ILC-Unet plus plus for Covid-19 Infection Segmentation

Since the appearance of Covid-19 pandemic, in the end of 2019, Medical Imaging has been widely used to analysis this disease. In fact, CT-scans of the Lung can help to diagnosis, detect and quantify Covid-19 infection. In this paper, we address the segmentation of Covid-19 infection from CT-scans. In more details, we propose a CNN-based segmentation architecture named ILC-Unet++. The proposed ILC-Unet++ architecture, which is trained for both Covid-19 Infection and Lung Segmentation. The proposed architecture were tested using three datasets with two scenarios (intra and cross datasets). The experimental results showed that the proposed architecture performs better than three baseline segmentation architectures (Unet, Unet++ and Attention-Unet) and two Covid-19 infection segmentation architectures (SCOATNet and nCoVSegNet).

ILC-Unet++ for Covid-19 Infection Segmentation

Since the appearance of Covid-19 pandemic, in the end of 2019, Medical Imaging has been widely used to analysis this disease. In fact, CT-scans of the Lung can help to diagnosis, detect and quantify Covid-19 infection. In this paper, we address the segmentation of Covid-19 infection from CT-scans. In more details, we propose a CNN-based segmentation architecture named ILC-Unet++. The proposed ILC-Unet++ architecture, which is trained for both Covid-19 Infection and Lung Segmentation. The proposed architecture were tested using three datasets with two scenarios (intra and cross datasets). The experimental results showed that the proposed architecture performs better than three baseline segmentation architectures (Unet, Unet++ and Attention-Unet) and two Covid-19 infection segmentation architectures (SCOATNet and nCoVSegNet). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Can HbA1c levels be used as an independent marker of mortality and morbidity risk in patients with COVID-19 positive swabs?

Background: Diabetes mellitus has been considered a significant risk factor for morbidity and mortality for COVID-19.1 HbA1c levels are often used as a marker of poor glycaemic control and are one way of diagnosing pre-diabetes as well as diabetes.2,3 We tried to explore whether HbA1c levels could be an independent risk factor for mortality and morbidity in patients with positive coronavirus (SARS-COv-2) swabs. Methods: This was a retrospective multicentre study of coronavirus swab positive patients who had a recent HbA1c test. Their demographic data, medical history, COVID-19 swab and laboratory results, and final outcomes were analysed. Patients were divided into three groups;HbA1c in normal (group 1), pre-diabetic (group 2) and diabetic (group 3) ranges. Data were analysed using JASP and statistical computation using a χ2 test. Results: A total of 1,226 patients had SARS-CoV-2 RNA identification swabs between 10 February 2020 and 1 May 2020. A cohort of 120 of these patients had positive swab results and recent HbA1c results. Mortality rates for group 1 (normal HbA1c) and 3 (diabetic HbA1c) were relatively higher than group 2 (pre-diabetic HbA1c). Among group 2, female patients had greater mortality, perhaps because of fewer male patients, although overall co-morbidity was less (4/120 (3.33%) in group 2 compared with 18/120 (15%) in group 1 and 14/120 (11.66%) in group 3. Overall, 36/120 (30%) patients died and 84/120 (70%) survived. Survival curves after analysis of data showed that increasing HbA1c levels were associated with poorer outcomes across all groups. Analysis was significant with p=0.003. Conclusions: HbA1c levels in this study were an independent marker of increased risk of mortality in COVID-19 swab positive patients. The findings are statistically significant (p=0.003). Increased co-morbidities at normal HbA1c seem to have a contributing role in enhanced mortality.

Consequences of SARS-CoV-2 disease on maternal, perinatal and neonatal outcomes: A retrospective observational cohort study

Novel coronavirus disease 2019 (COVID-19) continues to affect pregnant women with concerns for adverse maternal and fetal outcomes and is rapidly spreading throughout many countries since it was first reported in China on 31 December 2019. The aim of this study is to describe characteristics, maternal and fetal outcomes among mothers with confirmed maternal SARS-CoV-2 infection. This study presents a retrospective observational cohort study of 62 test-positive cases of coronavirus disease 2019 that presented at an affiliated tertiary university medical city from March 2020 to May 2020. A total of 14 patients (22.5%) presented with obvious typical symptoms of coronavirus disease 2019 associated viremia and were identified after they developed symptoms during admission or after the implementation of universal testing for all obstetric admissions. A total of 62 mothers were screened positive for the SARS-CoV-2 infection. Length of stay was higher in the symptomatic group. The median length of stay was 4 days for the asymptomatic cases while it was 6 days for the symptomatic cases. Amniotic fluid was meconium stained in (12.5%) of the asymptomatic group and in 30.8% in the symptomatic group. Post discharge mothers with asymptomatic SARS-CoV-2 infection were more likely to breastfeed their infants. OR (95% CI) was 1.4 (1.02-1.90) and P-value was 0.0327. There was non-statistically significant absence of perinatal morbidities or mortalities among symptomatic and asymptomatic mothers.