Currently, the tuberculosis (TB) detection model based on chest X-ray images has the problem of excessive reliance on hardware computing resources, high equipment performance requirements, and being harder to deploy in low-cost personal computer and embedded devices. An efficient tuberculosis detection model is proposed to achieve accurate, efficient, and stable tuberculosis screening on devices with lower hardware levels. Due to the particularity of the chest X-ray images of TB patients, there are fewer labeled data, and the deep neural network model is difficult to fully train. We first analyzed the data distribution characteristics of two public TB datasets, and found that the two-stage tuberculosis identification (first divide, then classify) is insufficient. Secondly, according to the particularity of the detection image(s), the basic residual module was optimized and improved, and this is regarded as a crucial component of this article’s network. Finally, an efficient attention mechanism was introduced, which was used to fuse the channel features. The network architecture was optimally designed and adjusted according to the correct and sufficient experimental content. In order to evaluate the performance of the network, it was compared with other lightweight networks under personal computer and Jetson Xavier embedded devices. The experimental results show that the recall rate and accuracy of the E-TBNet proposed in this paper are better than those of classic lightweight networks such as SqueezeNet and ShuffleNet, and it also has a shorter reasoning time. E-TBNet will be more advantageous to deploy on equipment with low levels of hardware.
A new approach method to dealing with the puzzle of spectral analysis in prompt gamma neutron activation analysis (PGNAA) is developed and demonstrated. It consists of utilizing BP neural network to PGNAA energy spectrum analysis which is based on Monte Carlo (MC) simulation, the main tasks which we will accomplish as follows: (1) Completing the MC simulation of PGNAA spectrum library, we respectively set mass fractions of element Si, Ca, Fe from 0.00 to 0.45 with a step of 0.05 and each sample is simulated using MCNP. (2) Establishing the BP model of adaptive quantitative analysis of PGNAA energy spectrum, we calculate peak areas of eight characteristic gamma rays that respectively correspond to eight elements in each individual of 1000 samples and that of the standard sample. (3) Verifying the viability of quantitative analysis of the adaptive algorithm where 68 samples were used successively. Results show that the precision when using neural network to calculate the content of each element is significantly higher than the MCLLS.
Rhythm control is the core part of the integrated management of atrial fibrillation (AF), especially in the early stages. Despite advances in catheter ablation (CA), the recurrence rate of AF after CA remains high. As a result, stratification and early management of AF recurrence after CA are critical. Currently, predictors of recurrence of AF after CA are mostly based on dysfunction caused by structural remodeling, apart from traditional risk factors. Atrial strain is a recently developed important parameter for detecting the deformability of atrial myocardium during the cardiac cycle prior to atrial remodeling. Although there is only preliminary evidence, atrial strain is still a promising parameter in predicting the recurrence of AF after CA at an early stage. This review focuses on the evaluation of atrial strain, the current applications of atrial strain in assessing atrial function, and predicting the recurrence of AF after CA. We summarize the contents related as follows: (1) CA for rhythm control in AF; (2) Evaluation methods of atrial strain; (3) Atrial strain in the remodeling and reverse remodeling of AF; and (4) Clinical applications of atrial strain in predicting the recurrence of AF after CA. Although there is accumulating evidence on the role of decreased atrial strain in the early prediction of AF recurrence, atrial strain is limited in clinical practice for lacking exact cut-off values and difficulty in distinguishing specific function phases of the atrium. More research is needed in the future to add strength to the early prediction value of atrial strain in AF recurrences.
A prompt γ neutron activation analysis (PGNAA) facility based on a 252 Cf spontaneous fission neutron was performed with the final goal of obtaining various optimised radiation protection design parameters. MCNP Monte Carlo code was used to simulate the lead (Pb) shield thickness on two sides of the sample chamber, and B 4 C, B 2 O 3 , LiOH, LiF, and borax were selected as neutron-absorbing materials that were simulated to determine optimal parameters for the optimal design of a biological multilayer composite shield. A series of calculations performed with the MCNP code indicated that the 5 cm thick Pb innermost layer of a biological shield rapidly reduced fast neutrons, and a moderation layer of 25 cm thick paraffin, 20 mm thick borax, and 2 mm thick B 4 C were selected as neutron-absorbing materials. The calculated biological shield protection parameters satisfied the requirements of the PGNAA facility used in the experiment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.