ABSTRACT
BACKGROUND: Helmet continuous positive airway pressure (CPAP) has been widely used during the COVID-19 pandemic. Specific filters (i.e. High Efficiency Particulate Air filter: HEPA; Heat & Moisture Exchanger Filter: HMEF) were used to prevent Sars-CoV2 environmental dispersion and were connected to the CPAP helmet. However, HEPA and HMEF filters may act as resistors to expiratory gas flow and increase the levels of pressure within the hood. METHODS: In a bench-top study, we investigated the levels of airway pressure generated by different HEPA and HMEF filters connected to the CPAP helmet in the absence of a Positive End Expiratory Pressure (PEEP) valve and with two levels of PEEP (5 and 10 cmH2O). All steps were performed using 3 increasing levels of gas flow (60, 80, 100 L/min). RESULTS: The use of 8 different commercially available filters significantly increased the pressure within the hood of the CPAP helmet with or without the use of PEEP valves. On average, the increase of pressure above the set PEEP ranged from 3 cmH2O to 10 cmH2O across gas flow rates of 60 to 100 L/min. The measure of airway pressure was highly correlated between the laboratory pressure transducer and the Helmet manometer. Bias with 95% Confidence Interval of Bias between the devices was 0.7 (-2.06; 0.66) cmH2O. CONCLUSIONS: The use of HEPA and HMEF filters placed before the PEEP valve at the expiratory port of the CPAP helmet significantly increase the levels of airway pressure compared to the set level of PEEP. The manometer can detect accurately the airway pressure in the presence of HEPA and HMEF filters in the helmet CPAP and its use should considered.
ABSTRACT
Rationale: Lesion segmentation is a critical step in medical image analysis, and methods to identify pathology without time-intensive manual labeling of data are of utmost importance during a pandemic and in resource-constrained healthcare settings. Here, we describe an unsupervised method of automatic lesion segmentation and quantification of COVID-19 lung tissue on chest Computed Tomography (CT) scans. Methods: Anonymized human COVID-19 (n=53), and non-pathologic control (n=87) inspiratory CT scans were used to train a publically available cycle-consistent generative adversarial network (CycleGAN), to convert the COVID-19 CT scans into generated "healthy" equivalents. Difference maps were created by subtracting the Hounsfield Units (HU) value for each voxel in the generated image from that of the original COVID-19 image. We then used these difference maps to construct 3D lesion segmentations to further quantitatively characterize COVID-19 lesions in an automated pipeline. Results: The CycleGAN produced lesion segmentations from COVID-19 CT scans of varying radiologic severity ranging from cases of patchy ground glass opacities to diffuse consolidative lesions. Images of COVID-19 patients showed higher HU intensity in original vs. generated images at sites of pulmonary lesions, while preserving normal parenchyma, fissures, vasculature, and airways (Figure 1, upper panels). The generated images showed larger lung gas volumes and lower tissue masses compared to their corresponding original COVID-19 images (p<0.001). Subtraction of the generated images from their corresponding original COVID-19 CT scans yielded difference maps showing the pathological tissue alone (Figure 1). Control, non-pathologic CT images were given as input to the CycleGAN, resulting in generated images nearly superimposable with the originals with no difference in gas volume or tissue mass (Figure 1, lower panel). Conclusions: To our knowledge, this is the first unsupervised COVID-19 lesion segmentation approach. Our automated lesion model performed well in mild and severe COVID-19 cases without the need for manually labelled lung segmentations as inputs. An automated lesion segmentation model can be used clinically to rapidly and objectively quantify pathologic pulmonary tissue to inform disease prognosis and treatment. Automated radiologic techniques, such as our model, circumvent the traditional bottle-neck of manually labeling data which has limited the scale and thus the impact of quantitative radiologic medical research.