications

COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets