key: cord-029710-ythz9ax0
authors: Homayounieh, Fatemeh; Ebrahimian, Shadi; Babaei, Rosa; Karimi Mobin, Hadi; Zhang, Eric; Bizzo, Bernardo Canedo; Mohseni, Iman; Digumarthy, Subba R.; Kalra, Mannudeep K.
title: CT Radiomics, Radiologists and Clinical Information in Predicting Outcome of Patients with COVID-19 Pneumonia
date: 2020-07-23
journal: Radiol Cardiothorac Imaging
DOI: 10.1148/ryct.2020200322
sha: 
doc_id: 29710
cord_uid: ythz9ax0

PURPOSE: To compare prediction of disease outcome, severity, and patient triage in COVID-19 pneumonia with whole lung radiomics, radiologists’ interpretation, and clinical variables. METHODS: Our IRB-approved retrospective study included 315 adult patients (mean age 56 (21-100) years, 190 males, 125 females) with COVID-19 pneumonia who underwent non-contrast chest CT. All patients (inpatients, n=210; outpatients, n=105) were followed up for at least two-weeks to record disease outcome. Clinical variables such as presenting symptoms, laboratory data, peripheral oxygen saturation, and comorbid diseases were recorded. Two radiologists assessed each CT in consensus and graded the extent of pulmonary involvement (by percentage of involved lobe) and type of opacities within each lobe. We obtained radiomics for the entire lung and multiple logistic regression analyses with areas under the curve (AUC) as outputs were performed. RESULTS: Most patients (276/315,88%) recovered from COVID-19 pneumonia; 36/315 patients (11%) died and 3/315 patients (1%) remain admitted in the hospital. Radiomics differentiated chest CT in outpatient vs inpatient with an AUC of 0.84 (p<0.005), while radiologists’ interpretations of disease extent and opacity type had an AUC of 0.69 (p<0.0001). Whole lung radiomics were superior to the radiologists’ interpretation for predicting patient outcome in terms of ICU admission (AUC:0.75 vs 0.68) and death (AUC:0.81 vs 0.68) (p<0.002). Addition of clinical variables to radiomics improved the AUC to 0.84 for predicting ICU admission. CONCLUSION: Radiomics from non-contrast chest CT were superior to radiologists’ assessment of extent and type of pulmonary opacities in predicting COVID-19 pneumonia outcome, disease severity, and patient triage.

I n p r e s s I n p r e s s I n p r e s s Introduction Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), the seventh known coronavirus in humans, is an enveloped, single-strand RNA virus responsible for the global COronaVIrus Disease of 2019 pandemic since the beginning 2020 [1] . Millions confirmed cases in 187 countries within 5 months, the pandemic has taken a huge toll on health and economic status, particularly in the most vulnerable, developing countries such as Iran.

Although any individual can get COVID-19 infection regardless of age and gender, elderly and those with underlying comorbidities such as obesity, hypertension and diabetes are at higher risk of severe COVID-19 pneumonia, complications and multiorgan failure [2] . Reverse transcriptase polymerase chain reaction (RT-PCR) assay from nasopharyngeal swab or bronchoalveolar lavage is the preferred test for diagnosis of COVID-19 infection [3, 4] . In the first 10 days of infection, the RT-PCR assay for COVID-19 infection has lower sensitivity (60-70%) than in the later stage of infection [5] [6] [7] . Although chest CT images can display findings of early pneumonia, about 20% of chest CT do not show any findings [8] . Thus, many organizations recommend limiting chest CT to subjects with moderate to severe COVID-19 pneumonia or in those with unexplained deterioration of respiratory status [9] [10] [11] [12] .

In resource-starved sites with limited access to RT-PCR assays and in high risk patients with negative initial RT-PCR, chest CT is frequently used for diagnosis and severity assessment of COVID-19 pneumonia [13, 14] . Subjective grading for assessing disease severity from lobar extent and type of pulmonary opacities is time-consuming, and therefore, has limited clinical applications [15] [16] [17] [18] [19] [20] . Some studies have explored radiomics for screening and diagnosis COVID-I n p r e s s severity, and patient triage in COVID-19 pneumonia. We compared prediction of disease outcome, severity, and patient triage in COVID-19 pneumonia with whole lung radiomics, radiologists' interpretation, and clinical variables.

The institutional ethical board (IRB) approved our retrospective, Health Insurance Portability and Accountability Act (HIPAA)-compliant human subject study with waiver of informed consent from the study subjects. We have no financial disclosures pertaining to this manuscript.

Our institution received research grants from Siemens Healthineers, Lunit Inc., and Riverain

Tech. for unrelated projects.

We identified 350 consecutive adult patients who presented with symptoms compatible with COVID-19 pneumonia and underwent non-contrast chest CT in a teaching hospital in Tehran, Iran, between February 20, 2020 and April 10, 2020. Inpatients: The recorded clinical variables for inpatients included age, gender, presenting symptoms (such as fever, chills, fatigue, myalgia, cough, sputum production, sore throat, hemoptysis, chest pain, shortness of breath, headache, anorexia, nausea and vomiting, diarrhea, and loss of consciousness), symptomatic days before hospital admission, temperature and peripheral capillary oxygen saturation (SpO2) on hospital admission, and presence of any comorbidities and immunodeficiencies. Results of the following laboratory tests were recorded: total white blood count, differential white blood counts, platelets count, C-reactive protein (CRP), erythrocyte sedimentation rate (ESR) and lactate dehydrogenase (LDH) level.

Information pertaining to patient outcome (discharged, deceased, or still admitted and under treatment at the time of data analysis) was recorded.

Outpatients: Patient symptoms, comorbidities, and past medical history for outpatients were not available due to lack of electronic medical records. Results of RT-PCR assays, when performed, were recorded for all patients. All patients (outpatients and inpatients) had a two-week tele-visit following their discharge or outpatient visit.

We excluded 20 inpatients and 15 outpatients due to presence of extensive motion artifacts on their chest CT images (13 and 6 patients, respectively), co-existing or atypical CT findings suggestive of other abnormalities (5 and 3 patients, respectively), incomplete CT datasets (2 and 3, respectively), and lack of follow-up (3 patients in outpatient setting). Thus, the final sample size included 315 adult patients (210 inpatients and 105 outpatients; mean age 56 years (21 to 100); 190 men, 125 women) who met our inclusion and exclusion criteria ( Figure 1 ).

All included patients had a standard-of-care, chest CT examination without oral and intravenous 

Two experienced thoracic radiologists (S.D. with 16-year experience, M.K. with 14-year experience) reviewed each CT examination in consensus (MicroDicom DICOM Viewer, Sofia, Bulgaria) in lung windows (at modifiable window width 1500 HU, window level -600 HU). The I n p r e s s existing or atypical CT findings (n= 8), and incomplete CT image series (n= 5). In consensus, they recorded the type of pulmonary opacities (ground-glass, mixed ground-glass and consolidation, consolidation, organizing pneumonia (reverse halo sign with ground-glass opacity surrounded by consolidation), nodular, or ground-glass with septal thickening (crazy paving appearance)) and the percentage of each lobe (right upper, right middle, right lower, left upper, and left lower) affected by the opacities (score 0: 0% involvement; score 1: <5% involvement; score 2: 5-25% involvement; score 3: 26-50% involvement; score 4: 51-75% involvement; score 5: >75% lobar involvement) [15, 23] . Total lung involvement (labeled as subjective severity score) was estimated by adding the scores for all lobes (minimum score 0; maximum score 25).

We classified this subjective severity score or total lung involvement into two groups (extensive: total score ≥15; non-extensive: total score <15). CT findings were classified into typical, intermediate, atypical and negative based on the published guidelines for COVID-19 pneumonia (Table 1 ) [24] .

Radiomics were estimated from the 2 mm image series. First, we segmented both lungs (entire lung volume) with a semiautomatic approach as Radiomics 3D Slicer Extension program [25] .

Regions beyond the lung were edited out to exclude mediastinal, hilar, or pleural structures and abnormalities from the lung volumes (F.H., 2-year postdoctoral research experience in radiology). Then, we derived a total of 1690 radiomics over the segmented entire lung volumes which included both the abnormal and normal lung parenchyma. These radiomics included first order (n=18), shape (n=17), gray level co-occurrence matrix (GLCM) (n=24), gray level run length matrix (GLRLM) (n=16), gray level size zone matrix (GLSZM) (n=16), neighboring gray I n p r e s s tone difference matrix (NGTDM) (n=5), gray level dependence matrix (GLDM) (n=14) features (total n=110) as described extensively in prior publications [26] . Squares, square roots, logarithms, and exponentials of these features (n=372) were also obtained in addition to 3-D wavelet transform (multidimensional decomposition of image -multidimensional signal processing) parameters (n=744) and Log with five (0-4 mm) sigma levels (n=465) of abovementioned features.

Data were analyzed with Microsoft EXCEL (Microsoft Inc., Redmond, Washington) and R Statistical Computing (https://www.R-project.org, R Foundation for Statistical Computing, Vienna, Austria, accessed on 4.15.2020). We performed multiple logistic regression tests for data analyses and obtained both the area under the curve (AUC) and p-values as outputs. The multiple logistic regression used a stepwise procedure and displayed AUCs and p-values for each combination of input variables (no variables were excluded from the model). From these, we identified the combination of input variables with best AUCs. For prediction of type of pulmonary opacities with radiomics, we classified the opacities into two groups (group 1: ground-glass opacities; group 2: other types of opacities including consolidation, nodular, ground-glass opacities mixed with consolidation or interlobular septal thickening). P-values < 0.05 were considered statistically significant.

Of the 210 inpatients, 115 (55%) patients had positive RT-PCR assays, 59 (28%) did not have any RT-PCR, and 36 (17%) had a negative single RT-PCR assay. Just 2 patients in outpatient setting had positive RT-PCR and the rest were not tested due to shortage of test kits and a large number of suspected patients with COVID-19 infection.

Of 315 patients included in our study, 227 patients (72%) had subjective severity score < 15 

Among the 115 inpatients with positive RT-PCR assay for COVID-19 pneumonia, 40 patients (40/115; 35%) had extensive pulmonary opacities with severity score ≥15 and 75 patients (75/115; 65%) patients had non-extensive pulmonary involvement and a severity score <15.

Radiomics differentiated these two groups with an AUC of 0.93 (95% CI AUC 0.89-0.94, p value< 0.004) ( Table 3) [15] [16] [17] [18] [19] [20] .

Use of chest CT-based radiomics has been described for differentiating COVID-19 pneumonia from other pneumonias [21, 22] . Chen et al. developed a diagnostic model based on clinical features and radiological semantic for differentiating COVID-19 pneumonia [22] . They trained their model with radiomics derived from lung opacities rather than the entire lung volume used in our study. Radiomics from pulmonary opacities can be tedious (with manual segmentation), subjective, and thus, prone to interobserver variations. In comparison, semiautomatic entire lung I n p r e s s also obtaining radiomics information from both the normal and abnormal lung parenchyma.

Likewise, the entire lung radiomics also account for other co-existing pulmonary abnormalities such as emphysema and atelectasis which can reduce the functional lung volume. A recent study from Colombi et al. reported that quantification of well-aerated pulmonary parenchyma on hospital admission chest CT could predict ICU admission and death related to COVID-19 pneumonia [28] .

The ability of whole lung radiomics to differentiate the type of pulmonary opacities can be explained on the basis of differences in CT numbers based on the type of pulmonary opacities (for example, ground-glass versus consolidation versus crazy-paving pattern). Likewise, success of radiomics for differentiating disease severity is likely related to changes in distribution of CT voxel values in patients with less or more extensive pulmonary opacities. Several prior studies have reported that radiomics help predict treatment response and prognosis in several malignancies including lung cancer [29] [30] [31] [32] . In fact, radiomics signatures of more heterogenous malignant lesions are associated with poor outcome. Although its application in an infectious disease like viral pneumonia such as in our study has not been assessed, the ability of radiomics to assess and quantify attenuation changes related to COVID-19 pneumonia like in patients with cancer explains why radiomics were useful for predicting disease outcome in our patient population.

Although prior studies have reported on the ability of visual severity score of COVID-19 pneumonia on chest CT [16, 18, 20] , we found that such qualitative assessment was not as useful as radiomics in predicting ICU admission or patient outcome (recovery versus death). This may be related to difficulty in differentiating various opacity types and assigning scores based on percentage of individual lung lobe involved by pulmonary opacities. Although not formally I n p r e s s quantified in prior studies [16, 18, 20] or in our study, it is challenging to assign reliable and reproducible scores based on difference of 1% in term of lung lobe involvement. For example, less than 4% lung lobe involvement gets a score of 1 and 5% is categorized with a score of 2.

Such scoring is also not part of the clinical interpretation of chest CT. The inconsistencies in scoring lung involvement from visual inspection may explain why radiologists significantly underperformed as compared to whole lung radiomics.

The main implication of our study is the demonstration of use of open access whole lung segmentation and radiomics tool in predicting patients requiring ICU admission and differentiating those with favorable and unfavorable outcome of COVID-19 pneumonia. Along with the clinical variables, whole lung radiomics can be a powerful tool for assessing diffuse pulmonary parenchymal diseases such as the viral pneumonia assessed in our study. Such prediction can help in allocation and planning of resources in high prevalence diseases such as the current COVID-19 pandemic. We believe that our study provides evidence for integration of information from whole lung radiomics into radiology reports. The automatic whole lung segmentation ability available in both open access and commercial image processing platforms, can avoid or minimize any effort from radiologists in obtaining radiomics information. However, institutions would require datasets such as in our study to establish a training model so that

individual prospective cases can be tested against such local models to account for local variations in CT scanners, scan parameters and patient characteristics. For such integration to happen, both the radiologists and referring physicians need to understand the principles, strengths and limitations of radiomics so that meaningful inferences can be drawn from a large amount of quantitative information generated from radiomics.

One of the limitations of our retrospective study was the lack of RT-PCR confirmation availability for all included cases due to the shortage of test kits in an extremely resource constrained country with high prevalence of COVID-19 pneumonia. However, neither radiomics nor subjective radiologist evaluation could differentiate between patients deemed to have COVID-19 pneumonia with or without RT-PCR. A recent study with 1014 patients reported positive rates of 88% for chest CT and 59% for RT-PCR assay for the diagnosis of suspected COVID-19, and a sensitivity of 97% for CT with RT-PCR as a reference standard [13] . Another limitation of our study pertains to the fact that some patients may have been admitted to the hospital based on severity of symptoms, other comorbidities (such as immunodeficiencies) or positive CT findings rather than an extensive lung changes related to COVID-19 pneumonia. In such cases neither radiomics nor subjective severity scores can reliably predict hospitalization.

We also included patients with negative RT-PCR but CT findings typical of COVID-19 pneumonia in our study. He et al. has reported on role of chest CT for clinically suspected COVID-19 pneumonia in patients with negative RT-PCR [33] . Prior studies have also included negative RT-PCR cases in part of their entire datasets [14] . Another limitation of our study is the lack of complete list of clinical variables for outpatients due to lack of electronic medical records in the teaching hospital in Tehran, Iran. Our results may not be generalizable due to use of single CT scanner and data from single institution. Further studies with multi-scanner and multicenter data will be necessary to validate our study results.

In conclusion, whole lung radiomics derived from non-contrast chest CT can help identify patients in need of ICU admission and predict outcome in patients with COVID-19 pneumonia.

Whole lung radiomics were superior to subjective assessment of radiologists in predicting patient 

COVID-19): Epidemiology, Clinical Spectrum and Implications for the Cardiovascular Clinician. (American College of Cardiology website)

Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet

Detection of 2019 novel coronavirus (2019-nCoV) by real-time RT-PCR

Virological assessment of hospitalized patients with COVID-2019

What is the role of imaging and biomarkers within the current testing strategy for the diagnosis of Covid-19?

Analysis and Prediction of False Negative Results for SARS-CoV-2 Detection with Pharyngeal Swab Specimen in COVID-19 Patients: A Retrospective Study

Clinical Characteristics of Coronavirus Disease 2019 in China

Interim Clinical Guidance for Management of Patients with Confirmed Coronavirus Disease (COVID-19)

ACR recommendations for the use of Chest Radiography and Computed Tomography (CT) for Suspected COVID-19 Infection

COVID-19) clinical radiology resources

Clinical Management of COVID-19 (Spanish)

Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases

Chest CT Features of COVID-19 in

Chest CT findings in coronavirus disease-19 (COVID-19): Relationship to duration of infection

The clinical and chest CT features associated with severe and critical COVID-19 pneumonia

Temporal Changes of CT Findings in 90 Patients with COVID-19 Pneumonia: A Longitudinal Study

Coronavirus disease 2019: initial chest CT findings

CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19)

Relation Between Chest CT findings and clinical conditions of Coronavirus Disease (COVID-19) pneumonia: A Multicenter Study

CT radiomics can help screen the Coronavirus disease 2019 (COVID-19): a preliminary study

A diagnostic model for coronavirus disease 2019 (COVID-19) based on radiological semantic and clinical features: a multi-center study

Time course of cung changes on chest CT During recovery from 2019 novel coronavirus (COVID-19) pneumonia. Radiology

Radiological Society of North America Expert Consensus Statement on Reporting Chest CT Findings Related to COVID-19. Endorsed by the Society of Thoracic Radiology, the American College of Radiology, and RSNA

Well-aerated Lung on Admitting Chest CT to Predict Adverse Outcome in COVID-19 Pneumonia

Feasibility of CT radiomics to predict treatment response of individual liver metastases in esophagogastric cancer patients

Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy

Novel Quantitative Imaging for Predicting Response to Therapy: Techniques and Clinical Applications

Radiomics predicts survival of patients with advanced non-small cell lung cancer undergoing PD-1 blockade using Nivolumab

Diagnostic performance between CT and initial real-time RT-PCR for clinically