scholarly journals Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3227
Author(s):  
Franko Hržić ◽  
Michael Janisch ◽  
Ivan Štajduhar ◽  
Jonatan Lerga ◽  
Erich Sorantin ◽  
...  

In clinical practice, fracture age estimation is commonly required, particularly in children with suspected non-accidental injuries. It is usually done by radiologically examining the injured body part and analyzing several indicators of fracture healing such as osteopenia, periosteal reaction, and fracture gap width. However, age-related changes in healing timeframes, inter-individual variabilities in bone density, and significant intra- and inter-operator subjectivity all limit the validity of these radiological clues. To address these issues, for the first time, we suggest an automated neural network-based system for determining the age of a pediatric wrist fracture. In this study, we propose and evaluate a deep learning approach for automatically estimating fracture age. Our dataset included 3570 medical cases with a skewed distribution toward initial consultations. Each medical case includes a lateral and anteroposterior projection of a wrist fracture, as well as patients’ age, and gender. We propose a neural network-based system with Monte-Carlo dropout-based uncertainty estimation to address dataset skewness. Furthermore, this research examines how each component of the system contributes to the final forecast and provides an interpretation of different scenarios in system predictions in terms of their uncertainty. The examination of the proposed systems’ components showed that the feature-fusion of all available data is necessary to obtain good results. Also, proposing uncertainty estimation in the system increased accuracy and F1-score to a final 0.906±0.011 on a given task.

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Mingxin Wang ◽  
Yingnan Zheng ◽  
Binbin Wang ◽  
Zhuofu Deng

Household load forecasting provides great challenges as a result of high uncertainty in individual consumption of load profile. Traditional models based on machine learning tried to explore uncertainty depending on clustering, spectral analysis, and sparse coding with hand craft features. Recently, deep learning skills like recurrent neural network attempt to learn the uncertainty with one-hot encoding which is too simple and not efficient. In this paper, for the first time, we proposed a multitask deep convolutional neural network for household load forecasting. The baseline of one branch is built on multiscale dilated convolutions for load forecasting. The other branch based on deep convolutional autoencoder is responsible for household profile encoding. In addition, an efficient encoding strategy for household profile is designed that serves a novel feature fusion mechanism integrated into forecasting branch. Our proposed network serves an end-to-end manner in training and inference process. Sufficient ablation studies were conducted to demonstrate effectiveness of innovations and great generalization in point and probabilistic load forecasting at household level, which provides a promising prospect in demand response.


2011 ◽  
Vol 10 (6) ◽  
pp. 64-69 ◽  
Author(s):  
S. A. Shalnova ◽  
V. A. Zhukova ◽  
V. A. Metelskaya ◽  
A. D. Deev ◽  
M. B. Khudyakov ◽  
...  

Aim. High-sensitive C-reactive protein (hsCRP) is currently regarded as an important marker of cardiovascular disease (CVD). The aim of the study was to assess the population characteristics of hsCRP in the sample of Moscow residents aged 55 years and older. Material and methods. The analysis included 1851 people (response rate 65 %), who participated in the SAHR (Stress, Aging, and Health in Russia) study. Results. The hsCRP levels were similar in men and women, with the right-skewed distribution. The hsCRP values ranged from 0,5 to 69,5 mg/dl in men (median 1,5 mg/l), and from 0,5 to 75 mg/l in women (median 1,5 mg/l). The mean hsCRP levels were slightly higher in men than in women (3,4±0,19 vs. 3,1±0,15, respectively; р=0,36). Overall, there was no marked age-related dynamics of hsCRP levels in men or women. The prevalence of high hsCRP levels (>3 mg/l) non-significantly increased from 31,2 % in the youngest age group to 36,2 % in those aged 75 years and older. Acute inflammation (hsCRP levels >10 mg/l) was registered in 85 participants (4,5 %), including 42 men and 43 women. After adjustment for age and gender, the lower education level remained a significant predictor of hsCRP elevation. Conclusion. No clear associations between hsCRP and age or gender were observed. However, participants with university and secondary education had significantly lower hsCRP concentrations, compared to their peers with education level lower than secondary.


Author(s):  
Judith Herrin

This book explores the exceptional roles that women played in the vibrant cultural and political life of medieval Byzantium. This book evokes the complex and exotic world of Byzantium's women, from empresses and saints to uneducated rural widows. Drawing on a diverse range of sources, the book sheds light on the importance of marriage in imperial statecraft, the tense coexistence of empresses in the imperial court, and the critical relationships of mothers and daughters. It looks at women's interactions with eunuchs, the in-between gender in Byzantine society, and shows how women defended their rights to hold land. The book describes how women controlled their inheritances, participated in urban crowds demanding the dismissal of corrupt officials, followed the processions of holy icons and relics, and marked religious feasts with liturgical celebrations, market activity, and holiday pleasures. The vivid portraits that emerge here reveal how women exerted an unrivalled influence on the patriarchal society of Byzantium, and remained active participants in the many changes that occurred throughout the empire's millennial history. The book brings together the author's finest essays on women and gender written throughout the long span of her career. This volume includes three new essays published here for the very first time and a new general introduction. It also provides a concise introduction to each essay that describes how it came to be written and how it fits into her broader views about women and Byzantium.


Angiology ◽  
2021 ◽  
pp. 000331972110287
Author(s):  
Turhan Turan ◽  
Faruk Kara ◽  
Selim Kul ◽  
Muhammet Rasit Sayın ◽  
Sinan Sahin ◽  
...  

The most common cause of complete atrioventricular block (CAVB) is age-related fibrotic degeneration and is referred to as primary idiopathic complete atrioventricular block (iCAVB). This study aims to investigate the relationship between iCAVB and arterial stiffness using the cardio-ankle vascular index (CAVI). In this study, of 205 CAVB patients, 41 patients with iCAVB implanted with a dual-chamber permanent pacemaker and 40 age- and gender-matched controls were studied. Arterial stiffness was assessed by a VaSera VS-1000 CAVI instrument. The CAVI values of patients with iCAVB were significantly higher compared with the controls (9.63 ± 1.42 vs 8.57 ± 1.12, P < .001). Idiopathic complete atrioventricular block frequency was higher among patients with abnormal CAVI values than those with borderline and normal CAVI ( P = .04). In multivariate analysis, only CAVI was an independent predictor of iCAVB after adjusting for other relevant factors (odds ratio, 2.575; 95% CI [1.390-4.770]; P = .003). The present study demonstrated that CAVI, as a marker of arterial stiffness, was increased among elderly patients with iCAVB. Thus, we provide a possible additional mechanism linking easily measured CAVI with iCAVB.


Genes ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 475
Author(s):  
Maria Santa Rocca ◽  
Ludovica Dusi ◽  
Andrea Di Nisio ◽  
Erminia Alviggi ◽  
Benedetta Iussig ◽  
...  

Telomeres are considered to be an internal biological clock, and their progressive shortening has been associated with the risk of age-related diseases and reproductive alterations. Over recent years, an increasing number of studies have focused on the association between telomere length and fertility, identifying sperm telomere length (STL) as a novel biomarker of male fertility. Although typically considered to be repeated DNA sequences, telomeres have recently been shown to also include a long non-coding RNA (lncRNA) known as TERRA (telomeric repeat-containing RNAs). Interestingly, males with idiopathic infertility show reduced testicular TERRA expression, suggesting a link between TERRA and male fertility. The aim of this study was to investigate the role of seminal TERRA expression in embryo quality. To this end, STL and TERRA expression were quantified by Real Time qPCR in the semen of 35 men who underwent assisted reproductive technologies (ART) and 30 fertile men. We found that TERRA expression in semen and STL was reduced in patients that underwent ART (both p < 0.001). Interestingly, TERRA and STL expressions were positively correlated (p = 0.010), and TERRA expression was positively associated with embryo quality (p < 0.001). These preliminary findings suggest a role for TERRA in the maintenance of sperm telomere integrity during gametogenesis, and for the first time, TERRA expression was found as a predictive factor for embryo quality in the setting of assisted reproduction.


Sign in / Sign up

Export Citation Format

Share Document