ABSTRACT
Applying Deep Learning (DL) in radiological images (i.e., chest X-rays) is emerging because of the necessity of having accurate and fast COVID-19 detectors. Deep Convolutional Neural Networks (DCNN) have been typically used as robust COVID-19 positive case detectors in these approaches. Such DCCNs tend to utilize Gradient Descent-Based (GDB) algorithms as the last fully-connected layers' trainers. Although GDB training algorithms have simple structures and fast convergence rates for cases with large training samples, they suffer from the manual tuning of numerous parameters, getting stuck in local minima, large training samples set requirements, and inherently sequential procedures. It is exceedingly challenging to parallelize them with Graphics Processing Units (GPU). Consequently, the Chimp Optimization Algorithm (ChOA) is presented for training the DCNN's fully connected layers in light of the scarcity of a big COVID-19 training dataset and for the purpose of developing a fast COVID-19 detector with the capability of parallel implementation. In addition, two publicly accessible datasets termed COVID-Xray-5 k and COVIDetectioNet are used to benchmark the proposed detector known as DCCN-Chimp. In order to make a fair comparison, two structures are proposed: i-6c-2 s-12c-2 s and i-8c-2 s-16c-2 s, all of which have had their hyperparameters fine-tuned. The outcomes are evaluated in comparison to standard DCNN, Hybrid DCNN plus Genetic Algorithm (DCNN-GA), and Matched Subspace classifier with Adaptive Dictionaries (MSAD). Due to the large variation in results, we employ a weighted average of the ensemble of ten trained DCNN-ChOA, with the validation accuracy of the weights being used to determine the final weights. The validation accuracy for the mixed ensemble DCNN-ChOA is 99.11%. LeNet-5 DCNN's ensemble detection accuracy on COVID-19 is 84.58%. Comparatively, the suggested DCNN-ChOA yields over 99.11% accurate detection with a false alarm rate of less than 0.89%. The outcomes show that the DCCN-Chimp can deliver noticeably superior results than the comparable detectors. The Class Activation Map (CAM) is another tool used in this study to identify probable COVID-19-infected areas. Results show that highlighted regions are completely connected with clinical outcomes, which has been verified by experts.
ABSTRACT
INTRODUCTION: Integrity of the great saphenous vein (GSV) endothelium is the most important key element for long-term patency rate of grafts in coronary artery bypass graft (CABG). Storage solutions play an important role in maintaining viability of vein endothelium. Diminished nitric oxide (NO) because of endothelial dysfunction may facilitate vascular inflammation and formation of atherosclerotic plaque. AIM: So, we decided to find a reasonable alternative preservative solution instead of heparinized blood (HB) by measuring NO concentration with Griess assay. MATERIAL AND METHOD: SVG samples were obtained from 54 patients undergoing elective CABG. 3 mm rings were stored in solutions: heparinized blood (HB), Krebs (K), Krebs + Propranolol (K+P) 6.66 g/l, Krebs + Adrenaline (K+A) 200 µl/l, and Krebs + Verapamil (K+V) 200 µl/l for 30, 45, 60 and 90 min. Nitrite concentration was measured by Griess assay at 540 nm. H&E staining was performed for histologic test. Statistical analysis was performed using SPSS (V16). Results were expressed as (Means ± SE) followed by One-Way ANOVA for finding best preservative solution. Repeated measurement test was used to investigate best time. In all analysis, (P<0.05) was considered significant. RESULTS: Average concentration of NO in (K+V) compare with HB (1st control), K (2nd control), (K+A) and (K+P) showed higher rate in all times from 30 to 90 min (16.55±1.85:) and in (K+A, K+P) compare with (HB) and (K) there was no statistically significant difference in the same times. Comparing the average concentration of (NO) between (HB) and (K) showed no significant difference (K+V>HB=K=K+A=K+P). Also, our investigations showed that NO concentration in (K+V) has the highest rate in time 90 min (10.07±0.56, p=0.002):. More than 50 percent of endothelial cells stay normal in (K+V) compare with other solutions. CONCLUSION: It seems that (K+V) is the best solution for the maintenance of normal physiology of SVGs endothelial cells. The most appropriate SVGs endothelial function is within 90 minutes after harvesting.
