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

Deep-learning segmentation to select liver parenchyma for categorizing hepatic steatosis on multinational chest CT

Unenhanced CT scans exhibit high specificity in detecting moderate-to-severe hepatic steatosis. Even though many CTs are scanned from health screening and various diagnostic contexts, their potential for hepatic steatosis detection has largely remained unexplored. The accuracy of previous methodologies has been limited by the inclusion of non-parenchymal liver regions. To overcome this limitation, we present a novel deep-learning (DL) based method tailored for the automatic selection of parenchymal portions in CT images. This innovative method automatically delineates circular regions for effectively detecting hepatic steatosis. We use 1,014 multinational CT images to develop a DL model for segmenting liver and selecting the parenchymal regions. The results demonstrate outstanding performance in both tasks. By excluding non-parenchymal portions, our DL-based method surpasses previous limitations, achieving radiologist-level accuracy in liver attenuation measurements and hepatic steatosis detection. To ensure the reproducibility, we have openly shared 1014 annotated CT images and the DL system codes. Our novel research contributes to the refinement the automated detection methodologies of hepatic steatosis on CT images, enhancing the accuracy and efficiency of healthcare screening processes.

Chest CT in covid-19 pneumonia's follow-up: A 30 patients case series

Background

Lung abnormalities do not fully resolve in all Covid-19 survivors and may progress to fibrosis. Understanding post-COVID lung changes helps identify patients susceptible of post-COVID-19 sequelae. We analyzed scannographic residual lung abnormalities and the full resolution percentage on intermediate- and long-term follow-up (3 months or more).

Methods

Data from 30 RT-PCR positive COVID-19 patients undergoing at least one follow-up chest CT at Ibn Sina Hospital, with a minimal time interval of 3 months between the RT-PCR and the CT performance were gathered retrospectively. The following elements were analyzed: (1) lung opacities, (2) distribution, (3) dominant lung opacity, (4) Sub-pleural bands, (5) Interlobular septal thickening, (6) Vascular dilatation, (7) Bronchiectasis, (8) Honey combing, (9) Architectural distortion, (10) mosaic attenuation, and (11) Additional findings: Enlarged lymph nodes, Pleural and Pericardial fluid. To evaluate the degree of lung opacification, a score founded on visual evaluation of the lung involvement's percentage was employed. Patients were then subdivided into two categories: (1) no residual opacities and (2) remaining pulmonary opacities.

Outcomes

30 patients were enrolled. The age ranged between 40 and 87 years. CT was indicated for symptoms or functional impairment. The time range between the positive RT-PCR and Follow-up CT varied between 3 and 12 months. CT severity score ranged between o and 23. Residual lung opacities were present in 24 cases (80%). The dominant lung opacities were Ground glass (46.7%), and linear/curvilinear opacities (23.3%). Signs of fibrosis were present in 9 patients (30%).

Conclusion

CT abnormalities following Covid-19 pneumonia's prevalence varies based on the extent of the original lung affection and the time gap since the acute phase. Residual anomalies' effects on respiratory physiology, symptoms, and quality of living are unknown. Maintained monitoring of COVID-19 survivors with clinical examination, iterative pulmonary function tests, and HRCT is advised.

COVID-MTL: Multitask learning with Shift3D and random-weighted loss for COVID-19 diagnosis and severity assessment

There is an urgent need for automated methods to assist accurate and effective assessment of COVID-19. Radiology and nucleic acid test (NAT) are complementary COVID-19 diagnosis methods. In this paper, we present an end-to-end multitask learning (MTL) framework (COVID-MTL) that is capable of automated and simultaneous detection (against both radiology and NAT) and severity assessment of COVID-19. COVID-MTL learns different COVID-19 tasks in parallel through our novel random-weighted loss function, which assigns learning weights under Dirichlet distribution to prevent task dominance; our new 3D real-time augmentation algorithm (Shift3D) introduces space variances for 3D CNN components by shifting low-level feature representations of volumetric inputs in three dimensions; thereby, the MTL framework is able to accelerate convergence and improve joint learning performance compared to single-task models. By only using chest CT scans, COVID-MTL was trained on 930 CT scans and tested on separate 399 cases. COVID-MTL achieved AUCs of 0.939 and 0.846, and accuracies of 90.23% and 79.20% for detection of COVID-19 against radiology and NAT, respectively, which outperformed the state-of-the-art models. Meanwhile, COVID-MTL yielded AUC of 0.800 ± 0.020 and 0.813 ± 0.021 (with transfer learning) for classifying control/suspected, mild/regular, and severe/critically-ill cases. To decipher the recognition mechanism, we also identified high-throughput lung features that were significantly related (P < 0.001) to the positivity and severity of COVID-19.

Spatially distributed infection increases viral load in a computational model of SARS-CoV-2 lung infection

A key question in SARS-CoV-2 infection is why viral loads and patient outcomes vary dramatically across individuals. Because spatial-temporal dynamics of viral spread and immune response are challenging to study in vivo, we developed Spatial Immune Model of Coronavirus (SIMCoV), a scalable computational model that simulates hundreds of millions of lung cells, including respiratory epithelial cells and T cells. SIMCoV replicates viral growth dynamics observed in patients and shows how spatially dispersed infections can lead to increased viral loads. The model also shows how the timing and strength of the T cell response can affect viral persistence, oscillations, and control. By incorporating spatial interactions, SIMCoV provides a parsimonious explanation for the dramatically different viral load trajectories among patients by varying only the number of initial sites of infection and the magnitude and timing of the T cell immune response. When the branching airway structure of the lung is explicitly represented, we find that virus spreads faster than in a 2D layer of epithelial cells, but much more slowly than in an undifferentiated 3D grid or in a well-mixed differential equation model. These results illustrate how realistic, spatially explicit computational models can improve understanding of within-host dynamics of SARS-CoV-2 infection.

CT of Post-Acute Lung Complications of COVID-19

The acute course of COVID-19 is variable and ranges from asymptomatic infection to fulminant respiratory failure. Patients recovering from COVID-19 can have persistent symptoms and CT abnormalities of variable severity. At 3 months after acute infection, a subset of patients will have CT abnormalities that include ground-glass opacity (GGO) and subpleural bands with concomitant pulmonary function abnormalities. At 6 months after acute infection, some patients have persistent CT changes to include the resolution of GGOs seen in the early recovery phase and the persistence or development of changes suggestive of fibrosis, such as reticulation with or without parenchymal distortion. The etiology of lung disease after COVID-19 may be a sequela of prolonged mechanical ventilation, COVID-19-induced acute respiratory distress syndrome (ARDS), or direct injury from the virus. Predictors of lung disease after COVID-19 include need for intensive care unit admission, mechanical ventilation, higher inflammatory markers, longer hospital stay, and a diagnosis of ARDS. Treatments of lung disease after COVID-19 are being investigated, including the potential of antifibrotic agents for prevention of lung fibrosis after COVID-19. Future research is needed to determine the long-term persistence of lung disease after COVID-19, its impact on patients, and methods to either prevent or treat it. © RSNA, 2021.