Covid Visual Assessment Scale ("Co.V.A.Sc."): quantification of COVID-19 disease extent on admission chest computed tomography (CT) in the prediction of clinical outcome-a retrospective analysis of 273 patients.

BACKGROUND: Admission chest CT is often included in COVID-19 patient management. PURPOSE: To evaluate the inter- and intraobserver variability of the Covid Visual Assessment Scale ("Co.V.A.Sc.") used for stratifying chest CT disease extent and to estimate its prospect to predict clinical outcomes. MATERIALS AND METHODS: This single-center, retrospective observational cohort study included all RT-PCR-confirmed COVID-19 adult patients undergoing admission chest CT, between 01/03/2021 and 17/03/2021. CTs were independently evaluated by two radiologists according to the "Co.V.A.Sc." (0: 0%, 1: 1-10%, 2: 11-25%, 3: 26-50%, 4: 51-75%, 5: > 75%). Patient demographics, laboratory, clinical, and hospitalization data were retrieved and analyzed in relation to the "Co.V.A.Sc." RESULTS: Overall, 273 patients (mean age 60.7 ± 14.8 years; 50.9% male) were evaluated. Excellent inter- and intraobserver variability was noted between the two independent radiologists' "Co.V.A.Sc." EVALUATIONS: "Co.V.A.Sc." classification (Exp(B) 0.391, 95%CI 0.212-0.719; p = 0.025) and patient age (Exp(B) 0.947, 95%CI 0.902-0.993; p = 0.25) were the only variables correlated with ICU admission, while age (Exp(B) 1.111, p = 0.0001), "Co.V.A.Sc." (Exp(B) 2.408; p = 0.002), and male gender (Exp(B) 3.213; p = 0.028) were correlated with in-hospital mortality. Specifically, for each "Co.V.A.Sc." unit increase, the probability of ICU admission increased by 1.47 times, and the probability of death increased by 11.1 times. According to ROC analysis, "Co.V.A.Sc." could predict ICU admission and in-hospital death with an optimal cutoff value of unit 3 (sensitivity 56.0%, specificity 84.3%) and unit 4 (sensitivity 41.9%, specificity 93.6%), respectively. CONCLUSION: "Co.V.A.Sc." upon hospital admittance seems to predict ICU admission and in-hospital death and could aid in optimizing risk-stratification and patient management.

Deep learning networks on chronic liver disease assessment with fine-tuning of shear wave elastography image sequences.

Chronic liver disease (CLD) is currently one of the major causes of death worldwide. If not treated, it may lead to cirrhosis, hepatic carcinoma and death. Ultrasound (US) shear wave elastography (SWE) is a relatively new, popular, non-invasive technique among radiologists. Although many studies have been published validating the SWE technique either in a clinical setting, or by applying machine learning on SWE elastograms, minimal work has been done on comparing the performance of popular pre-trained deep learning networks on CLD assessment. Currently available literature reports suggest technical advancements on specific deep learning structures, with specific inputs and usually on a limited CLD fibrosis stage class group, with limited comparison on competitive deep learning schemes fed with different input types. The aim of the present study is to compare some popular deep learning pre-trained networks using temporally stable and full elastograms, with or without augmentation as well as propose suitable deep learning schemes for CLD diagnosis and progress assessment. 200 liver biopsy validated patients with CLD, underwent US SWE examination. Four images from the same liver area were saved to extract elastograms and processed to exclude areas that were temporally unstable. Then, full and temporally stable masked elastograms for each patient were separately fed into GoogLeNet, AlexNet, VGG16, ResNet50 and DenseNet201 with and without augmentation. The networks were tested for differentiation of CLD stages in seven classification schemes over 30 repetitions using liver biopsy as the reference. All networks achieved maximum mean accuracies ranging from 87.2%-97.4% and area under the receiver operating characteristic curves (AUCs) ranging from 0.979-0.990 while the radiologists had AUCs ranging from 0.800-0.870. ResNet50 and DenseNet201 had better average performance than the other networks. The use of the temporal stability mask led to improved performance on about 50% of inputs and network combinations while augmentation led to lower performance for all networks. These findings can provide potential networks with higher accuracy and better setting in the CLD diagnosis and progress assessment. A larger data set would help identify the best network and settings for CLD assessment in clinical practice.

Temporal stability assessment in shear wave elasticity images validated by deep learning neural network for chronic liver disease fibrosis stage assessment.

PURPOSE: To automatically detect and isolate areas of low and high stiffness temporal stability in shear wave elastography (SWE) image sequences and define their impact in chronic liver disease (CLD) diagnosis improvement by means of clinical examination study and deep learning algorithm employing convolutional neural networks (CNNs). MATERIALS AND METHODS: Two hundred SWE image sequences from 88 healthy individuals (F0 fibrosis stage) and 112 CLD patients (46 with mild fibrosis (F1), 16 with significant fibrosis (F2), 22 with severe fibrosis (F3), and 28 with cirrhosis (F4)) were analyzed to detect temporal stiffness stability between frames. An inverse Red, Green, Blue (RGB) colormap-to-stiffness process was performed for each image sequence, followed by a wavelet transform and fuzzy c-means clustering algorithm. This resulted in a binary mask depicting areas of high and low stiffness temporal stability. The mask was then applied to the first image of the SWE sequence, and the derived, masked SWE image was used to estimate its impact in standard clinical examination and CNN classification. Regarding the impact of the masked SWE image in clinical examination, one measurement by two radiologists was performed in each SWE image and two in the corresponding masked image measuring areas with high and low stiffness temporal stability. Then, stiffness stability parameters, interobserver variability evaluation and diagnostic performance by means of ROC analysis were assessed. The masked and unmasked sets of SWE images were fed into a CNN scheme for comparison. RESULTS: The clinical impact evaluation study showed that the masked SWE images decreased the interobserver variability of the radiologists' measurements in the high stiffness temporal stability areas (interclass correlation coefficient (ICC) = 0.92) compared to the corresponding unmasked ones (ICC = 0.76). In terms of diagnostic accuracy, measurements in the high-stability areas of the masked SWE images (area-under-the-curve (AUC) ranging from 0.800 to 0.851) performed similarly to those in the unmasked SWE images (AUC ranging from 0.805 to 0.893). Regarding the measurements in the low stiffness temporal stability areas of the masked SWE images, results for interobserver variability (ICC = 0.63) and diagnostic accuracy (AUC ranging from 0.622 to 0.791) were poor. Regarding the CNN classification, the masked SWE images showed improved accuracy (ranging from 82.5% to 95.5%) compared to the unmasked ones (ranging from 79.5% to 93.2%) for various CLD stage combinations. CONCLUSION: Our detection algorithm excludes unreliable areas in SWE images, reduces interobserver variability, and augments CNN's accuracy scores for many combinations of fibrosis stages.

Comparative Effectiveness of Plain Balloon Angioplasty, Bare Metal Stents, Drug-Coated Balloons, and Drug-Eluting Stents for the Treatment of Infrapopliteal Artery Disease: Systematic Review and Bayesian Network Meta-analysis of Randomized Controlled Trials.

PURPOSE: To report a Bayesian network meta-analysis of randomized controlled trials (RCTs) comparing bare metal stents (BMS), paclitaxel-coated balloons (PCBs), and drug-eluting stents (DES) with balloon angioplasty (BA) or with each other in the infrapopliteal arteries. METHODS: Sixteen RCTs comprising 1805 patients with 1-year median follow-up were analyzed. Bayesian random effects binomial models were employed (WinBUGS). Relative treatment effects were expressed as odds ratios (ORs) with 95% credible intervals (CrI), and the cumulative rank probabilities were calculated to provide hierarchies of competing treatments. Quality of evidence (QoE) was assessed with the GRADE (grading of recommendations assessment, development, and evaluation) system. Sensitivity, heterogeneity, and consistency analyses were performed. RESULTS: There was high QoE that infrapopliteal DES significantly reduced restenosis compared with BMS (OR 0.26, 95% CrI 0.12 to 0.51) and BA (OR 0.22, 95% CrI 0.11 to 0.45). Likewise, DES significantly reduced target lesion revascularization (TLR) compared with BA (OR 0.41, 95% CrI 0.22 to 0.75) and BMS (OR 0.26, 95% CrI 0.15 to 0.45). Paclitaxel-coated balloons also reduced TLR compared with BA (OR 0.55, 95% CrI 0.34 to 0.90) and BMS (OR 0.35, 95% CrI 0.18 to 0.67), but QoE was low to moderate. BA had lower TLR than BMS (OR 0.63, 95% CrI 0.40 to 0.99) with high QoE. DES was the only treatment that significantly reduced limb amputations compared with BA (OR 0.58, 95% CrI 0.35 to 0.96), PCB (OR 0.51, 95% CrI 0.26 to 0.98), or BMS (OR 0.38, 95% CrI 0.19 to 0.72) with moderate to high QoE. DES also significantly improved wound healing compared with BA (OR 2.02, 95% CrI 1.01 to 4.07) or BMS (OR 3.45, 95% CrI 1.41 to 8.73) with high QoE. Results were stable on sensitivity and meta-regression analyses without any significant publication bias or inconsistency. CONCLUSION: Infrapopliteal DES were associated with significantly lower rates of restenosis, TLR, and amputations and improved wound healing compared to BA and BMS. DES also significantly reduced amputations compared with PCB.

Drug-eluting versus plain balloon angioplasty for the treatment of failing dialysis access: final results and cost-effectiveness analysis from a prospective randomized controlled trial (NCT01174472).

OBJECTIVE: To report the final results and cost-effectiveness analysis of a prospective randomized controlled trial investigating drug-eluting balloon (DEB) versus plain balloon angioplasty (BA) for the treatment of failing dialysis access (NCT01174472). METHODS: 40 patients were randomized to angioplasty with either DEB (n=20) or BA (n=20) for treatment of significant venous stenosis causing a failing dialysis access. Both arteriovenous fistulas (AVF) and synthetic arteriovenous grafts (AVG) were included. Angiographic follow up was scheduled every two months. Primary endpoints were technical success and target lesion primary patency at 1 year. Cumulative and survival analysis was performed. Incremental net benefit (INB) and incremental cost effectiveness ratio (ICER) were calculated and the cost-effectiveness acceptability curve (CEAC) was drawn. RESULTS: Baseline variables were equally distributed between the two groups. At 1 year, cumulative target lesion primary patency was significantly higher after DEB application (35% vs. 5% after BA, p<0.001). Overall, median primary patency was 0.64 years in case of DEB vs. 0.36 years in case of BA (p=0.0007; unadjusted HR=0.27 [95%CI: 0.13-0.58]; Cox adjusted HR=0.23 [95%CI: 0.10-0.50]). ICER was 2198 Euros (€) per primary patency year of dialysis access gained. INB was 1068€ (95%CI: 31-2105€) for a willingness-to-pay (WTP) threshold of 5000€ (corresponding acceptability probability >97%). CONCLUSION: DEB angioplasty may be a cost-effective option that significantly improves patency after angioplasty of venous stenoses of failing vascular dialysis access. Further large-scale randomized trials are warranted.

Cost-effectiveness analysis of infrapopliteal drug-eluting stents.

INTRODUCTION: There are no cost-utility data about below-the-knee placement of drug-eluting stents. The authors determined the cost-effectiveness of infrapopliteal drug-eluting stents for critical limb ischemia (CLI) treatment. METHODS: The event-free individual survival outcomes defined by the absence of any major events, including death, major amputation, and target limb repeat procedures, were reconstructed on the basis of two published infrapopliteal series. The first included spot Bail-out use of Sirolimus-eluting stents versus bare metal stents after suboptimal balloon angioplasty (Bail-out SES).The second was full-lesion Primary Everolimus-eluting stenting versus plain balloon angioplasty and bail-out bare metal stenting as necessary (primary EES). The number-needed-to-treat (NNT) to avoid one major event and incremental cost-effectiveness ratios (ICERs) were calculated for a 3-year postprocedural period for both strategies. RESULTS: Overall event-free survival was significantly improved in both strategies (hazard ratio (HR) [confidence interval (CI)]: 0.68 [0.41-1.12] in Bail-out SES and HR [CI]: 0.53 [0.29-0.99] in Primary EES). Event-free survival gain per patient was 0.89 (range, 0.11-3.0) years in Bail-out SES with an NNT of 4.6 (CI: 2.5-25.6) and a corresponding ICER of 6,518 (range 1,685-10,112). Survival gain was 0.91 (range 0.25-3.0) years in Primary EES with an NNT of 2.7 (CI: 1.7-5.8) and an ICER of 11,581 (range, 4,945-21,428) per event-free life-year gained. Two-way sensitivity analysis showed that stented lesion length >10 cm and/or DES list price >1000 were associated with the least economically favorable scenario in both strategies. CONCLUSIONS: Both strategies of bail-out SES and primary EES placement in the infrapopliteal arteries for CLI treatment exhibit single-digit NNT and relatively low corresponding ICERs.