• MeSH
• předčasná porodní činnost farmakoterapie   MeSH
• tokolytika aplikace a dávkování   MeSH

Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning models, are a subtype of artificial neural networks, which are inspired by the complex structure of the human brain and are often used for image classification tasks. One of the biggest challenges in all deep neural networks is the overfitting issue, which happens when the model performs well on the training data, but fails to make accurate predictions for the new data that is fed into the model. Several regularization methods have been introduced to prevent the overfitting problem. In the research presented in this manuscript, the overfitting challenge was tackled by selecting a proper value for the regularization parameter dropout by utilizing a swarm intelligence approach. Notwithstanding that the swarm algorithms have already been successfully applied to this domain, according to the available literature survey, their potential is still not fully investigated. Finding the optimal value of dropout is a challenging and time-consuming task if it is performed manually. Therefore, this research proposes an automated framework based on the hybridized sine cosine algorithm for tackling this major deep learning issue. The first experiment was conducted over four benchmark datasets: MNIST, CIFAR10, Semeion, and UPS, while the second experiment was performed on the brain tumor magnetic resonance imaging classification task. The obtained experimental results are compared to those generated by several similar approaches. The overall experimental results indicate that the proposed method outperforms other state-of-the-art methods included in the comparative analysis in terms of classification error and accuracy.

• MeSH
• algoritmy MeSH
• lidé MeSH
• magnetická rezonanční tomografie MeSH
• nádory mozku * MeSH
• neuronové sítě * MeSH
• psaní rukou MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

• MeSH
• artefakty MeSH
• diagnostické zobrazování metody   MeSH
• lidé MeSH
• počítačová rentgenová tomografie metody   přístrojové vybavení   využití   MeSH
• počítačová simulace MeSH
• počítačové zpracování obrazu MeSH
• počítačové zpracování signálu MeSH
• statistika jako téma MeSH
• teoretické modely MeSH
• Check Tag
• lidé MeSH

This paper explores regularization options for the ill-posed spline coefficient equations in the realistic Laplacian computation. We investigate the use of the Tikhonov regularization, truncated singular value decomposition, and the so-called lambda-correction with the regularization parameter chosen by the L-curve, generalized cross-validation, quasi-optimality, and the discrepancy principle criteria. The provided range of regularization techniques is much wider than in the previous works. The improvement of the realistic Laplacian is investigated by simulations on the three-shell spherical head model. The conclusion is that the best performance is provided by the combination of the Tikhonov regularization and the generalized cross-validation criterion-a combination that has never been suggested for this task before.

• MeSH
• algoritmy MeSH
• diagnóza počítačová metody   MeSH
• elektroencefalografie metody   MeSH
• financování organizované MeSH
• lidé MeSH
• mapování mozku metody   MeSH
• modely neurologické MeSH
• mozek fyziologie   MeSH
• počítačová simulace MeSH
• Check Tag
• lidé MeSH

PURPOSE: The Tofts and the extended Tofts models are the pharmacokinetic models commonly used in dynamic contrast-enhanced MRI (DCE-MRI) perfusion analysis, although they do not provide two important biological markers, namely, the plasma flow and the permeability-surface area product. Estimates of such markers are possible using advanced pharmacokinetic models describing the vascular distribution phase, such as the tissue homogeneity model. However, the disadvantage of the advanced models lies in biased and uncertain estimates, especially when the estimates are computed voxelwise. The goal of this work is to improve the reliability of the estimates by including information from neighboring voxels. THEORY AND METHODS: Information from the neighboring voxels is incorporated in the estimation process through spatial regularization in the form of total variation. The spatial regularization is applied on five maps of perfusion parameters estimated using the tissue homogeneity model. Since the total variation is not differentiable, two proximal techniques of convex optimization are used to solve the problem numerically. RESULTS: The proposed algorithm helps to reduce noise in the estimated perfusion-parameter maps together with improving accuracy of the estimates. These conclusions are proved using a numerical phantom. In addition, experiments on real data show improved spatial consistency and readability of perfusion maps without considerable lowering of the quality of fit. CONCLUSION: The reliability of the DCE-MRI perfusion analysis using the tissue homogeneity model can be improved by employing spatial regularization. The proposed utilization of modern optimization techniques implies only slightly higher computational costs compared to the standard approach without spatial regularization.

• MeSH
• algoritmy MeSH
• fantomy radiodiagnostické MeSH
• glioblastom diagnostické zobrazování   MeSH
• kontrastní látky farmakologie   MeSH
• krysa rodu rattus MeSH
• magnetická rezonanční tomografie * MeSH
• mozek diagnostické zobrazování   MeSH
• nádory mozku diagnostické zobrazování   MeSH
• perfuze MeSH
• permeabilita MeSH
• počítačová simulace MeSH
• počítačové zpracování obrazu MeSH
• poměr signál - šum MeSH
• reprodukovatelnost výsledků MeSH
• zvířata MeSH
• Check Tag
• krysa rodu rattus MeSH
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

• MeSH
• inzulin MeSH

V práci je popsán význam pravidelné pohybové aktivity v primární prevenci neinfekčních onemocnění hromadného výskytu ve vojenské populaci. Práce popisuje jednotlivé druhy tělesné přípravy v AČR, sportovní možnosti a druhy sportů na útvarech a typy přezkoušení z tělesné přípravy.

The study is focused on the significance of regular physical activity in primary prevention of non-communicable diseases in the military population. The study describes individual types of physical preparation in the Army of the Czech Republic, sports possibilities and kinds of sports in individual units and types of physical activity testing.

• MeSH
• lidé MeSH
• neinfekční nemoci prevence a kontrola   MeSH
• ozbrojené síly * MeSH
• pohybová aktivita * MeSH
• primární prevence MeSH
• rehabilitace MeSH
• Check Tag
• lidé MeSH
• Geografické názvy
• Česká republika MeSH

OBJECTIVES: This study examines the role of personality in cognitive performance, adherence, and satisfaction with regular cognitive self-monitoring. MATERIALS AND METHODS: One hundred fifty-seven cognitively healthy older adults, age 55+, completed the 44-item Big-Five Inventory and were subsequently engaged in online monthly cognitive monitoring using the Cogstate Brief Battery for up to 35 months (M=14 mo, SD=7 mo). The test measures speed and accuracy in reaction time, visual learning, and working memory tasks. RESULTS: Neuroticism, although not related to cognitive performance overall (P>0.05), was related to a greater increase in accuracy (estimate=0.07, P=0.04) and speed (estimate=-0.09, P=0.03) on One Card Learning. Greater conscientiousness was related to faster overall speed on Detection (estimate=-1.62, P=0.02) and a significant rate of improvement in speed on One Card Learning (estimate=-0.10, P<0.03). No differences in satisfaction or adherence to monthly monitoring as a function of neuroticism or conscientiousness were observed. CONCLUSIONS: Participants volunteering for regular cognitive monitoring may be quite uniform in terms of personality traits, with personality traits playing a relatively minor role in adherence and satisfaction. The more neurotic may exhibit better accuracy and improve in speed with time, whereas the more conscientious may perform faster overall and improve in speed on some tasks, but the effects appear small.

• MeSH
• kognice fyziologie   MeSH
• lidé MeSH
• osobnostní testy * MeSH
• prospektivní studie MeSH
• sebezhodnocení (psychologie) * MeSH
• senioři MeSH
• Check Tag
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

• MeSH
• dialýza ledvin metody   MeSH
• jednotky nemocniční MeSH
• náhrada funkce ledvin MeSH
• Publikační typ
• monografie MeSH

• Konspekt
• Patologie. Klinická medicína
• NLK Obory
• nefrologie
• hematologie a transfuzní lékařství

BACKGROUND: Absorption rates of the phosphate-buffered insulin analogs aspart, lispro, and glulisine prevail over that of regular human insulin. The aim of this prospective observational open-label controlled study was to compare the effects of aspart and human regular insulin resulting from their sequential long-lasting routine administration in small preprandial boluses to individuals with type 2 diabetes according to identical algorithms. METHODS: Fifty-seven individuals with type 2 diabetes 64.0 +/- 1.29 (mean +/- SE) years old with diabetes' duration of 12.4 +/- 1.06 years, treated with human regular insulin for 5.2 +/- 0.44 years, and a serum C-peptide level of 1.1 +/- 0.10 nmol/L were enrolled into the study. Following two checkups performed in the course of the 364 +/- 17.9-day baseline period, human regular insulin was replaced with aspart in equivalent boluses, and two checkups in the course of 330 +/- 11.1-day sequential period were performed. The control group consisted of 17 individuals with type 2 diabetes 68.4 +/- 2.36 years old with diabetes' duration of 9.9 +/- 1.57 years, treated with insulin for 4.2 +/- 0.57 years, and a C-peptide level of 1.1 +/- 0.11 nmol/L. Data were analyzed using the statistical program SPSS version 10.1. (SPSS, Inc., Chicago, IL). RESULTS: Following the switch from human regular insulin to aspart, hemoglobin A1c (HbA1c) decreased from 8.4 +/- 0.23% at baseline to 7.9 +/- 0.17% (P = 0.031), and thereafter to 7.5 +/- 0.20% (P < 0.001), while plasma glucose concentrations in 10-point profiles, daily insulin dose (37.1 +/- 1.39 IU/day), body mass index (BMI) (30.5 +/- 0.82 kg/m(2)), and frequency of hypo- and hyperglycemic episodes did not change (P > 0.05). Patients quote satisfaction was good. No adverse events were recorded. In the control group, no significant change of baseline HbA1c (8.4 +/- 0.54%), insulin dose (33.1 +/- 3.17 IU/day), and BMI (32.1 +/- 1.12 kg/m(2)) was found. CONCLUSION: Aspart appears to be more effective than human regular insulin for complementary insulin treatment in individuals with type 2 diabetes.

• MeSH
• C-peptid krev   MeSH
• diabetes mellitus 2. typu farmakoterapie   krev   MeSH
• financování organizované MeSH
• glykovaný hemoglobin metabolismus   MeSH
• hypoglykemika terapeutické užití   MeSH
• index tělesné hmotnosti MeSH
• inzulin analogy a deriváty   terapeutické užití   MeSH
• krevní glukóza metabolismus   MeSH
• lidé středního věku MeSH
• lidé MeSH
• lipidy krev   MeSH
• prospektivní studie MeSH
• senioři MeSH
• spokojenost pacientů MeSH
• výsledek terapie MeSH
• Check Tag
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• klinické zkoušky kontrolované MeSH