Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features.

PURPOSE: To investigate the efficacy of radiomics in diagnosing patients with coronavirus disease (COVID-19) and other types of viral pneumonia with clinical symptoms and CT signs similar to those of COVID-19. METHODS: Between 18 January 2020 and 20 May 2020, 110 SARS-CoV-2 positive and 108 SARS-CoV-2 negative patients were retrospectively recruited from three hospitals based on the inclusion criteria. Manual segmentation of pneumonia lesions on CT scans was performed by four radiologists. The latest version of Pyradiomics was used for feature extraction. Four classifiers (linear classifier, k-nearest neighbour, least absolute shrinkage and selection operator [LASSO], and random forest) were used to differentiate SARS-CoV-2 positive and SARS-CoV-2 negative patients. Comparison of the performance of the classifiers and radiologists was evaluated by ROC curve and Kappa score. RESULTS: We manually segmented 16,053 CT slices, comprising 32,625 pneumonia lesions, from the CT scans of all patients. Using Pyradiomics, 120 radiomic features were extracted from each image. The key radiomic features screened by different classifiers varied and lead to significant differences in classification accuracy. The LASSO achieved the best performance (sensitivity: 72.2%, specificity: 75.1%, and AUC: 0.81) on the external validation dataset and attained excellent agreement (Kappa score: 0.89) with radiologists (average sensitivity: 75.6%, specificity: 78.2%, and AUC: 0.81). All classifiers indicated that "Original_Firstorder_RootMeanSquared" and "Original_Firstorder_Uniformity" were significant features for this task. CONCLUSIONS: We identified radiomic features that were significantly associated with the classification of COVID-19 pneumonia using multiple classifiers. The quantifiable interpretation of the differences in features between the two groups extends our understanding of CT imaging characteristics of COVID-19 pneumonia.

Chest CT in COVID-19: What the Radiologist Needs to Know.

Chest CT has a potential role in the diagnosis, detection of complications, and prognostication of coronavirus disease 2019 (COVID-19). Implementation of appropriate precautionary safety measures, chest CT protocol optimization, and a standardized reporting system based on the pulmonary findings in this disease will enhance the clinical utility of chest CT. However, chest CT examinations may lead to both false-negative and false-positive results. Furthermore, the added value of chest CT in diagnostic decision making is dependent on several dynamic variables, most notably available resources (real-time reverse transcription-polymerase chain reaction [RT-PCR] tests, personal protective equipment, CT scanners, hospital and radiology personnel availability, and isolation room capacity) and the prevalence of both COVID-19 and other diseases with overlapping manifestations at chest CT. Chest CT is valuable to detect both alternative diagnoses and complications of COVID-19 (acute respiratory distress syndrome, pulmonary embolism, and heart failure), while its role for prognostication requires further investigation. The authors describe imaging and managing care of patients with COVID-19, with topics including (a) chest CT protocol, (b) chest CT findings of COVID-19 and its complications, (c) the diagnostic accuracy of chest CT and its role in diagnostic decision making and prognostication, and (d) reporting and communicating chest CT findings. The authors also review other specific topics, including the pathophysiology and clinical manifestations of COVID-19, the World Health Organization case definition, the value of performing RT-PCR tests, and the radiology department and personnel impact related to performing chest CT in COVID-19. ©RSNA, 2020.

The radiology workforce's response to the COVID-19 pandemic in the Middle East, North Africa and India.

INTRODUCTION: This study aimed to investigate the response of the radiology workforce to the impact of the coronavirus disease 2019 (COVID-19) pandemic on professional practice in India and eight other Middle Eastern and North African countries. It further investigated the levels of fear and anxiety among this workforce during the pandemic. METHODS: A quantitative cross-sectional study was conducted using an online survey from 22 May-2 June 2020 among radiology workers employed during the COVID-19 pandemic. The survey collected information related to the following themes: (1) demographic characteristics, (2) the impact of COVID-19 on radiology practice, and (3) fear and (4) anxiety emanating from the global pandemic. RESULTS: We received 903 responses. Fifty-eight percent had completed training on infection control required for handling COVID-19 patients. A large proportion (79.5%) of the respondents strongly agreed or agreed that personal protective equipment (PPE) was adequately available at work during the pandemic. The respondents reported experiences of work-related stress (42.9%), high COVID-19 fear score (83.3%) and anxiety (10%) during the study period. CONCLUSION: There was a perceived workload increase in general x-ray and Computed Tomography imaging procedures because they were the key modalities for the initial and follow-up investigations of COVID-19. However, there was adequate availability of PPE during the study period. Most radiology workers were afraid of being infected with the virus. Fear was predominant among workers younger than 30 years of age and also in temporary staff. Anxiety occurred completely independent of gender, age, experience, country, place of work, and work status. IMPLICATIONS FOR PRACTICE: It is important to provide training and regular mental health support and evaluations for healthcare professionals, including radiology workers, during similar future pandemics.

Dr Mom's Added Burden.

Today's female physicians face a "triple whammy" of structural discrimination, rigid work expectations, and increasing educational debt. Coronavirus disease 2019 is disproportionately amplifying these forces on women. The burden of these forces on women, the likely long-term consequences, and some preliminary solutions are discussed.

Endovascular simulation as a supplemental training tool during the COVID-19 national emergency.

The ongoing COVID pandemic raises many concerns as our healthcare system is pushed to its limits and as a consequence, Interventional Radiology training may be compromised. Endovascular simulators allow trainees many benefits to build and maintain endovascular skills in a safe environment. Our experience demonstrates a methodology to maintain IR training with use of didactic and simulation supplementation during the COVID-19 pandemic, which may be helpful for incorporation at other institutions facing similar challenges.