Study of Thoracic CT in COVID-19: The STOIC Project

Development and multicentric external validation of a prognostic COVID-19 severity model based on thoracic CT

BACKGROUND

Risk stratification of COVID-19 patients can support therapeutic decisions, planning and resource allocation in the hospital. In times of high incidence, a prognostic model based on data efficiently retrieved from one source can enable fast decision support.

METHODS

A model was developed to identify patients at risk of developing severe COVID-19 within one month based on their age, sex and imaging features extracted from the thoracic computed tomography (CT). The model was trained on publicly available data from the Study of Thoracic CT in COVID-19 (STOIC) challenge and validated on unseen data from the same study and an external, multicentric dataset. The model, trained on data acquired before any variant of concern dominated, was assessed separately on data collected at later stages of the pandemic when the delta and omicron variants were most prevalent.

RESULTS

A logistic regression based on handcrafted features was found to perform on par with a direct deep learning approach, and the former was selected for simplicity. Volumetric and intensity-based features of lesions and healthy lung parenchyma proved most predictive, in addition to patient age and sex. The model reached an area under the curve of 0.78 on the challenge test set and 0.74 on the external test set. The performance did not drop for the subset acquired at a later stage of the pandemic.

CONCLUSIONS

A logistic regression utilizing features from thoracic CT and its metadata can provide rapid decision support by estimating short-term COVID-19 severity. Its stable performance underscores its potential for real-world clinical integration. By enabling rapid risk stratification using readily available imaging data, this approach can support early clinical decision-making, optimize resource allocation, and improve patient management, particularly during surges in COVID-19 cases. Furthermore, this study provides a foundation for future research on prognostic modelling in respiratory infections.

Artificial intelligence in respiratory pandemics-ready for disease X? A scoping review

OBJECTIVES

This study aims to identify repeated previous shortcomings in medical imaging data collection, curation, and AI-based analysis during the early phase of respiratory pandemics. Based on the results, it seeks to highlight essential steps for improving future pandemic preparedness.

MATERIALS AND METHODS

We searched PubMed/MEDLINE, Scopus, and Cochrane Reviews for articles published from January 1, 2000, to December 31, 2021, using the terms "imaging" or "radiology" or "radiography" or "CT" or "x-ray" combined with "SARS," "MERS," "H1N1," or "COVID-19." WHO and CDC Databases were searched for case definitions.

RESULTS

Over the last 20 years, the world faced several international health emergencies caused by respiratory diseases such as SARS, MERS, H1N1, and COVID-19. During the same period, major technological advances enabled the analysis of vast amounts of imaging data and the continual development of artificial intelligence algorithms to support radiological diagnosis and prognosis. Timely availability of data proved critical, but so far, data collection attempts were initialized only as individual responses to each outbreak, leading to long delays and hampering unified guidelines and data-driven technology to support the management of pandemic outbreaks. Our findings highlight the multifaceted role of imaging in the early stages of SARS, MERS, H1N1, and COVID-19, and outline possible actions for advancing future pandemic preparedness.

CONCLUSIONS

Advancing international cooperation and action on these topics is essential to create a functional, effective, and rapid counteraction system to future respiratory pandemics exploiting state of the art imaging and artificial intelligence.

KEY POINTS

Question What has been the role of radiological data for diagnosis and prognosis in early respiratory pandemics and what challenges were present? Findings International cooperation is essential to developing an effective rapid response system for future respiratory pandemics using advanced imaging and artificial intelligence. Clinical relevance Strengthening global collaboration and leveraging cutting-edge imaging and artificial intelligence are crucial for developing rapid and effective response systems. This approach is essential for improving patient outcomes and managing future respiratory pandemics more effectively.

Leveraging deep transfer learning and explainable AI for accurate COVID-19 diagnosis: Insights from a multi-national chest CT scan study

The COVID-19 pandemic has emerged as a global health crisis, impacting millions worldwide. Although chest computed tomography (CT) scan images are pivotal in diagnosing COVID-19, their manual interpretation by radiologists is time-consuming and potentially subjective. Automated computer-aided diagnostic (CAD) frameworks offer efficient and objective solutions. However, machine or deep learning methods often face challenges in their reproducibility due to underlying biases and methodological flaws. To address these issues, we propose XCT-COVID, an explainable, transferable, and reproducible CAD framework based on deep transfer learning to predict COVID-19 infection from CT scan images accurately. This is the first study to develop three distinct models within a unified framework by leveraging a previously unexplored large dataset and two widely used smaller datasets. We employed five known convolutional neural network architectures, both with and without pretrained weights, on the larger dataset. We optimized hyperparameters through extensive grid search and 5-fold cross-validation (CV), significantly enhancing the model performance. Experimental results from the larger dataset showed that the VGG16 architecture (XCT-COVID-L) with pretrained weights consistently outperformed other architectures, achieving the best performance, on both 5-fold CV and independent test. When evaluated with the external datasets, XCT-COVID-L performed well with data with similar distributions, demonstrating its transferability. However, its performance significantly decreased on smaller datasets with lower-quality images. To address this, we developed other models, XCT-COVID-S1 and XCT-COVID-S2, specifically for the smaller datasets, outperforming existing methods. Moreover, eXplainable Artificial Intelligence (XAI) analyses were employed to interpret the models' functionalities. For prediction and reproducibility purposes, the implementation of XCT-COVID is publicly accessible at https://github.com/cbbl-skku-org/XCT-COVID/.

MedLSAM: Localize and segment anything model for 3D CT images

Recent advancements in foundation models have shown significant potential in medical image analysis. However, there is still a gap in models specifically designed for medical image localization. To address this, we introduce MedLAM, a 3D medical foundation localization model that accurately identifies any anatomical part within the body using only a few template scans. MedLAM employs two self-supervision tasks: unified anatomical mapping (UAM) and multi-scale similarity (MSS) across a comprehensive dataset of 14,012 CT scans. Furthermore, we developed MedLSAM by integrating MedLAM with the Segment Anything Model (SAM). This innovative framework requires extreme point annotations across three directions on several templates to enable MedLAM to locate the target anatomical structure in the image, with SAM performing the segmentation. It significantly reduces the amount of manual annotation required by SAM in 3D medical imaging scenarios. We conducted extensive experiments on two 3D datasets covering 38 distinct organs. Our findings are twofold: (1) MedLAM can directly localize anatomical structures using just a few template scans, achieving performance comparable to fully supervised models; (2) MedLSAM closely matches the performance of SAM and its specialized medical adaptations with manual prompts, while minimizing the need for extensive point annotations across the entire dataset. Moreover, MedLAM has the potential to be seamlessly integrated with future 3D SAM models, paving the way for enhanced segmentation performance. Our code is public at https://github.com/openmedlab/MedLSAM.

The STOIC2021 COVID-19 AI challenge: Applying reusable training methodologies to private data

Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.

Deep learning reveals lung shape differences on baseline chest CT between mild and severe COVID-19: A multi-site retrospective study

Severe COVID-19 can lead to extensive lung disease causing lung architectural distortion. In this study we employed machine learning and statistical atlas-based approaches to explore possible changes in lung shape among COVID-19 patients and evaluated whether the extent of these changes was associated with COVID-19 severity. On a large multi-institutional dataset (N = 3443), three different populations were defined; a) healthy (no COVID-19), b) mild COVID-19 (no ventilator required), c) severe COVID-19 (ventilator required), and the presence of lung shape differences between them were explored using baseline chest CT. Significant lung shape differences were observed along mediastinal surfaces of the lungs across all severity of COVID-19 disease. Additionally, differences were seen on basal surfaces of the lung when compared between healthy and severe COVID-19 patients. Finally, an AI model (a 3D residual convolutional network) characterizing these shape differences coupled with lung infiltrates (ground-glass opacities and consolidation regions) was found to be associated with COVID-19 severity.

Opportunistic Screening for Coronary Artery Disease: An Untapped Population Health Resource

BACKGROUND

Coronary artery disease is the leading cause of death in the United States. At-risk asymptomatic adults are eligible for screening with electrocardiogram-gated coronary artery calcium (CAC) CT, which aids in risk stratification and management decision-making. Incidental CAC (iCAC) is easily quantified on chest CT in patients imaged for noncardiac indications; however, radiologists do not routinely report the finding.

OBJECTIVE

To determine the clinical significance of CAC identified incidentally on routine chest CT performed for noncardiac indications.

DESIGN

An informationist developed search strategies in MEDLINE, Embase, and SCOPUS, and two reviewers independently screened results at both the abstract and full text levels. Data extracted from eligible articles included age, rate of iCAC identification, radiologist reporting frequency, impact on downstream medical management, and association of iCAC with patient outcomes.

RESULTS

From 359 unique citations, 83 research publications met inclusion criteria. The percentage of patients with iCAC ranged from 9% to 100%. Thirty-one investigations measured association(s) between iCAC and cardiovascular morbidity and mortality, and 29 identified significant correlations, including nonfatal myocardial infarction, fatal myocardial infarction, major adverse cardiovascular event, cardiovascular death, and all-cause death. iCAC was present in 20% to 100% of the patients in these cohorts, but when present, iCAC was reported by radiologists in only 31% to 44% of cases. Between 18% and 77% of patients with iCAC were not on preventive medications in studies that reported these data. Seven studies measured the effect of reporting on guideline directed medical therapy, and 5 (71%) reported an increase in medication prescriptions after diagnosis of iCAC, with one confirming reductions in low-density lipoprotein levels. Twelve investigations reported good concordance between CAC grade on noncardiac CT and Agatston score on electrocardiogram-gated cardiac CT, and 10 demonstrated that artificial intelligence tools can reliably calculate an Agatston score on noncardiac CT.

CONCLUSION

A body of evidence demonstrates that patients with iCAC on routine chest CT are at risk for cardiovascular disease events and death, but they are often undiagnosed. Uniform reporting of iCAC in the chest CT impression represents an opportunity for radiology to contribute to early identification of high-risk individuals and potentially reduce morbidity and mortality. AI tools have been validated to calculate Agatston score on routine chest CT and hold the best potential for facilitating broad adoption.

Radiologic Abnormalities in Prolonged SARS-CoV-2 Infection: A Systematic Review

We systematically reviewed radiological abnormalities in patients with prolonged SARS-CoV-2 infection, defined as persistently positive polymerase chain reaction (PCR) results for SARS-CoV-2 for > 21 days, with either persistent or relapsed symptoms. We extracted data from 24 patients (median age, 54.5 [interquartile range, 44-64 years]) reported in the literature and analyzed their representative CT images based on the timing of the CT scan relative to the initial PCR positivity. Our analysis focused on the patterns and distribution of CT findings, severity scores of lung involvement on a scale of 0-4, and the presence of migration. All patients were immunocompromised, including 62.5% (15/24) with underlying lymphoma and 83.3% (20/24) who had received anti-CD20 therapy within one year. Median duration of infection was 90 days. Most patients exhibited typical CT appearance of coronavirus disease 19 (COVID-19), including ground-glass opacities with or without consolidation, throughout the follow-up period. Notably, CT severity scores were significantly lower during ≤ 21 days than during > 21 days (P < 0.001). Migration was observed on CT in 22.7% (5/22) of patients at ≤ 21 days and in 68.2% (15/22) to 87.5% (14/16) of patients at > 21 days, with rare instances of parenchymal bands in previously affected areas. Prolonged SARS-CoV-2 infection usually presents as migrating typical COVID-19 pneumonia in immunocompromised patients, especially those with impaired B-cell immunity.

Oscillometry Longitudinal Data on COVID-19 Acute Respiratory Syndrome Treated with Non-Invasive Respiratory Support

Background: Oscillometry allows for the non-invasive measurements of lung mechanics. In COVID-19 ARDS patients treated with Non-Invasive Oxygen Support (NI-OS), we aimed to (1) observe lung mechanics at the patients' admission and their subsequent changes, (2) compare lung mechanics with clinical and imaging data, and (3) evaluate whether lung mechanics helps to predict clinical outcomes. Methods: We retrospectively analyzed the data from 37 consecutive patients with moderate-severe COVID-19 ARDS. Oscillometry was performed on their 1st, 4th, and 7th day of hospitalization. Resistance (R5), reactance (X5), within-breath reactance changes (ΔX5), and the frequency dependence of the resistance (R5-R19) were considered. Twenty-seven patients underwent computed tomographic pulmonary angiography (CTPA): collapsed, poorly aerated, and normally inflated areas were quantified. Adverse outcomes were defined as intubation or death. Results: Thirty-two patients were included in this study. At the first measurement, only 44% of them had an abnormal R5 or X5. In total, 23 patients had measurements performed on their 3rd day and 7 on their 7th day of hospitalization. In general, their R5, R5-R19, and ΔX decreased with time, while their X5 increased. Collapsed areas on the CTPA correlated with the X5 z-score (ρ = -0.38; p = 0.046), while poorly aerated areas did not. Seven patients had adverse outcomes but did not present different oscillometry parameters on their 1st day of hospitalization. Conclusions: Our study confirms the feasibility of oscillometry in critically ill patients with COVID-19 pneumonia undergoing NI-OS. The X5 z-scores indicates collapsed but not poorly aerated lung areas in COVID-19 pneumonia. Our data, which show a severe impairment of gas exchange despite normal reactance in most patients with COVID-19 ARDS, support the hypothesis of a composite COVID-19 ARDS physiopathology.

Assessing the impact of structured reporting on learning how to report lung cancer staging CT: A triple cohort study on inexperienced readers

PURPOSE

To assess the clinical utility of chest computed tomography (CT) reports for non-small-cell lung cancer (NSCLC) staging generated by inexperienced readers using structured reporting (SR) templates from the Royal College of Radiologists (RCR-SR) and the Italian Society of Medical and Interventional Radiology (SIRM-SR), compared to traditional non-systematic reports (NSR).

METHODS

In a cohort of 30 NSCLC patients, six third-year radiology residents reported CT examinations in two 2-month-apart separate sessions using NSR in the first and NSR, RCR-SR, or SIRM-SR in the second. Couples of expert radiologists and thoracic oncologists in consensus evaluated completeness, accuracy, and clarity. All the quality indicators were expressed on a 100-point scale. The Wilcoxon signed ranks, and Wilcoxon-Mann Whitney tests were used for statistical analyses.

RESULTS

Results showed significantly higher completeness for RCR-SR (90 %) and SIRM-SR (100 %) compared to NSR (70 %) in the second session (all p < 0.001). SIRM-SR demonstrated superior accuracy (70 % vs. 55 %, p < 0.001) over NSR, while RCR-SR and NSR accuracy did not significantly differ (60 % vs. 62.5 %, p = 0.06). In the second session, RCR-SR and SIRM-SR surpassed NSR in completeness, accuracy, and clarity (all p < 0.001, except p = 0.04 for accuracy between RCR-SR and NSR). SIRM-SR outperformed RCR-SR in completeness (100 % vs. 90 %, p < 0.001) and accuracy (70 % vs. 62.5 %, p = 0.002), with equivalent clarity (90 % for both, p = 0.27).

CONCLUSIONS

Inexperienced readers using RCR-SR and SIRM-SR demonstrated high-quality reporting, indicating their potential in radiology residency programs to enhance reporting skills for NSCLC staging and effective interaction with all the physicians involved in managing NSCLC patients.

Validation of Diagnostic Accuracy and Disease Severity Correlation of Chest Computed Tomography Severity Scores in Patients with COVID-19 Pneumonia

The aim of our study was to establish and compare the diagnostic accuracy and clinical applicability of published chest CT severity scoring systems used for COVID-19 pneumonia assessment and to propose the most efficient CT scoring system with the highest diagnostic performance and the most accurate prediction of disease severity. This retrospective study included 218 patients with PCR-confirmed SARS-CoV-2 infection and chest CT. Two radiologists blindly evaluated CT scans and calculated nine different CT severity scores (CT SSs). The diagnostic validity of CT SSs was tested by ROC analysis. Interobserver agreement was excellent (intraclass correlation coefficient: 0.982-0.995). The predominance of either consolidations or a combination of consolidations and ground-glass opacities (GGOs) was a predictor of more severe disease (both p < 0.005), while GGO prevalence alone was not. Correlation between all CT SSs was high, ranging from 0.848 to 0.971. CT SS 30 had the highest diagnostic accuracy (AUC = 0.805) in discriminating mild from severe COVID-19 disease compared to all the other proposed scoring systems (AUC range 0.755-0.788). In conclusion, CT SS 30 achieved the highest diagnostic accuracy in predicting the severity of COVID-19 disease while maintaining simplicity, reproducibility, and applicability in complex clinical settings.

Development and external validation of a prediction model for the transition from mild to moderate or severe form of COVID-19

OBJECTIVES

COVID-19 pandemic seems to be under control. However, despite the vaccines, 5 to 10% of the patients with mild disease develop moderate to critical forms with potential lethal evolution. In addition to assess lung infection spread, chest CT helps to detect complications. Developing a prediction model to identify at-risk patients of worsening from mild COVID-19 combining simple clinical and biological parameters with qualitative or quantitative data using CT would be relevant to organizing optimal patient management.

METHODS

Four French hospitals were used for model training and internal validation. External validation was conducted in two independent hospitals. We used easy-to-obtain clinical (age, gender, smoking, symptoms' onset, cardiovascular comorbidities, diabetes, chronic respiratory diseases, immunosuppression) and biological parameters (lymphocytes, CRP) with qualitative or quantitative data (including radiomics) from the initial CT in mild COVID-19 patients.

RESULTS

Qualitative CT scan with clinical and biological parameters can predict which patients with an initial mild presentation would develop a moderate to critical form of COVID-19, with a c-index of 0.70 (95% CI 0.63; 0.77). CT scan quantification improved the performance of the prediction up to 0.73 (95% CI 0.67; 0.79) and radiomics up to 0.77 (95% CI 0.71; 0.83). Results were similar in both validation cohorts, considering CT scans with or without injection.

CONCLUSION

Adding CT scan quantification or radiomics to simple clinical and biological parameters can better predict which patients with an initial mild COVID-19 would worsen than qualitative analyses alone. This tool could help to the fair use of healthcare resources and to screen patients for potential new drugs to prevent a pejorative evolution of COVID-19.

CLINICAL TRIAL REGISTRATION

NCT04481620.

CLINICAL RELEVANCE STATEMENT

CT scan quantification or radiomics analysis is superior to qualitative analysis, when used with simple clinical and biological parameters, to determine which patients with an initial mild presentation of COVID-19 would worsen to a moderate to critical form.

KEY POINTS

• Qualitative CT scan analyses with simple clinical and biological parameters can predict which patients with an initial mild COVID-19 and respiratory symptoms would worsen with a c-index of 0.70. • Adding CT scan quantification improves the performance of the clinical prediction model to an AUC of 0.73. • Radiomics analyses slightly improve the performance of the model to a c-index of 0.77.

Multivariable Risk Modelling and Survival Analysis with Machine Learning in SARS-CoV-2 Infection

AIM

To evaluate the performance of a machine learning model based on demographic variables, blood tests, pre-existing comorbidities, and computed tomography(CT)-based radiomic features to predict critical outcome in patients with acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

METHODS

We retrospectively enrolled 694 SARS-CoV-2-positive patients. Clinical and demographic data were extracted from clinical records. Radiomic data were extracted from CT. Patients were randomized to the training (80%, n = 556) or test (20%, n = 138) dataset. The training set was used to define the association between severity of disease and comorbidities, laboratory tests, demographic, and CT-based radiomic variables, and to implement a risk-prediction model. The model was evaluated using the C statistic and Brier scores. The test set was used to assess model prediction performance.

RESULTS

Patients who died (n = 157) were predominantly male (66%) over the age of 50 with median (range) C-reactive protein (CRP) = 5 [1, 37] mg/dL, lactate dehydrogenase (LDH) = 494 [141, 3631] U/I, and D-dimer = 6.006 [168, 152.015] ng/mL. Surviving patients (n = 537) had median (range) CRP = 3 [0, 27] mg/dL, LDH = 484 [78, 3.745] U/I, and D-dimer = 1.133 [96, 55.660] ng/mL. The strongest risk factors were D-dimer, age, and cardiovascular disease. The model implemented using the variables identified using the LASSO Cox regression analysis classified 90% of non-survivors as high-risk individuals in the testing dataset. In this sample, the estimated median survival in the high-risk group was 9 days (95% CI; 9-37), while the low-risk group did not reach the median survival of 50% (p < 0.001).

CONCLUSIONS

A machine learning model based on combined data available on the first days of hospitalization (demographics, CT-radiomics, comorbidities, and blood biomarkers), can identify SARS-CoV-2 patients at risk of serious illness and death.

Pleuropulmonary Manifestations of Vacuoles, E1 Enzyme, X-Linked, Autoinflammatory, Somatic (VEXAS) Syndrome

BACKGROUND

The vacuoles, E1 enzyme, X-linked, autoinflammatory, somatic (VEXAS) syndrome is a newly identified autoinflammatory disorder related to somatic UBA1 mutations. Up to 72% of patients may show lung involvement.

RESEARCH QUESTION

What are the pleuropulmonary manifestations in VEXAS syndrome?

STUDY DESIGN AND METHODS

One hundred fourteen patients were included in the French cohort of VEXAS syndrome between November 2020 and May 2021. Each patient included in the study who had an available chest CT scan was discussed in an adjudication multidisciplinary team and classified as showing potentially pleuropulmonary-specific involvement of VEXAS syndrome or others.

RESULTS

Fifty-one patients had a CT scan available for review and 45 patients (39%) showed pleuropulmonary abnormalities on chest CT scan that were considered related to VEXAS syndrome after adjudication. Most patients were men (95%) with a median age 67.0 years at the onset of symptoms. Among these 45 patients, 44% reported dyspnea and 40% reported cough. All 45 patients showed lung opacities on chest CT scan (including ground-glass opacities [87%], consolidations [49%], reticulation [38%], and septal lines [51%]) and 53% of patients showed pleural effusion. Most patients showed improvement with prednisone, but usually required > 20 mg/d. The main clinical and biological features as well the median survival did not differ between the 45 patients with pleuropulmonary involvement and the rest of the cohort, suggesting that the prevalence of pleuropulmonary involvement might have been underdiagnosed in the rest of the cohort.

INTERPRETATION

Pulmonary manifestations are frequent in VEXAS syndrome, but rarely are at the forefront. The initial outcome is favorable with prednisone and does not seem to lead to pulmonary fibrosis.

Current and Emerging Knowledge in COVID-19

COVID-19 has emerged as a pandemic leading to a global public health crisis of unprecedented morbidity. A comprehensive insight into the imaging of COVID-19 has enabled early diagnosis, stratification of disease severity, and identification of potential sequelae. The evolution of COVID-19 can be divided into early infectious, pulmonary, and hyperinflammatory phases. Clinical features, imaging features, and management are different among the three phases. In the early stage, peripheral ground-glass opacities are predominant CT findings, and therapy directly targeting SARS-CoV-2 is effective. In the later stage, organizing pneumonia or diffuse alveolar damage pattern are predominant CT findings and anti-inflammatory therapies are more beneficial. The risk of severe disease or hospitalization is lower in breakthrough or Omicron variant infection compared with nonimmunized or Delta variant infections. The protection rates of the fourth dose of mRNA vaccination were 34% and 67% against overall infection and hospitalizations for severe illness, respectively. After acute COVID-19 pneumonia, most residual CT abnormalities gradually decreased in extent, but they may remain as linear or multifocal reticular or cystic lesions. Advanced insights into the pathophysiologic and imaging features of COVID-19 along with vaccine benefits have improved patient care, but emerging knowledge of post-COVID-19 condition, or long COVID, also presents radiology with new challenges.

Can a chest HRCT-based crash course on COVID-19 cases make inexperienced thoracic radiologists readily available to face the next pandemic?

OBJECTIVE

To test the inter-reader agreement in assessing lung disease extent, HRCT signs, and Radiological Society of North America (RSNA) categorization between a chest-devoted radiologist (CR) and two HRCT-naïve radiology residents (RR1 and RR2) after the latter attended a COVID-19-based chest high-resolution computed tomography (HRCT) "crash course".

METHODS

The course was built by retrospective inclusion of 150 patients who underwent HRCT for COVID-19 pneumonia between November 2020 and January 2021. During a first 10-days-long "training phase", RR1 and RR2 read a pool of 100/150 HRCTs, receiving day-by-day access to CR reports as feedback. In the subsequent 2-days-long "test phase", they were asked to report 50/150 HRCTs with no feedback. Test phase reports of RR1/RR2 were then compared with CR using unweighted or linearly-weighted Cohen's kappa (k) statistic and intraclass correlation coefficient (ICC).

RESULTS

We observed almost perfect agreement in assessing disease extent between RR1-CR (k = 0.83, p < 0.001) and RR2-CR (k = 0.88, p < 0.001). The agreement between RR1-CR and RR2-CR on consolidation, crazy paving pattern, organizing pneumonia (OP) pattern, and pulmonary artery (PA) diameter was substantial (k = 0.65 and k = 0.68), moderate (k = 0.42 and k = 0.51), slight (k = 0.10 and k = 0.20), and good-to-excellent (ICC = 0.87 and ICC = 0.91), respectively. The agreement in providing RSNA categorization was moderate for R1 versus CR (k = 0.56) and substantial for R2 versus CR (k = 0.67).

CONCLUSION

HRCT-naïve readers showed an acceptable overall agreement with CR, supporting the hypothesis that a crash course can be a tool to readily make non-subspecialty radiologists available to cooperate in reading high burden of HRCT examinations during a pandemic/epidemic.

Chest computed tomography of suspected COVID-19 pneumonia in the Emergency Department: comparative analysis between patients with different vaccination status

Purpose

To identify differences in chest computed tomography (CT) of the symptomatic coronavirus disease 2019 (COVID-19) population according to the patients' severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination status (non-vaccinated, vaccinated with incomplete or complete vaccination cycle).

Material and methods

CT examinations performed in the Emergency Department (ED) in May-November 2021 for suspected COVID-19 pneumonia with a positive SARS-CoV-2 test were retrospectively included. Personal data were compared for vaccination status. One 13-year experienced radiologist and two 4th-year radiology residents independently evaluated chest CT scans according to CO-RADS and ACR COVID classifications. In possible COVID-19 pneumonia cases, defined as CO-RADS 3 to 5 (ACR indeterminate and typical) by each reader, high involvement CT score (≥ 25%) and CT patterns (presence of ground glass opacities, consolidations, crazy paving areas) were compared for vaccination status.

Results

184 patients with known vaccination status were included in the analysis: 111 non-vaccinated (60%) for SARS-CoV-2 infection, 21 (11%) with an incomplete vaccination cycle, and 52 (28%) with a complete vaccination cycle (6 different vaccine types). Multivariate logistic regression showed that the only factor predicting the absence of pneumonia (CO-RADS 1 and ACR negative cases) for the 3 readers was a complete vaccination cycle (OR = 12.8-13.1compared to non-vaccinated patients, p ≤ 0.032). Neither CT score nor CT patterns of possible COVID-19 pneumonia showed any statistically significant correlation with vaccination status for the 3 readers.

Conclusions

Symptomatic SARS-CoV-2-infected patients with a complete vaccination cycle had much higher odds of showing a negative CT chest examination in ED compared to non-vaccinated patients. Neither CT involvement nor CT patterns of interstitial pneumonia showed differences across different vaccination status.

Stereotactic body radiation therapy (SBRT) as salvage treatment for early stage lung cancer with interstitial lung disease (ILD): An observational and exploratory case series of non-asian patients

Interstitial lung disease (ILD) can coexist with early-stage lung cancer (LC) and may compromise surgery and worsen patients' outcomes. Stereotactic body radiation therapy (SBRT) is the gold standard treatment for medically inoperable early-stage lung cancer, but radiation therapy is contra-indicated for patients with ILD because of the higher risk of severe radiation-induced pneumonitis. SBRT may spare healthy lung tissue, but data are scarce in this rare population. Our exploratory case series aimed to retrospectively identify patients treated with SBRT in this setting: 19 patients were diagnosed with early-stage LC-ILD over the past 6 years and 9 received SBRT. Most of them were smokers with a median age of 71, 4 had no pathological documentation. After SBRT, 5 patients had grade I-II respiratory adverse events (AEs), but none had treatment-related grade III-IV respiratory AEs. Two patients died within 6 months of SBRT, and for both, death was related to metastatic relapse. In this case series, the radiological evolution of ILD before radiotherapy and the evolution of the radiotherapy scar on CT-Scan were also explored with different evolutionary models. This exploratory study shows available data that could be studied in a larger retrospective cohort to identify risk factors for SBRT in the LC-ILD population. The use of dosimetric data as a risk factor for SBRT should be done with cautiousness due to heterogeneous and complex dose delivery and different fractionation schedule.

Deep-learning-based hepatic fat assessment (DeHFt) on non-contrast chest CT and its association with disease severity in COVID-19 infections: A multi-site retrospective study

BACKGROUND

Hepatic steatosis (HS) identified on CT may provide an integrated cardiometabolic and COVID-19 risk assessment. This study presents a deep-learning-based hepatic fat assessment (DeHFt) pipeline for (a) more standardised measurements and (b) investigating the association between HS (liver-to-spleen attenuation ratio <1 in CT) and COVID-19 infections severity, wherein severity is defined as requiring invasive mechanical ventilation, extracorporeal membrane oxygenation, death.

METHODS

DeHFt comprises two steps. First, a deep-learning-based segmentation model (3D residual-UNet) is trained (N.ß=.ß80) to segment the liver and spleen. Second, CT attenuation is estimated using slice-based and volumetric-based methods. DeHFt-based mean liver and liver-to-spleen attenuation are compared with an expert's ROI-based measurements. We further obtained the liver-to-spleen attenuation ratio in a large multi-site cohort of patients with COVID-19 infections (D1, N.ß=.ß805; D2, N.ß=.ß1917; D3, N.ß=.ß169) using the DeHFt pipeline and investigated the association between HS and COVID-19 infections severity.

FINDINGS

The DeHFt pipeline achieved a dice coefficient of 0.95, 95% CI [0.93...0.96] on the independent validation cohort (N.ß=.ß49). The automated slice-based and volumetric-based liver and liver-to-spleen attenuation estimations strongly correlated with expert's measurement. In the COVID-19 cohorts, severe infections had a higher proportion of patients with HS than non-severe infections (pooled OR.ß=.ß1.50, 95% CI [1.20...1.88], P.ß<.ß.001).

INTERPRETATION

The DeHFt pipeline enabled accurate segmentation of liver and spleen on non-contrast CTs and automated estimation of liver and liver-to-spleen attenuation ratio. In three cohorts of patients with COVID-19 infections (N.ß=.ß2891), HS was associated with disease severity. Pending validation, DeHFt provides an automated CT-based metabolic risk assessment.

FUNDING

For a full list of funding bodies, please see the Acknowledgements.

Dynamic change of COVID-19 lung infection evaluated using co-registration of serial chest CT images

Purpose

To evaluate the volumetric change of COVID-19 lesions in the lung of patients receiving serial CT imaging for monitoring the evolution of the disease and the response to treatment.

Materials and methods

A total of 48 patients, 28 males and 20 females, who were confirmed to have COVID-19 infection and received chest CT examination, were identified. The age range was 21-93 years old, with a mean of 54 ± 18 years. Of them, 33 patients received the first follow-up (F/U) scan, 29 patients received the second F/U scan, and 11 patients received the third F/U scan. The lesion region of interest (ROI) was manually outlined. A two-step registration method, first using the Affine alignment, followed by the non-rigid Demons algorithm, was developed to match the lung areas on the baseline and F/U images. The baseline lesion ROI was mapped to the F/U images using the obtained geometric transformation matrix, and the radiologist outlined the lesion ROI on F/U CT again.

Results

The median (interquartile range) lesion volume (cm³) was 30.9 (83.1) at baseline CT exam, 18.3 (43.9) at first F/U, 7.6 (18.9) at second F/U, and 0.6 (19.1) at third F/U, which showed a significant trend of decrease with time. The two-step registration could significantly decrease the mean squared error (MSE) between baseline and F/U images with p < 0.001. The method could match the lung areas and the large vessels inside the lung. When using the mapped baseline ROIs as references, the second-look ROI drawing showed a significantly increased volume, p < 0.05, presumably due to the consideration of all the infected areas at baseline.

Conclusion

The results suggest that the registration method can be applied to assist in the evaluation of longitudinal changes of COVID-19 lesions on chest CT.

Human Observer Net: A Platform Tool for Human Observer Studies of Image Data

Background Current software applications for human observer studies of images lack flexibility in study design, platform independence, multicenter use, and assessment methods and are not open source, limiting accessibility and expandability. Purpose To develop a user-friendly software platform that enables efficient human observer studies in medical imaging with flexibility of study design. Materials and Methods Software for human observer imaging studies was designed as an open-source web application to facilitate access, platform-independent usability, and multicenter studies. Different interfaces for study creation, participation, and management of results were implemented. The software was evaluated in human observer experiments between May 2019 and March 2021, in which duration of observer responses was tracked. Fourteen radiologists evaluated and graded software usability using the 100-point system usability scale. The application was tested in Chrome, Firefox, Safari, and Edge browsers. Results Software function was designed to allow visual grading analysis (VGA), multiple-alternative forced-choice (m-AFC), receiver operating characteristic (ROC), localization ROC, free-response ROC, and customized designs. The mean duration of reader responses per image or per image set was 6.2 seconds ± 4.8 (standard deviation), 5.8 seconds ± 4.7, 8.7 seconds ± 5.7, and 6.0 seconds ± 4.5 in four-AFC with 160 image quartets per reader, four-AFC with 640 image quartets per reader, localization ROC, and experimental studies, respectively. The mean system usability scale score was 83 ± 11 (out of 100). The documented code and a demonstration of the application are available online (https://github.com/genskeu/HON, https://hondemo.pythonanywhere.com/). Conclusion A user-friendly and efficient open-source application was developed for human reader experiments that enables study design versatility, as well as platform-independent and multicenter usability. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Thompson in this issue.