Search

Purpose: The use of convolution neural networks (CNN) to accurately predict dose distributions can accelerate intensity-modulated radiation therapy (IMRT) planning. The purpose of our study is to develop a novel deep learning architecture for precise voxel-level dose prediction on brain tumors. Methods: A dataset of 120 patients with brain tumors is built for the retrospective study. The dose distributions are predicted by a designed end-to-end model called TS-Net, in which the transformer encoder module is utilized to obtain abundant global features by learning long-range correlations of the input sequence. In addition, semantic field alignment (SFA) block is proposed in decoding path to ensure effective propagation of strong semantic information from deep to shallow. Five images from different channels are fed into the architecture, including a computed tomography (CT) image, a planning target volumes (PTV) image, an organs-at-risk (OARs) image, a beam configuration image, and a distance image, and the predicted dose distributions are taken as outputs. We use different evaluation metrics to evaluate the performance of the model and discuss the role of the auxiliary beam configuration information provided by non-modulated dose distributions. Results: The TS-Net prediction accuracies in terms of mean absolute error (MAE) are 2.98% for PTV, 7.19% for brainstem, 1.88% for left len, 2.48% for right len, 9.61% for left optic nerve, 9.10% for right optic nerve, 8.99% for optic chiasma, and 8.28% for pituitary. There is no statistically significant difference between the predicted results and clinical dose distributions for clinical indexes including homogeneity index (HI), D50, and D95 for PTV; V40, mean dose, and max dose for OARs; except for conformation index (CI) and D2 for PTV. The model has dice similarity coefficient (DSC) values of above 0.91 for most isodose volumes, clearly outperforming HD U-Net, and being slightly better than U-Net and DCNN. Conclusion: The proposed TS-Net with beam configuration input can achieve accurate voxel-level dose prediction for brain tumors, and is a usable tool for improving the efficiency and quality of radiotherapy. [ABSTRACT FROM AUTHOR]

This study proposes a novel prediction model for uni- and multi-variable forecast, where error feedback is added to the original forecast value predicted using the persistence model. The error feedback mechanism is constructed to find out the relationship between the errors and the original forecast values. Simulation studies are carried out using wind power data obtained from two databases, and the results demonstrate that the proposed model provides a more accurate and stable forecast compared to other methods. Based on this, the economic benefit of accurate wind power forecast has been analysed for power system dispatch, which aims to minimise the operation cost. The dispatch results of two scenarios have shown that accurate forecast result decreases the cost of reserve capacity, balancer set invoking capacity and the possibility of wind curtailment, which leads to more economic dispatch of power systems. [ABSTRACT FROM AUTHOR]

The natural rubber/styrene butadiene rubber/organoclay (NR/SBR/organoclay) nanocomposites were successfully prepared with different types of organoclay by direct compounding. The optimal type of organoclay was selected by the mechanical properties characterization of the NR/SBR/organoclay composites. The series of NR/SBR/organoclay (the optimal organoclay) nanocomposites were prepared with various organoclay contents loading from 1.0 to 7.0 parts per hundreds of rubber (phr). The nearly completely exfoliated organoclay nanocomposites with uniform dispersion were confirmed by transmission electron microscopy (TEM) and X-ray diffraction (XRD). The results of mechanical properties measurement showed that the tensile strength, tensile modulus, and tear strength were improved significantly when the organoclay content was less than 5.0 phr. The tensile strength and the tear strength of the nanocomposite with only 3.0 phr organoclay were improved by 92.8% and 63.4%, respectively. It showed organoclay has excellent reinforcement effect with low content. The reduction of the score and cure times of the composites indicated that the organoclay acted as accelerator in the process of vulcanization. The incorporation of a small amount of organoclay greatly improved the swelling behavior and thermal stability, which was attributed to the good barrier properties of the dispersed organoclay layers. The outstanding performance of co-reinforcement system with organoclay in the tire formulation showed that the organoclay had a good application prospect in the tire industry, especially for the improvement of abrasion resistance and the reduction of production cost. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2011 [ABSTRACT FROM AUTHOR]

It has been recognized that protease-activated receptors (PARs), interleukin (IL)-4 and IL-6 are involved in the pathogenesis of allergic diseases, and that IL-12 plays a role in adaptive immune response. However, little is known of the effect of IL-12 on protease-induced cytokine release from mast cells. In the present study, we examined potential influence of IL-12 on mast cell PAR expression and IL-4 and IL-6 release. The results showed that IL-12 downregulated the expression of PAR-2 and upregulated expression of PAR-4 on P815 cells. It also downregulated expression of PAR-2 mRNA, and upregulated expression of PAR-1, PAR-3 and PAR-4 mRNAs. However, IL-12 enhanced trypsin- and tryptase-induced PAR-2 and PAR-2 mRNA expression. It was observed that IL-12 induced release of IL-4, but reduced trypsin- and tryptase-stimulated IL-4 secretion from P815 cells. PD98059, U0126 and LY294002 not only abolished IL-12-induced IL-4 release but also inhibited IL-12-induced phosphorylation of extracellular signal-regulated kinase and Akt. In conclusion, IL-12 may serve as a regulator in keeping the balance of Th1 and Th2 cytokine production in allergic inflammation.Immunology and Cell Biology (2007) 85, 558–566; doi:10.1038/sj.icb.7100085; published online 26 June 2007 [ABSTRACT FROM AUTHOR]