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.

Toward the determination of sensitive and reliable whole-lung computed tomography features for robust standard radiomics and delta-radiomics analysis in a nonhuman primate model of coronavirus disease 2019.

Purpose: We propose a method to identify sensitive and reliable whole-lung radiomic features from computed tomography (CT) images in a nonhuman primate model of coronavirus disease 2019 (COVID-19). Criteria used for feature selection in this method may improve the performance and robustness of predictive models. Approach: Fourteen crab-eating macaques were assigned to two experimental groups and exposed to either severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) or a mock inoculum. High-resolution CT scans were acquired before exposure and on several post-exposure days. Lung volumes were segmented using a deep-learning methodology, and radiomic features were extracted from the original image. The reliability of each feature was assessed by the intraclass correlation coefficient (ICC) using the mock-exposed group data. The sensitivity of each feature was assessed using the virus-exposed group data by defining a factor R that estimates the excess of variation above the maximum normal variation computed in the mock-exposed group. R and ICC were used to rank features and identify non-sensitive and unstable features. Results: Out of 111 radiomic features, 43% had excellent reliability ( ICC > 0.90 ), and 55% had either good ( ICC > 0.75 ) or moderate ( ICC > 0.50 ) reliability. Nineteen features were not sensitive to the radiological manifestations of SARS-CoV-2 exposure. The sensitivity of features showed patterns that suggested a correlation with the radiological manifestations. Conclusions: Features were quantified and ranked based on their sensitivity and reliability. Features to be excluded to create more robust models were identified. Applicability to similar viral pneumonia studies is also possible.

Toward the determination of sensitive and reliable whole-lung computed tomography features for robust standard radiomics and delta-radiomics analysis in a nonhuman primate model of coronavirus disease 2019

. Purpose We propose a method to identify sensitive and reliable whole-lung radiomic features from computed tomography (CT) images in a nonhuman primate model of coronavirus disease 2019 (COVID-19). Criteria used for feature selection in this method may improve the performance and robustness of predictive models. Approach Fourteen crab-eating macaques were assigned to two experimental groups and exposed to either severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) or a mock inoculum. High-resolution CT scans were acquired before exposure and on several post-exposure days. Lung volumes were segmented using a deep-learning methodology, and radiomic features were extracted from the original image. The reliability of each feature was assessed by the intraclass correlation coefficient (ICC) using the mock-exposed group data. The sensitivity of each feature was assessed using the virus-exposed group data by defining a factor R that estimates the excess of variation above the maximum normal variation computed in the mock-exposed group. R and ICC were used to rank features and identify non-sensitive and unstable features. Results Out of 111 radiomic features, 43% had excellent reliability ( Conclusions Features were quantified and ranked based on their sensitivity and reliability. Features to be excluded to create more robust models were identified. Applicability to similar viral pneumonia studies is also possible.

Duplex One-Step RT-qPCR Assays for Simultaneous Detection of Genomic and Subgenomic RNAs of SARS-CoV-2 Variants.

A hallmark of severe acute respiratory syndrome virus (SARS-CoV-2) replication is the discontinuous transcription of open reading frames (ORFs) encoding structural virus proteins. Real-time reverse transcription PCR (RT-qPCR) assays in previous publications used either single or multiplex assays for SARS-CoV-2 genomic RNA detection and a singleplex approach for subgenomic RNA detection. Although multiplex approaches often target multiple genomic RNA segments, an assay that concurrently detects genomic and subgenomic targets has been lacking. To bridge this gap, we developed two duplex one-step RT-qPCR assays that detect SARS-CoV-2 genomic ORF1a and either subgenomic spike or subgenomic ORF3a RNAs. All primers and probes for our assays were designed to bind to variants of SARS-CoV-2. In this study, our assays successfully detected SARS-CoV-2 Washington strain and delta variant isolates at various time points during the course of live virus infection in vitro. The ability to quantify subgenomic SARS-CoV-2 RNA is important, as it may indicate the presence of active replication, particularly in samples collected longitudinally. Furthermore, specific detection of genomic and subgenomic RNAs simultaneously in a single reaction increases assay efficiency, potentially leading to expedited lucidity about viral replication and pathogenesis of any variant of SARS-CoV-2.

Medical imaging of pulmonary disease in SARS-CoV-2-exposed non-human primates.

Chest X-ray (CXR), computed tomography (CT), and positron emission tomography-computed tomography (PET-CT) are noninvasive imaging techniques widely used in human and veterinary pulmonary research and medicine. These techniques have recently been applied in studies of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-exposed non-human primates (NHPs) to complement virological assessments with meaningful translational readouts of lung disease. Our review of the literature indicates that medical imaging of SARS-CoV-2-exposed NHPs enables high-resolution qualitative and quantitative characterization of disease otherwise clinically invisible and potentially provides user-independent and unbiased evaluation of medical countermeasures (MCMs). However, we also found high variability in image acquisition and analysis protocols among studies. These findings uncover an urgent need to improve standardization and ensure direct comparability across studies.

Sangivamycin is highly effective against SARS-CoV-2 in vitro and has favorable drug properties.

Sangivamycin is a nucleoside analog that is well tolerated by humans and broadly active against phylogenetically distinct viruses, including arenaviruses, filoviruses, and orthopoxviruses. Here, we show that sangivamycin is a potent antiviral against multiple variants of replicative severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with half-maximal inhibitory concentration in the nanomolar range in several cell types. Sangivamycin suppressed SARS-CoV-2 replication with greater efficacy than remdesivir (another broad-spectrum nucleoside analog). When we investigated sangivamycin's potential for clinical administration, pharmacokinetic; absorption, distribution, metabolism, and excretion (ADME); and toxicity properties were found to be favorable. When tested in combination with remdesivir, efficacy was additive rather than competitive against SARS-CoV-2. The proven safety in humans, long half-life, potent antiviral activity (compared to remdesivir), and combinatorial potential suggest that sangivamycin is likely to be efficacious alone or in combination therapy to suppress viremia in patients. Sangivamycin may also have the ability to help combat drug-resistant or vaccine-escaping SARS-CoV-2 variants since it is antivirally active against several tested variants. Our results support the pursuit of sangivamycin for further preclinical and clinical development as a potential coronavirus disease 2019 therapeutic.

COVID-19 - prime time for microphysiological systems, as illustrated for the brain.

The development of therapies for and preventions against infectious diseases depends on the availability of disease models. Bioengineering of human organoids and organs-on-chips is one extremely promising avenue of research. These miniature, laboratory-grown organ systems have been broadly used during the ongoing, unprecedented coronavirus 2019 (COVID-19) pandemic to show the many effects of the etiologic agent, severe acute respiratory coronavirus 2 (SARS-CoV-2) on human organs. In contrast, exposure of most animals either did not result in infection or caused mild clinical signs - not the severe course of the infection suffered by many humans. This article illuminates the opportunities of microphysiological systems (MPS) to study COVID-19 in vitro, with a focus on brain cell infection and its translational rel-evance to COVID-19 effects on the human brain. Neurovirulence of SARS-CoV-2 has been reproduced in different types of human brain organoids by 10 groups, consistently showing infection of a small portion of brain cells accompanied by limited viral replication. This mirrors increasingly recognized neurological manifestations in COVID-19 patients (evidence of virus infection and brain-specific antibody formation in brain tissue and cerebrospinal fluid). The pathogenesis of neuro-logical signs, their long-term consequences, and possible interventions remain unclear, but future MPS technologies offer prospects to address these open questions.

Animal models for COVID-19.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the aetiological agent of coronavirus disease 2019 (COVID-19), an emerging respiratory infection caused by the introduction of a novel coronavirus into humans late in 2019 (first detected in Hubei province, China). As of 18 September 2020, SARS-CoV-2 has spread to 215 countries, has infected more than 30 million people and has caused more than 950,000 deaths. As humans do not have pre-existing immunity to SARS-CoV-2, there is an urgent need to develop therapeutic agents and vaccines to mitigate the current pandemic and to prevent the re-emergence of COVID-19. In February 2020, the World Health Organization (WHO) assembled an international panel to develop animal models for COVID-19 to accelerate the testing of vaccines and therapeutic agents. Here we summarize the findings to date and provides relevant information for preclinical testing of vaccine candidates and therapeutic agents for COVID-19.

Molecular detection of SARS-CoV-2 in formalin-fixed, paraffin-embedded specimens.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause of human coronavirus disease 2019 (COVID-19), emerged in Wuhan, China, in December 2019. The virus rapidly spread globally, resulting in a public health crisis including almost 5 million cases and 323,256 deaths as of May 21, 2020. Here, we describe the identification and evaluation of commercially available reagents and assays for the molecular detection of SARS-CoV-2 in infected FFPE cell pellets. We identified a suitable rabbit polyclonal anti-SARS-CoV spike protein antibody and a mouse monoclonal anti-SARS-CoV nucleocapsid protein (NP) antibody for cross-detection of the respective SARS-CoV-2 proteins by IHC and immunofluorescence assay (IFA). Next, we established RNAscope in situ hybridization (ISH) to detect SARS-CoV-2 RNA. Furthermore, we established a multiplex FISH (mFISH) to detect positive-sense SARS-CoV-2 RNA and negative-sense SARS-CoV-2 RNA (a replicative intermediate indicating viral replication). Finally, we developed a dual staining assay using IHC and ISH to detect SARS-CoV-2 antigen and RNA in the same FFPE section. It is hoped that these reagents and assays will accelerate COVID-19 pathogenesis studies in humans and in COVID-19 animal models.