LASSO-Cox Modeling of Survival Using High-Resolution CT-Based Radiomic Features in a Cohort of COVID-19 Patients and Its Generalizability to Standard Image Reconstruction

Background: Few studies have focused on predicting the overall survival (OS) of patients affected by SARS-CoV-2 (i.e., COVID-19) using radiomic features (RFs) extracted from computer tomography (CT) images. Reconstruction of CT scans might potentially affect the values of RFs. Methods: Out of 435 patients, 239 had the scans reconstructed with a single modality, and hence, were used for training/testing, and 196 were reconstructed with two modalities were used as validation to evaluate RFs robustness to reconstruction. During training, the dataset was split into train/test using a 70/30 proportion, randomizing the procedure 100 times to obtain 100 different models. In all cases, RFs were normalized using the z-score and then given as input into a Cox proportional-hazards model regularized with the Least Absolute Shrinkage and Selection Operator (LASSO-Cox), used for feature selection and developing a robust model. The RFs retained multiple times in the models were also included in a final LASSO-Cox for developing the predictive model. Thus, we conducted sensitivity analysis increasing the number of retained RFs with an occurrence cut-off from 11% to 60%. The Bayesian information criterion (BIC) was used to identify the cut-off to build the optimal model. Results: The best BIC value indicated 45% as the optimal occurrence cut-off, resulting in five RFs used for generating the final LASSO-Cox. All the Kaplan-Meier curves of training and validation datasets were statistically significant in identifying patients with good and poor prognoses, irrespective of CT reconstruction. Conclusions: The final LASSO-Cox model maintained its predictive ability for predicting the OS in COVID-19 patients irrespective of CT reconstruction algorithms.

An Imaging Overview of COVID-19 ARDS in ICU Patients and Its Complications: A Pictorial Review.

A significant proportion of patients with COVID-19 pneumonia could develop acute respiratory distress syndrome (ARDS), thus requiring mechanical ventilation, and resulting in a high rate of intensive care unit (ICU) admission. Several complications can arise during an ICU stay, from both COVID-19 infection and the respiratory supporting system, including barotraumas (pneumothorax and pneumomediastinum), superimposed pneumonia, coagulation disorders (pulmonary embolism, venous thromboembolism, hemorrhages and acute ischemic stroke), abdominal involvement (acute mesenteric ischemia, pancreatitis and acute kidney injury) and sarcopenia. Imaging plays a pivotal role in the detection and monitoring of ICU complications and is expanding even to prognosis prediction. The present pictorial review describes the clinicopathological and radiological findings of COVID-19 ARDS in ICU patients and discusses the imaging features of complications related to invasive ventilation support, as well as those of COVID-19 itself in this particularly fragile population. Radiologists need to be familiar with COVID-19's possible extra-pulmonary complications and, through reliable and constant monitoring, guide therapeutic decisions. Moreover, as more research is pursued and the pathophysiology of COVID-19 is increasingly understood, the role of imaging must evolve accordingly, expanding from the diagnosis and subsequent management of patients to prognosis prediction.

Outcome Prediction for SARS-CoV-2 Patients Using Machine Learning Modeling of Clinical, Radiological, and Radiomic Features Derived from Chest CT Images

(1) Background: Chest Computed Tomography (CT) has been proposed as a non-invasive method for confirming the diagnosis of SARS-CoV-2 patients using radiomic features (RFs) and baseline clinical data. The performance of Machine Learning (ML) methods using RFs derived from semi-automatically segmented lungs in chest CT images was investigated regarding the ability to predict the mortality of SARS-CoV-2 patients. (2) Methods: A total of 179 RFs extracted from 436 chest CT images of SARS-CoV-2 patients, and 8 clinical and 6 radiological variables, were used to train and evaluate three ML methods (Least Absolute Shrinkage and Selection Operator [LASSO] regularized regression, Random Forest Classifier [RFC], and the Fully connected Neural Network [FcNN]) for their ability to predict mortality using the Area Under the Curve (AUC) of Receiver Operator characteristic (ROC) Curves. These three groups of variables were used separately and together as input for constructing and comparing the final performance of ML models. (3) Results: All the ML models using only RFs achieved an informative level regarding predictive ability, outperforming radiological assessment, without however reaching the performance obtained with ML based on clinical variables. The LASSO regularized regression and the FcNN performed equally, both being superior to the RFC. (4) Conclusions: Radiomic features based on semi-automatically segmented CT images and ML approaches can aid in identifying patients with a high risk of mortality, allowing a fast, objective, and generalizable method for improving prognostic assessment by providing a second expert opinion that outperforms human evaluation.

An Imaging Overview of COVID-19 ARDS in ICU Patients and Its Complications: A Pictorial Review

A significant proportion of patients with COVID-19 pneumonia could develop acute respiratory distress syndrome (ARDS), thus requiring mechanical ventilation, and resulting in a high rate of intensive care unit (ICU) admission. Several complications can arise during an ICU stay, from both COVID-19 infection and the respiratory supporting system, including barotraumas (pneumothorax and pneumomediastinum), superimposed pneumonia, coagulation disorders (pulmonary embolism, venous thromboembolism, hemorrhages and acute ischemic stroke), abdominal involvement (acute mesenteric ischemia, pancreatitis and acute kidney injury) and sarcopenia. Imaging plays a pivotal role in the detection and monitoring of ICU complications and is expanding even to prognosis prediction. The present pictorial review describes the clinicopathological and radiological findings of COVID-19 ARDS in ICU patients and discusses the imaging features of complications related to invasive ventilation support, as well as those of COVID-19 itself in this particularly fragile population. Radiologists need to be familiar with COVID-19's possible extra-pulmonary complications and, through reliable and constant monitoring, guide therapeutic decisions. Moreover, as more research is pursued and the pathophysiology of COVID-19 is increasingly understood, the role of imaging must evolve accordingly, expanding from the diagnosis and subsequent management of patients to prognosis prediction.

Extracorporeal membrane oxygenation (ECMO) in COVID-19 patients: a pocket guide for radiologists.

During the coronavirus disease 19 (COVID-19) pandemic, extracorporeal membrane oxygenation (ECMO) has been proposed as a possible therapy for COVID-19 patients with acute respiratory distress syndrome. This pictorial review is intended to provide radiologists with up-to-date information regarding different types of ECMO devices, correct placement of ECMO cannulae, and imaging features of potential complications and disease evolution in COVID-19 patients treated with ECMO, which is essential for a correct interpretation of diagnostic imaging, so as to guide proper patient management.

Clinical implications of microvascular CT scan signs in COVID-19 patients requiring invasive mechanical ventilation.

PURPOSE: COVID-19-related acute respiratory distress syndrome (ARDS) is characterized by the presence of signs of microvascular involvement at the CT scan, such as the vascular tree in bud (TIB) and the vascular enlargement pattern (VEP). Recent evidence suggests that TIB could be associated with an increased duration of invasive mechanical ventilation (IMV) and intensive care unit (ICU) stay. The primary objective of this study was to evaluate whether microvascular involvement signs could have a prognostic significance concerning liberation from IMV. MATERIAL AND METHODS: All the COVID-19 patients requiring IMV admitted to 16 Italian ICUs and having a lung CT scan recorded within 3 days from intubation were enrolled in this secondary analysis. Radiologic, clinical and biochemical data were collected. RESULTS: A total of 139 patients affected by COVID-19 related ARDS were enrolled. After grouping based on TIB or VEP detection, we found no differences in terms of duration of IMV and mortality. Extension of VEP and TIB was significantly correlated with ground-glass opacities (GGOs) and crazy paving pattern extension. A parenchymal extent over 50% of GGO and crazy paving pattern was more frequently observed among non-survivors, while a VEP and TIB extent involving 3 or more lobes was significantly more frequent in non-responders to prone positioning. CONCLUSIONS: The presence of early CT scan signs of microvascular involvement in COVID-19 patients does not appear to be associated with differences in duration of IMV and mortality. However, patients with a high extension of VEP and TIB may have a reduced oxygenation response to prone positioning. TRIAL REGISTRATION: NCT04411459.

Comparing the first and the second waves of COVID-19 in Italy: differences in epidemiological features and CT findings using a semi-quantitative score.

PURPOSE: CT findings of hospitalized COVID-19 patients were analyzed during both the first and the second waves of the pandemic, in order to detect any significant differences between the two groups. METHODS: In this observational, retrospective, monocentric study, all hospitalized patients who underwent CT for suspected COVID-19 pneumonia from February 27 to March 27, 2020 (first wave) and from October 26 to November 24, 2020 (second wave) were enrolled. Epidemiological data, radiological pattern according to the RSNA consensus statement and visual score extension using a semi-quantitative score were compared. RESULTS: Two hundred and eleven patients (mean age, 64.52 years ± 15.14, 144 males) were evaluated during the first wave while 455 patients (mean age, 68.26 years ± 16.34, 283 males) were studied during the second wave. The same prevalence of patterns was documented in both the first and the second waves (p = 0.916), with non-typical patterns always more frequently observed in elderly patients, especially the "indeterminate" pattern. Compared to those infected during the first wave, the patients of the second wave were older (64.52 vs.68.26, p = 0.005) and presented a slightly higher mean semi-quantitative score (9.0 ± 2.88 vs. 8.4 ± 3.06, p = 0.042). Age and semi-quantitative score showed a positive correlation (r = 0.15, p = 0.001). CONCLUSIONS: There was no difference regarding CT pattern prevalence between the first and the second waves, confirming both the validity of the RSNA consensus and the most frequent radiological COVID-19 features. Non-typical COVID-19 features were more frequently observed in older patients, thus should not be underestimated in the elderly population.

Classification Performance for COVID Patient Prognosis from Automatic AI Segmentation—A Single-Center Study

Background: COVID assessment can be performed using the recently developed individual risk score (prediction of severe respiratory failure in hospitalized patients with SARS-COV2 infection, PREDI-CO score) based on High Resolution Computed Tomography. In this study, we evaluated the possibility of automatizing this estimation using semi-supervised AI-based Radiomics, leveraging the possibility of performing non-supervised segmentation of ground-glass areas. Methods: We collected 92 from patients treated in the IRCCS Sant’Orsola-Malpighi Policlinic and public databases;each lung was segmented using a pre-trained AI method;ground-glass opacity was identified using a novel, non-supervised approach;radiomic measurements were collected and used to predict clinically relevant scores, with particular focus on mortality and the PREDI-CO score. We compared the prediction obtained through different machine learning approaches. Results: All the methods obtained a well-balanced accuracy (70%) on the PREDI-CO score but did not obtain satisfying results on other clinical characteristics due to unbalance between the classes. Conclusions: Semi-supervised segmentation, implemented using a combination of non-supervised segmentation and feature extraction, seems to be a viable approach for patient stratification and could be leveraged to train more complex models. This would be useful in a high-demand situation similar to the current pandemic to support gold-standard segmentation for AI training.

Diagnostic Accuracy of North America Expert Consensus Statement on Reporting CT Findings in Patients Suspected of Having COVID-19 Infection: An Italian Single-Center Experience.

PURPOSE: To evaluate the diagnostic accuracy of the four standardized categories for CT reporting proposed by the Radiological Society of North America (RSNA) to support a faster triage compared with real-time reverse-transcription polymerase chain reaction (RT-PCR), which is the reference standard for suspected coronavirus disease 2019 (COVID-19), but has long reporting time (6-48 hours). MATERIALS AND METHODS: A retrospective analysis of 569 thin-section CT examinations performed for patients suspected of having COVID-19 from February 27 to March 27, 2020 (peak of infection in Italy) was conducted. The imaging pattern was classified according to the statement by the RSNA as "typical," "indeterminate," "atypical," and "negative" and compared with RT-PCR for 460 patients. Interobserver variability in reporting between a senior and a junior radiologist was evaluated. Use of the vascular enlargement sign in indeterminate cases was also assessed. RESULTS: The diagnosis of COVID-19 was made in 45.9% (211/460) of patients. The "typical" pattern (n = 172) showed a sensitivity of 71.6%, a specificity of 91.6%, and a positive predictive value of 87.8% for COVID-19. The "atypical" (n = 67) and "negative" (n = 123) pattern demonstrated a positive predictive value of 89.6% and 86.2% for non-COVID-19, respectively. The "indeterminate" (n = 98) pattern was nonspecific, but vascular enlargement was most frequently found in patients with COVID-19 (86.1%; P < .001). Interobserver agreement was good for the "typical" and "negative" pattern and fair for "indeterminate" and "atypical" (κ = 0.5; P = .002). CONCLUSION: In an epidemic setting, the application of the four categories proposed by the RSNA provides a standardized diagnostic hypothesis, strongly linked to the RT-PCR results for the "typical," "atypical," and "negative" pattern. In the "indeterminate" pattern, the analysis of the vascular enlargement sign could facilitate the interpretation of imaging features.© RSNA, 2020.

Impact of the COVID-19 outbreak on the profession and psychological wellbeing of radiologists: a nationwide online survey.

BACKGROUND: The COVID-19 outbreak has played havoc within healthcare systems, with radiology sharing a substantial burden. Our purpose is to report findings from a survey on the crisis impact among members of the Italian Society of Medical and Interventional Radiology (SIRM). METHODS: All members were invited to a 42-question online survey about the impact of the COVID-19 outbreak on personal and family life, professional activity, socioeconomic and psychological condition. Participants were classified based on working in the most severely affected Italian regions ("hot regions") or elsewhere. RESULTS: A total of 2150 radiologists joined the survey. More than 60% of respondents estimated a workload reduction greater than 50%, with a higher prevalence among private workers in hot regions (72.7% vs 66.5% elsewhere, p = 0.1010). Most respondents were concerned that the COVID-19 outbreak could impact the management of non-COVID-19 patients and expected a work overload after the crisis. More than 40% were moderately or severely worried that their professional activity could be damaged, and most residents believed that their training had been affected. More than 50% of respondents had increased emotional stress at work, including moderate or severe symptoms due to sleep disturbances, feeling like living in slow motion and having negative thoughts, those latter being more likely in single-living respondents from hot regions [log OR 0.7108 (CI95% 0.3445 ÷ 1.0770), p = 0.0001]. CONCLUSIONS: The COVID-19 outbreak has had a sensible impact on the working and personal life of SIRM members, with more specific criticalities in hot regions. Our findings could aid preserving the radiologists' wellbeing after the crisis.

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia.

Segmentation is a complex task, faced by radiologists and researchers as radiomics and machine learning grow in potentiality. The process can either be automatic, semi-automatic, or manual, the first often not being sufficiently precise or easily reproducible, and the last being excessively time consuming when involving large districts with high-resolution acquisitions. A high-resolution CT of the chest is composed of hundreds of images, and this makes the manual approach excessively time consuming. Furthermore, the parenchymal alterations require an expert evaluation to be discerned from the normal appearance; thus, a semi-automatic approach to the segmentation process is, to the best of our knowledge, the most suitable when segmenting pneumonias, especially when their features are still unknown. For the studies conducted in our institute on the imaging of COVID-19, we adopted 3D Slicer, a freeware software produced by the Harvard University, and combined the threshold with the paint brush instruments to achieve fast and precise segmentation of aerated lung, ground glass opacities, and consolidations. When facing complex cases, this method still requires a considerable amount of time for proper manual adjustments, but provides an extremely efficient mean to define segments to use for further analysis, such as the calculation of the percentage of the affected lung parenchyma or texture analysis of the ground glass areas.

Use of CT and artificial intelligence in suspected or COVID-19 positive patients: statement of the Italian Society of Medical and Interventional Radiology.

The COVID-19 pandemic started in Italy in February 2020 with an exponential growth that has exceeded the number of cases reported in China. Italian radiology departments found themselves at the forefront in the management of suspected and positive COVID cases, both in diagnosis, in estimating the severity of the disease and in follow-up. In this context SIRM recommends chest X-ray as first-line imaging tool, CT as additional tool that shows typical features of COVID pneumonia, and ultrasound of the lungs as monitoring tool. SIRM recommends, as high priority, to ensure appropriate sanitation procedures on the scan equipment after detecting any suspected or positive COVID-19 patients. In this emergency situation, several expectations have been raised by the scientific community about the role that artificial intelligence can have in improving the diagnosis and treatment of coronavirus infection, and SIRM wishes to deliver clear statements to the radiological community, on the usefulness of artificial intelligence as a radiological decision support system in COVID-19 positive patients. (1) SIRM supports the research on the use of artificial intelligence as a predictive and prognostic decision support system, especially in hospitalized patients and those admitted to intensive care, and welcomes single center of multicenter studies for a clinical validation of the test. (2) SIRM does not support the use of CT with artificial intelligence for screening or as first-line test to diagnose COVID-19. (3) Chest CT with artificial intelligence cannot replace molecular diagnosis tests with nose-pharyngeal swab (rRT-PCR) in suspected for COVID-19 patients.

The paradigms of urban planning to emergency-proof Rethinking the organisation of settlements at the time of a pandemic

Urban planning is one of the sectors that is able to provide a contribution to the definition of a desirable scenario for the future of the city and the territory as it deals with the physical and functional organisation of human settlements, more than others, also for reasons related to its historical origin. The paradigms now acquired from a disciplinary point of view, such as densification, sustainable mobility, mixite, urban green, etc., raise the issue of compatibility with the needs of social distancing imposed by the health emergency. One wonders if and how the principles and criteria for the physical and functional organisation of settlements, which inform and substantiate the technical-scientific documents and the spatial and urban planning instruments themselves, will change. The response confirms the overall goodness of the organisational model shared by the community of urban planners. This can only be a stimulus to continue the research and application activities in the field with even greater commitment and determination. The crisis must in any case build an opportunity to rethink the functioning of the city, its spaces, its times and its forms of social and economic interaction, as we imagine will happen in all other fields