Unsupervised segmentation and quantification of COVID-19 lesions on computed Tomography scans using CycleGAN.

BACKGROUND: 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 a method for fully automated segmentation and quantification of pathological COVID-19 lung tissue on chest Computed Tomography (CT) scans without the need for manually segmented training data. METHODS: We trained a cycle-consistent generative adversarial network (CycleGAN) to convert images of COVID-19 scans into their generated healthy equivalents. Subtraction of the generated healthy images from their corresponding original CT scans yielded maps of pathological tissue, without background lung parenchyma, fissures, airways, or vessels. We then used these maps to construct three-dimensional lesion segmentations. Using a validation dataset, Dice scores were computed for our lesion segmentations and other published segmentation networks using ground truth segmentations reviewed by radiologists. RESULTS: The COVID-to-Healthy generator eliminated high Hounsfield unit (HU) voxels within pulmonary lesions and replaced them with lower HU voxels. The generator did not distort normal anatomy such as vessels, airways, or fissures. The generated healthy images had higher gas content (2.45 ± 0.93 vs 3.01 ± 0.84 L, P < 0.001) and lower tissue density (1.27 ± 0.40 vs 0.73 ± 0.29 Kg, P < 0.001) than their corresponding original COVID-19 images, and they were not significantly different from those of the healthy images (P < 0.001). Using the validation dataset, lesion segmentations scored an average Dice score of 55.9, comparable to other weakly supervised networks that do require manual segmentations. CONCLUSION: Our CycleGAN model successfully segmented pulmonary lesions in mild and severe COVID-19 cases. Our model's performance was comparable to other published models; however, our model is unique in its ability to segment lesions without the need for manual segmentations.

"I have the strength to get through this using my past experiences with HIV": findings from a mixed-method survey of health outcomes, service accessibility, and psychosocial wellbeing among people living with HIV during the Covid-19 pandemic.

We examined the impact of Covid-19 restrictions on the wellbeing and access to care among people living with HIV (PLWH) in the UK. A cross-sectional anonymous online survey was circulated to PLWH attending care at three HIV services in Sussex. The questionnaire covered key themes: socio-demographic characteristics; changes in physical and mental health; accessibility of essential health services and information; and socio-economic concerns. Free-text qualitative responses were examined through framework analysis. Quantitative data from 653 respondents were available, with a subset of 385 free-text qualitative responses. In terms of mental health, 501 (77.6%) respondents reported feeling more anxious; 464 (71.8%) reported feeling more depressed than usual; and 128 (19.8%) reported having suicidal thoughts since the start of the pandemic. Respondents worried about running out of HIV medicine (n = 264, 40.7%); accessing HIV services (n = 246, 38.0%) as well as other health services (n = 408, 63.0%). Widespread resilience was also noted: 537 (83.3%) of respondents felt that living with HIV had equipped them with the strength to adapt to the Covid-19 pandemic. Findings highlight important gaps between the multifaceted needs of PLWH. Multisectoral collaborations and investments are needed to adequately support PLWH and to build resilience to future shocks within HIV services.

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network.

The purpose of this study was to develop a fully-automated segmentation algorithm, robust to various density enhancing lung abnormalities, to facilitate rapid quantitative analysis of computed tomography images. A polymorphic training approach is proposed, in which both specifically labeled left and right lungs of humans with COPD, and nonspecifically labeled lungs of animals with acute lung injury, were incorporated into training a single neural network. The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. Performance of the proposed lung segmentation algorithm was extensively evaluated on CT scans of subjects with COPD, confirmed COVID-19, lung cancer, and IPF, despite no labeled training data of the latter three diseases. Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. The proposed lung segmentation algorithm was quantitatively evaluated using semi-automated and manually-corrected segmentations in 87 COVID-19 CT images, achieving an average symmetric surface distance of [Formula: see text] mm and Dice coefficient of [Formula: see text]. Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. However, the most severe cases demonstrated involvement of all lobes. The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.

An Update on Pulmonary Hypertension in Coronavirus Disease-19 (COVID-19).

Coronavirus 19 disease (COVID-19) continues to be a pandemic with global implications.  Respiratory system involvement is the most common manifestation in symptomatic patients.  In this literature review, we describe the diagnosis, management, and implications of pulmonary hypertension (PH) among patients with COVID-19.  We defined pulmonary hypertension as increasing mean pulmonary artery pressure (mPAP) of ≥ 25 mm Hg at rest.  In our literature search, we identified 4 articles with details on pulmonary hypertension.  Among these, two reported various echocardiographic details for diagnosing pulmonary hypertension.  In 1 study evidence of pulmonary hypertension was noted in 13.4% of patients.  Patients with severe COVID-19 were reported to have a higher proportion of pulmonary hypertension as compared to mild COVID-19 disease [22% vs 2%].  Elevated pulmonary artery systolic pressure was significant in predicting mortality.  COVID-19 patients with chronic obstructive pulmonary disease, congestive heart failure, myocardial injury, pulmonary embolism, and prior pulmonary hypertension were at a higher risk of worsening pulmonary hypertension.  Multiple mechanisms for developing pulmonary hypertension that have been postulated are i) concomitant worsening myocardial injury, ii) cytokine storm, endothelial injury, hypercoagulability attributing to development of venous thromboembolism, iii) and the presence of thrombotic microangiopathy.  Among patients with severe COVID-19 disease and pulmonary hypertension, complications including acute respiratory distress syndrome, acute myocardial injury, the requirement of intensive care unit admission, the requirement of mechanical ventilation, and mortality are higher.

COVID-19 and residential care facilities: issues and concerns identified by the international network prevention of elder abuse (INPEA)

PurposeThe COVID-19 pandemic has affected the physical, psychological, social and financial health of older persons. On this subject, the United Nations published a policy brief on the impact of COVID-19 on older persons in May 2020. In line with this, the purpose of this general review is to address three issues affecting older persons living in residential care facilities: protective measures implemented to block the virus’ entry, the types of mistreatment most frequently experienced and the necessity to promote and defend the rights of these persons.Design/methodology/approachThe design of this study is based on input gathered since the end of April during meetings of the International Network for the Prevention of Elder Abuse (INPEA) and the results of a July survey of its members.FindingsThe survey results indicate variability in the implementation of protective measures in different countries and the significant presence of mistreatment and violation of the rights of older persons. Three major issues demand attention: ageism, systemic and managerial problems and the effects of implemented measures. All these prompt the INPEA to once again plea for the adoption of an international convention of human rights of older persons.Originality/valueTo our knowledge, this is the first article sharing the views of the INPEA from a global perspective in the context of COVID-19.

Household Items-Based Personalized Video Rehabilitation amidst the COVID-19 Pandemic: Handouts We All Wish We Had

Category: Ankle;Sports Introduction/Purpose: Rehabilitation is vital in the recovery of countless foot and ankle injuries and operations.1With our attention directed to providing care on the frontlines of the COVID-19 pandemic, rehabilitation has fallen by the wayside with poor consequences. Access to outpatient rehabilitation services and their specialized exercise equipment has significantly decreased,2 leaving patients feeling abandoned and surgeons looking for help on how to guide patients’ postoperative rehabilitation. This poster serves to introduce household items-based personalized video rehabilitation (PVR). Methods: Rehabilitation exercise videos were produced by a board-certified athletic trainer and board-certified orthopaedic foot and ankle surgeon. The videos showed how to perform rehabilitation exercises with common household items (Figure 3).The videos were produced in a structured order, explaining the purpose of the exercise, showing what household items are needed, and demonstrating the proper technique of the exercise. Following recording of the videos, they were assembled into injury/scenario-specific infographics (Figure 1). Results: 34 rehabilitation exercise videos were recorded, with an average length of two minutes, 11 seconds.11 injury/scenario- specific infographics were assembled, with each page of an infographic containing seven exercises (Figure 1), with specific information and access for each exercise (Figure 2).Patients can access the videos by clicking on the hyperlink, or by scanning the QR code. When giving infographics, healthcare professionals can guide patients on which exercises to perform. Conclusion: Household items-based PVR provides patients with an interactive infographic that gives access to concise videos of rehabilitation exercises, especially during a time of reduced rehabilitation accessibility. Healthcare professionals can assign patient- specific exercises on the infographic that are appropriate for a patients’ phase of rehabilitation. Not meant to replace the current rehabilitation model, household item-based PVR is a paradigm shift that will allow physicians to bridge gaps in care.

COVID-19 and restrictive lung disease: A deadly combo to trip off the fine balance.

Coronavirus Disease (COVID-19) pandemic has so far led to innumerable deaths worldwide. The risk factors so far that have been most studied as poor prognostic factors are old age, individuals with multiple comorbidities and immunocompromised patients. Amongst the chronic lung diseases, most patients with COVID-19 reported so far had asthma, chronic obstructive pulmonary disease (COPD), and interstitial lung disease. Herein, we discuss the significance of restrictive lung disease during the COVID-19 pandemic as a potential risk factor via an example of a patient with kyphoscoliosis who succumbed to death due to COVID-19 pneumonia.

COVID-19 and clinical mimics. Correct diagnosis is the key to appropriate therapy.

As of 29 April 2020, across the globe, there are 3,216,353 confirmed Coronavirus disease 2019 (COVID-19 disease) with 227,894 deaths. The health care infrastructure of most of the countries is overwhelmed due to the gigantic upsurge of the new cases within a short time period. Most of the beds in the regular wards and critical care units are currently occupied by either people under investigation (PUI) or COVID-19 confirmed cases. We hereby discuss the challenges faced while approaching any case of shortness of breath, or other common upper respiratory symptoms during the current COVID-19 pandemic era.