Deep-Learning-Based Whole-Lung and Lung-Lesion Quantification Despite Inconsistent Ground Truth: Application to Computerized Tomography in SARS-CoV-2 Nonhuman Primate Models

Rationale and Objectives Animal modeling of infectious diseases such as coronavirus disease 2019 (COVID-19) is important for exploration of natural history, understanding of pathogenesis, and evaluation of countermeasures. Preclinical studies enable rigorous control of experimental conditions as well as pre-exposure baseline and longitudinal measurements, including medical imaging, that are often unavailable in the clinical research setting. Computerized tomography (CT) imaging provides important diagnostic, prognostic, and disease characterization to clinicians and clinical researchers. In that context, automated deep-learning systems for the analysis of CT imaging have been broadly proposed, but their practical utility has been limited. Manual outlining of the ground truth (i.e., lung-lesions) requires accurate distinctions between abnormal and normal tissues that often have vague boundaries and is subject to reader heterogeneity in interpretation. Indeed, this subjectivity is demonstrated as wide inconsistency in manual outlines among experts and from the same expert [1]. The application of deep-learning data-science tools has been less well-evaluated in the preclinical setting, including in nonhuman primate (NHP) models of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection/COVID-19, in which the translation of human-derived deep-learning tools is challenging. The automated segmentation of the whole lung and lung lesions provides a potentially standardized and automated method to detect and quantify disease. Materials and Methods We used deep-learning-based quantification of the whole lung and lung lesions on CT scans of NHPs exposed to SARS-CoV-2. We proposed a novel multi-model ensemble technique to address the inconsistency in the ground truths for deep-learning-based automated segmentation of the whole lung and lung lesions. Multiple models were obtained by training the convolutional neural network (CNN) on different subsets of the training data instead of having a single model using the entire training dataset. Moreover, we employed a feature pyramid network (FPN), a CNN that provides predictions at different resolution levels, enabling the network to predict objects with wide size variations. Results We achieved an average of 99.4 and 60.2% Dice coefficients for whole-lung and lung-lesion segmentation, respectively. The proposed multi-model FPN outperformed well-accepted methods U-Net (50.5%), V-Net (54.5%), and Inception (53.4%) for the challenging lesion-segmentation task. We show the application of segmentation outputs for longitudinal quantification of lung disease in SARS-CoV-2-exposed and mock-exposed NHPs. Conclusion Deep-learning methods should be optimally characterized for and targeted specifically to preclinical research needs in terms of impact, automation, and dynamic quantification independently from purely clinical applications.

Deep-Learning-Based Whole-Lung and Lung-Lesion Quantification Despite Inconsistent Ground Truth: Application to Computerized Tomography in SARS-CoV-2 Nonhuman Primate Models.

RATIONALE AND OBJECTIVES: Animal modeling of infectious diseases such as coronavirus disease 2019 (COVID-19) is important for exploration of natural history, understanding of pathogenesis, and evaluation of countermeasures. Preclinical studies enable rigorous control of experimental conditions as well as pre-exposure baseline and longitudinal measurements, including medical imaging, that are often unavailable in the clinical research setting. Computerized tomography (CT) imaging provides important diagnostic, prognostic, and disease characterization to clinicians and clinical researchers. In that context, automated deep-learning systems for the analysis of CT imaging have been broadly proposed, but their practical utility has been limited. Manual outlining of the ground truth (i.e., lung-lesions) requires accurate distinctions between abnormal and normal tissues that often have vague boundaries and is subject to reader heterogeneity in interpretation. Indeed, this subjectivity is demonstrated as wide inconsistency in manual outlines among experts and from the same expert. The application of deep-learning data-science tools has been less well-evaluated in the preclinical setting, including in nonhuman primate (NHP) models of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection/COVID-19, in which the translation of human-derived deep-learning tools is challenging. The automated segmentation of the whole lung and lung lesions provides a potentially standardized and automated method to detect and quantify disease. MATERIALS AND METHODS: We used deep-learning-based quantification of the whole lung and lung lesions on CT scans of NHPs exposed to SARS-CoV-2. We proposed a novel multi-model ensemble technique to address the inconsistency in the ground truths for deep-learning-based automated segmentation of the whole lung and lung lesions. Multiple models were obtained by training the convolutional neural network (CNN) on different subsets of the training data instead of having a single model using the entire training dataset. Moreover, we employed a feature pyramid network (FPN), a CNN that provides predictions at different resolution levels, enabling the network to predict objects with wide size variations. RESULTS: We achieved an average of 99.4 and 60.2% Dice coefficients for whole-lung and lung-lesion segmentation, respectively. The proposed multi-model FPN outperformed well-accepted methods U-Net (50.5%), V-Net (54.5%), and Inception (53.4%) for the challenging lesion-segmentation task. We show the application of segmentation outputs for longitudinal quantification of lung disease in SARS-CoV-2-exposed and mock-exposed NHPs. CONCLUSION: Deep-learning methods should be optimally characterized for and targeted specifically to preclinical research needs in terms of impact, automation, and dynamic quantification independently from purely clinical applications.

In-line miniature 3D-printed pressure-cycled ventilator maintains respiratory homeostasis in swine with induced acute pulmonary injury.

The COVID-19 pandemic demonstrated the need for inexpensive, easy-to-use, rapidly mass-produced resuscitation devices that could be quickly distributed in areas of critical need. In-line miniature ventilators based on principles of fluidics ventilate patients by automatically oscillating between forced inspiration and assisted expiration as airway pressure changes, requiring only a continuous supply of pressurized oxygen. Here, we designed three miniature ventilator models to operate in specific pressure ranges along a continuum of clinical lung injury (mild, moderate, and severe injury). Three-dimensional (3D)-printed prototype devices evaluated in a lung simulator generated airway pressures, tidal volumes, and minute ventilation within the targeted range for the state of lung disease each was designed to support. In testing in domestic swine before and after induction of pulmonary injury, the ventilators for mild and moderate injury met the design criteria when matched with the appropriate degree of lung injury. Although the ventilator for severe injury provided the specified design pressures, respiratory rate was elevated with reduced minute ventilation, a result of lung compliance below design parameters. Respiratory rate reflected how well each ventilator matched the injury state of the lungs and could guide selection of ventilator models in clinical use. This simple device could help mitigate shortages of conventional ventilators during pandemics and other disasters requiring rapid access to advanced airway management, or in transport applications for hands-free ventilation.

Chest imaging in patients with acute respiratory failure because of coronavirus disease 2019.

PURPOSE OF REVIEW: This review aims to explore the different imaging modalities, such as chest radiography (CXR), computed tomography (CT), ultrasound, PET/CT scan, and MRI to describe the main features for the evaluation of the chest in COVID-19 patients with ARDS. RECENT FINDINGS: This article includes a systematic literature search, evidencing the different chest imaging modalities used in patients with ARDS from COVID-19. Literature evidences different possible approaches going from the conventional CXR and CT to the LUS, MRI, and PET/CT. SUMMARY: CT is the technique with higher sensitivity and definition for studying chest in COVID-19 patients. LUS or bedside CXR are critical in patients requiring close and repeated monitoring. Moreover, LUS and CXR reduce the radiation burden and the risk of infection compared with CT. PET/CT and MRI, especially in ARDS patients, are not usually used for diagnostic or follow-up purposes.

Federated learning for predicting clinical outcomes in patients with COVID-19.

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

AI-Assisted CT as a Clinical and Research Tool for COVID-19.

There is compelling support for widening the role of computed tomography (CT) for COVID-19 in clinical and research scenarios. Reverse transcription polymerase chain reaction (RT-PCR) testing, the gold standard for COVID-19 diagnosis, has two potential weaknesses: the delay in obtaining results and the possibility of RT-PCR test kits running out when demand spikes or being unavailable altogether. This perspective article discusses the potential use of CT in conjunction with RT-PCR in hospitals lacking sufficient access to RT-PCR test kits. The precedent for this approach is discussed based on the use of CT for COVID-19 diagnosis and screening in the United Kingdom and China. The hurdles and challenges are presented, which need addressing prior to realization of the potential roles for CT artificial intelligence (AI). The potential roles include a more accurate clinical classification, characterization for research roles and mechanisms, and informing clinical trial response criteria as a surrogate for clinical outcomes.

Generalized chest CT and lab curves throughout the course of COVID-19.

A better understanding of temporal relationships between chest CT and labs may provide a reference for disease severity over the disease course. Generalized curves of lung opacity volume and density over time can be used as standardized references from well before symptoms develop to over a month after recovery, when residual lung opacities remain. 739 patients with COVID-19 underwent CT and RT-PCR in an outbreak setting between January 21st and April 12th, 2020. 29 of 739 patients had serial exams (121 CTs and 279 laboratory measurements) over 50 ± 16 days, with an average of 4.2 sequential CTs each. Sequential volumes of total lung, overall opacity and opacity subtypes (ground glass opacity [GGO] and consolidation) were extracted using deep learning and manual segmentation. Generalized temporal curves of CT and laboratory measurements were correlated. Lung opacities appeared 3.4 ± 2.2 days prior to symptom onset. Opacity peaked 1 day after symptom onset. GGO onset was earlier and resolved later than consolidation. Lactate dehydrogenase, and C-reactive protein peaked earlier than procalcitonin and leukopenia. The temporal relationships of quantitative CT features and clinical labs have distinctive patterns and peaks in relation to symptom onset, which may inform early clinical course in patients with mild COVID-19 pneumonia, or may shed light upon chronic lung effects or mechanisms of medical countermeasures in clinical trials.

Federated semi-supervised learning for COVID region segmentation in chest CT using multi-national data from China, Italy, Japan.

The recent outbreak of Coronavirus Disease 2019 (COVID-19) has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. The current guideline is using RT-PCR for testing. As a complimentary tool with diagnostic imaging, chest Computed Tomography (CT) has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis with chest CT scan, which has shown promising results. However, domain shift of data across clinical data centers poses a serious challenge when deploying learning-based models. A common way to alleviate this issue is to fine-tune the model locally with the target domains local data and annotations. Unfortunately, the availability and quality of local annotations usually varies due to heterogeneity in equipment and distribution of medical resources across the globe. This impact may be pronounced in the detection of COVID-19, since the relevant patterns vary in size, shape, and texture. In this work, we attempt to find a solution for this challenge via federated and semi-supervised learning. A multi-national database consisting of 1704 scans from three countries is adopted to study the performance gap, when training a model with one dataset and applying it to another. Expert radiologists manually delineated 945 scans for COVID-19 findings. In handling the variability in both the data and annotations, a novel federated semi-supervised learning technique is proposed to fully utilize all available data (with or without annotations). Federated learning avoids the need for sensitive data-sharing, which makes it favorable for institutions and nations with strict regulatory policy on data privacy. Moreover, semi-supervision potentially reduces the annotation burden under a distributed setting. The proposed framework is shown to be effective compared to fully supervised scenarios with conventional data sharing instead of model weight sharing.

CT and clinical assessment in asymptomatic and pre-symptomatic patients with early SARS-CoV-2 in outbreak settings.

OBJECTIVES: The early infection dynamics of patients with SARS-CoV-2 are not well understood. We aimed to investigate and characterize associations between clinical, laboratory, and imaging features of asymptomatic and pre-symptomatic patients with SARS-CoV-2. METHODS: Seventy-four patients with RT-PCR-proven SARS-CoV-2 infection were asymptomatic at presentation. All were retrospectively identified from 825 patients with chest CT scans and positive RT-PCR following exposure or travel risks in outbreak settings in Japan and China. CTs were obtained for every patient within a day of admission and were reviewed for infiltrate subtypes and percent with assistance from a deep learning tool. Correlations of clinical, laboratory, and imaging features were analyzed and comparisons were performed using univariate and multivariate logistic regression. RESULTS: Forty-eight of 74 (65%) initially asymptomatic patients had CT infiltrates that pre-dated symptom onset by 3.8 days. The most common CT infiltrates were ground glass opacities (45/48; 94%) and consolidation (22/48; 46%). Patient body temperature (p < 0.01), CRP (p < 0.01), and KL-6 (p = 0.02) were associated with the presence of CT infiltrates. Infiltrate volume (p = 0.01), percent lung involvement (p = 0.01), and consolidation (p = 0.043) were associated with subsequent development of symptoms. CONCLUSIONS: COVID-19 CT infiltrates pre-dated symptoms in two-thirds of patients. Body temperature elevation and laboratory evaluations may identify asymptomatic patients with SARS-CoV-2 CT infiltrates at presentation, and the characteristics of CT infiltrates could help identify asymptomatic SARS-CoV-2 patients who subsequently develop symptoms. The role of chest CT in COVID-19 may be illuminated by a better understanding of CT infiltrates in patients with early disease or SARS-CoV-2 exposure. KEY POINTS: • Forty-eight of 74 (65%) pre-selected asymptomatic patients with SARS-CoV-2 had abnormal chest CT findings. • CT infiltrates pre-dated symptom onset by 3.8 days (range 1-5). • KL-6, CRP, and elevated body temperature identified patients with CT infiltrates. Higher infiltrate volume, percent lung involvement, and pulmonary consolidation identified patients who developed symptoms.

Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

Preparation of a radiology department in an Italian hospital dedicated to COVID-19 patients.

Preparedness for the ongoing coronavirus disease 2019 (COVID-19) and its spread in Italy called for setting up of adequately equipped and dedicated health facilities to manage sick patients while protecting healthcare workers, uninfected patients, and the community. In our country, in a short time span, the demand for critical care beds exceeded supply. A new sequestered hospital completely dedicated to intensive care (IC) for isolated COVID-19 patients needed to be designed, constructed, and deployed. Along with this new initiative, the new concept of "Pandemic Radiology Unit" was implemented as a practical solution to the emerging crisis, born out of a critical and urgent acute need. The present article describes logistics, planning, and practical design issues for such a pandemic radiology and critical care unit (e.g., space, infection control, safety of healthcare workers, etc.) adopted in the IC Hospital Unit for the care and management of COVID-19 patients.

Disposable Isolation Device to Reduce COVID-19 Contamination During CT Scanning.

RATIONALE AND OBJECTIVES: The use of chest computed tomography (CT) in the era of the COVID-19 pandemic raises concern regarding the transmission risks to patients and staff caused by CT room contamination. Meanwhile the Center for Disease Control guidance for air exchange in between patients may heavily impact workflows. To design a portable custom isolation device to reduce imaging equipment contamination during a pandemic. MATERIALS AND METHODS: Center for Disease Control air exchange guidelines and requirements were reviewed. Device functional requirements were outlined and designed. Engineering requirements were reviewed. Methods of practice and risk mitigation plans were outlined including donning and doffing procedures and failure modes. Cost impact was assessed in terms of CT patient throughput. RESULTS: CT air exchange solutions and alternatives were reviewed. Multiple isolation bag device designs were considered. Several designs were custom fabricated, prototyped and reduced to practice. A final design was tested on volunteers for comfort, test-fit, air seal, and breathability. Less than 14 times enhanced patient throughput was estimated, in an ideal setting, which could more than counterbalance the cost of the device itself. CONCLUSION: A novel isolation bag device is feasible for use in CT and might facilitate containment and reduce contamination in radiology departments during the COVID Pandemic.

How to Handle a COVID-19 Patient in the Angiographic Suite.

This is a single-center report on coordination of staff and handling of patients during the outbreak of the COVID-19 (coronavirus disease 2019) in a region with high incidence and prevalence of disease. The selection of procedures for interventional radiology (IR), preparation of staff and interventional suite before the arrival of patients, the facility ventilation systems and intra- and post-procedural workflow optimization are described. The control measures described may increase the cost of the equipment, prolong procedural times and increase technical difficulties. However, these precautions may help control the spread of COVID-19 within the healthcare facility.