Misra, Durga Prasanna

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

Background: COVID-19 lung segmentation using Computed Tomography (CT) scans is important for the diagnosis of lung severity. The process of automated lung segmentation is challenging due to (a) CT radiation dosage and (b) ground-glass opacities caused by COVID-19. The lung segmentation methodologies proposed in 2020 were semi- or automated but not reliable, accurate, and user-friendly. The proposed study presents a COVID Lung Image Analysis System (COVLIAS 1.0, AtheroPoint™, Roseville, CA, USA) consisting of hybrid deep learning (HDL) models for lung segmentation. Methodology: The COVLIAS 1.0 consists of three methods based on solo deep learning (SDL) or hybrid deep learning (HDL). SegNet is proposed in the SDL category while VGG-SegNet and ResNet-SegNet are designed under the HDL paradigm. The three proposed AI approaches were benchmarked against the National Institute of Health (NIH)-based conventional segmentation model using fuzzy-connectedness. A cross-validation protocol with a 40:60 ratio between training and testing was designed, with 10% validation data. The ground truth (GT) was manually traced by a radiologist trained personnel. For performance evaluation, nine different criteria were selected to perform the evaluation of SDL or HDL lung segmentation regions and lungs long axis against GT. Results: Using the database of 5000 chest CT images (from 72 patients), COVLIAS 1.0 yielded AUC of ~0.96, ~0.97, ~0.98, and ~0.96 (p-value < 0.001), respectively within 5% range of GT area, for SegNet, VGG-SegNet, ResNet-SegNet, and NIH. The mean Figure of Merit using four models (left and right lung) was above 94%. On benchmarking against the National Institute of Health (NIH) segmentation method, the proposed model demonstrated a 58% and 44% improvement in ResNet-SegNet, 52% and 36% improvement in VGG-SegNet for lung area, and lung long axis, respectively. The PE statistics performance was in the following order: ResNet-SegNet > VGG-SegNet > NIH > SegNet. The HDL runs in <1 s on test data per image. Conclusions: The COVLIAS 1.0 system can be applied in real-time for radiology-based clinical settings.

Aim The objective was to examine the prevalence of atherosclerotic cardiovascular disease (ASCVD) and its risk factors among patients with RA with diabetes mellitus (RA-DM) and patients with RA without diabetes mellitus (RAwoDM), and to evaluate lipid and blood pressure (BP) goal attainment in RA-DM and RAwoDM in primary and secondary prevention. Methods The cohort was derived from the Survey of Cardiovascular Disease Risk Factors in Patients with Rheumatoid Arthritis from 53 centres/19 countries/3 continents during 2014–2019. We evaluated the prevalence of cardiovascular disease (CVD) among RA-DM and RAwoDM. The study population was divided into those with and without ASCVD, and within these groups we compared risk factors and CVD preventive treatment between RA-DM and RAwoDM. Results The study population comprised of 10 543 patients with RA, of whom 1381 (13%) had DM. ASCVD was present in 26.7% in RA-DM compared with 11.6% RAwoDM (p<0.001). The proportion of patients with a diagnosis of hypertension, hyperlipidaemia and use of lipid-lowering or antihypertensive agents was higher among RA-DM than RAwoDM (p<0.001 for all). The majority of patients with ASCVD did not reach the lipid goal of low-density lipoprotein cholesterol <1.8 mmol/L. The lipid goal attainment was statistically and clinically significantly higher in RA-DM compared with RAwoDM both for patients with and without ASCVD. The systolic BP target of <140 mm Hg was reached by the majority of patients, and there were no statistically nor clinically significant differences in attainment of BP targets between RA-DM and RAwoDM. Conclusion CVD preventive medication use and prevalence of ASCVD were higher in RA-DM than in RAwoDM, and lipid goals were also more frequently obtained in RA-DM. Lessons may be learnt from CVD prevention programmes in DM to clinically benefit patients with RA .

Abstract Aims To assess differences in estimated cardiovascular disease (CVD) risk among rheumatoid arthritis (RA) patients from different world regions and to evaluate the management and goal attainment of lipids and blood pressure (BP). Methods and results The survey of CVD risk factors in patients with RA was conducted in 14 503 patients from 19 countries during 2014–19. The treatment goal for BP was &lt;140/90 mmHg. CVD risk prediction and lipid goals were according to the 2016 European guidelines. Overall, 21% had a very high estimated risk of CVD, ranging from 5% in Mexico, 15% in Asia, 19% in Northern Europe, to 31% in Central and Eastern Europe and 30% in North America. Of the 52% with indication for lipid-lowering treatment (LLT), 44% were using LLT. The lipid goal attainment was 45% and 18% in the high and very high risk groups, respectively. Use of statins in monotherapy was 24%, while 1% used statins in combination with other LLT. Sixty-two per cent had hypertension and approximately half of these patients were at BP goal. The majority of the patients used antihypertensive treatment in monotherapy (24%), while 10% and 5% as a two- or three-drug combination. Conclusion We revealed considerable geographical differences in estimated CVD risk and preventive treatment. Low goal attainment for LLT was observed, and only half the patients obtained BP goal. Despite a high focus on the increased CVD risk in RA patients over the last decade, there is still substantial potential for improvement in CVD preventive measures.