Only in Titles

Search results for: Super Block

paperclip

Error loading info... Pleas try again later.
paperclip

#33961556   2021/05/13 To Up

SRGAT: Single Image Super-Resolution With Graph Attention Network.

Deep neural networks have demonstrated remarkable reconstruction for single-image super-resolution (SISR). However, most existing CNN-based SISR methods directly learn the relation between low-resolution (LR) and high-resolution (HR) images, neglecting to explore the recurrence of internal patches, hence hindering the representational power of CNNs. In this paper, we propose a novel single image Super-Resolution network based on Graph ATtention network (SRGAT) to make full use of the internal patch-recurrence in a natural image. The proposed model employs a feature mapping block with a recurrent structure to refine low-level representations with high-level information. Especifically, the feature mapping block contains a parallel graph similarity branch and a content branch, where the graph similarity branch aims at exploiting the similarity and symmetry across different image patches in low-resolution feature space and provides additional priors for the content branch to enhance texture details. Specifically, we consider the internal patch-recurrence of an image by constructing a graph network on image feature patches. In this way, the information from neighboring patches can be interacted using graph attention network (GAT) to help it recover additional textures, which complements the textures learned from the content branch. Extensive quantitative and qualitative evaluations on five benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art super-resolution methods.
Yanyang Yan, Wenqi Ren, Xiaobin Hu, Kun Li, Haifeng Shen, Xiaochun Cao

1843 related Products with: SRGAT: Single Image Super-Resolution With Graph Attention Network.

1 mgKIT 125 ml 1ml100 mg2ml10 mg1mg 1000 ml 1ml

Related Pathways

paperclip

#33953229   2021/05/05 To Up

Inverse renormalization group based on image super-resolution using deep convolutional networks.

The inverse renormalization group is studied based on the image super-resolution using the deep convolutional neural networks. We consider the improved correlation configuration instead of spin configuration for the spin models, such as the two-dimensional Ising and three-state Potts models. We propose a block-cluster transformation as an alternative to the block-spin transformation in dealing with the improved estimators. In the framework of the dual Monte Carlo algorithm, the block-cluster transformation is regarded as a transformation in the graph degrees of freedom, whereas the block-spin transformation is that in the spin degrees of freedom. We demonstrate that the renormalized improved correlation configuration successfully reproduces the original configuration at all the temperatures by the super-resolution scheme. Using the rule of enlargement, we repeatedly make inverse renormalization procedure to generate larger correlation configurations. To connect thermodynamics, an approximate temperature rescaling is discussed. The enlarged systems generated using the super-resolution satisfy the finite-size scaling.
Kenta Shiina, Hiroyuki Mori, Yusuke Tomita, Hwee Kuan Lee, Yutaka Okabe

1450 related Products with: Inverse renormalization group based on image super-resolution using deep convolutional networks.

One 96-Well Microplate Ki 2 ml 200 125 ml 100.00 ug200 Tests 6 ml Ready-to-use One 96-Well Microplate Ki10 μg1 mg

Related Pathways

paperclip

#33945478   2021/05/07 To Up

VolumeNet: A Lightweight Parallel Network for Super-Resolution of MR and CT Volumetric Data.

Deep learning-based super-resolution (SR) techniques have generally achieved excellent performance in the computer vision field. Recently, it has been proven that three-dimensional (3D) SR for medical volumetric data delivers better visual results than conventional two-dimensional (2D) processing. However, deepening and widening 3D networks increases training difficulty significantly due to the large number of parameters and small number of training samples. Thus, we propose a 3D convolutional neural network (CNN) for SR of magnetic resonance (MR) and computer tomography (CT) volumetric data called ParallelNet using parallel connections. We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with a few parameters. As a result, the model thoroughly learns more feature maps with larger receptive fields. In addition, to further improve accuracy, we present an efficient version of ParallelNet (called VolumeNet), which reduces the number of parameters and deepens ParallelNet using a proposed lightweight building block module called the Queue module. Unlike most lightweight CNNs based on depthwise convolutions, the Queue module is primarily constructed using separable 2D cross-channel convolutions. As a result, the number of network parameters and computational complexity can be reduced significantly while maintaining accuracy due to full channel fusion. Experimental results demonstrate that the proposed VolumeNet significantly reduces the number of model parameters and achieves high precision results compared to state-of-the-art methods in tasks of brain MR image SR, abdomen CT image SR, and reconstruction of super-resolution 7T-like images from their 3T counterparts.
Yinhao Li, Yutaro Iwamoto, Lanfen Lin, Rui Xu, Ruofeng Tong, Yen-Wei Chen

1714 related Products with: VolumeNet: A Lightweight Parallel Network for Super-Resolution of MR and CT Volumetric Data.

1000 tests100ug Lyophilized1 Set1 g100ug200ul100 μg1 Set

Related Pathways

paperclip

#33939871   2021/05/03 To Up

Degradation of ester linkages in rice straw components by Sphingobium species recovered from the sea bottom using a non-secretory tannase-family α/β hydrolase.

Microbial decomposition of allochthonous plant components imported into the aquatic environment is one of the vital steps of the carbon cycle on earth. To expand the knowledge of the biodegradation of complex plant materials in aquatic environments, we recovered a sunken wood from the bottom of Otsuchi Bay, situated in northeastern Japan in 2012. We isolated Sphingobium with high ferulic acid esterase activity. The strain, designated as OW59, grew on various aromatic compounds and sugars, occurring naturally in terrestrial plants. A genomic study of the strain suggested its role in degrading hemicelluloses. We identified a gene encoding a non-secretory tannase-family α/β hydrolase, which exhibited ferulic acid esterase activity. This enzyme shares the consensus catalytic triad (Ser-His-Asp) within the tannase family block X in the ESTHER database. The molecules, which had the same calculated elemental compositions, were produced consistently in both the enzymatic and microbial degradation of rice straw crude extracts. The non-secretory tannase-family α/β hydrolase activity may confer an important phenotypic feature on the strain to accelerate plant biomass degradation. Our study provides insights into the underlying biodegradation process of terrestrial plant polymers in aquatic environments. This article is protected by copyright. All rights reserved.
Yukari Ohta, Madoka Katsumata, Kanako Kurosawa, Yoshihiro Takaki, Hiroshi Nishimura, Takashi Watanabe, Ken-Ichi Kasuya

2921 related Products with: Degradation of ester linkages in rice straw components by Sphingobium species recovered from the sea bottom using a non-secretory tannase-family α/β hydrolase.

96T100ul100ug 100ul 100ul 100ul 100ul25 mg1 Product tipe: Instrumen100ug 100ul

Related Pathways

paperclip

#33922811   2021/04/23 To Up

3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution.

The diagnosis of brain pathologies usually involves imaging to analyze the condition of the brain. Magnetic resonance imaging (MRI) technology is widely used in brain disorder diagnosis. The image quality of MRI depends on the magnetostatic field strength and scanning time. Scanners with lower field strengths have the disadvantages of a low resolution and high imaging cost, and scanning takes a long time. The traditional super-resolution reconstruction method based on MRI generally states an optimization problem in terms of prior information. It solves the problem using an iterative approach with a large time cost. Many methods based on deep learning have emerged to replace traditional methods. MRI super-resolution technology based on deep learning can effectively improve MRI resolution through a three-dimensional convolutional neural network; however, the training costs are relatively high. In this paper, we propose the use of two-dimensional super-resolution technology for the super-resolution reconstruction of MRI images. In the first reconstruction, we choose a scale factor of 2 and simulate half the volume of MRI slices as input. We utilize a receiving field block enhanced super-resolution generative adversarial network (RFB-ESRGAN), which is superior to other super-resolution technologies in terms of texture and frequency information. We then rebuild the super-resolution reconstructed slices in the MRI. In the second reconstruction, the image after the first reconstruction is composed of only half of the slices, and there are still missing values. In our previous work, we adopted the traditional interpolation method, and there was still a gap in the visual effect of the reconstructed images. Therefore, we propose a noise-based super-resolution network (nESRGAN). The noise addition to the network can provide additional texture restoration possibilities. We use nESRGAN to further restore MRI resolution and high-frequency information. Finally, we achieve the 3D reconstruction of brain MRI images through two super-resolution reconstructions. Our proposed method is superior to 3D super-resolution technology based on deep learning in terms of perception range and image quality evaluation standards.
Hongtao Zhang, Yuki Shinomiya, Shinichi Yoshida

2949 related Products with: 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution.

100ul 2 ml 125 ml One 96-Well Microplate Ki 25 ml Ready-to-use 1 mgEaOne 96-Well Microplate Ki 6 ml 25 MGOne 96-Well Microplate Ki100tests

Related Pathways

paperclip

#33906885   2021/04/26 To Up

Successful peripheral nerve block under dexmedetomidine sedation for femoral neck fracture fixation in a 97-year-old patient.

Hip fracture is a common injury in elderly patients. In Japan, the number of super-old patients-age >90 years-with hip fractures has increased drastically over time. Available strategies for anaesthetic management for hip fracture surgery include general anaesthesia, neuraxial anaesthesia and peripheral nerve block. However, general and neuraxial anaesthesia are often avoided for various reasons, particularly in elderly patients. In recent years, peripheral nerve block has proven effective in various surgical procedures. Additionally, dexmedetomidine exhibits neuroprotective effects and has been used safely in super-old patients. Herein, we demonstrate successful anaesthetic management with peripheral nerve block under dexmedetomidine sedation for open reduction and internal fixation of a femoral neck fracture in a 97-year-old patient.
Yoshiaki Ishida, Fumiko Ogura, Satoko Kondo, Yoshie Toba

1433 related Products with: Successful peripheral nerve block under dexmedetomidine sedation for femoral neck fracture fixation in a 97-year-old patient.

1

Related Pathways

paperclip

#33869823   2021/03/08 To Up

Phosphorus availability and exchangeable aluminum response to phosphate rock and organic inputs in the Central Highlands of Kenya.

Soil acidity and phosphorus deficiency are some of the constraints hampering agricultural production in tropical regions. The prevalence of soil acidity is associated with phosphorus (P) insufficiency and aluminum saturation. We conducted a two-seasons experiment to evaluate soil phosphorus availability and exchangeable aluminum in response to phosphate rock and organic inputs in acidic . The field experiment was installed in Tharaka Nithi County in the Central Highlands of Kenya. The experimental design was a randomized complete block design with treatments replicated thrice. The treatments were: Green manure ( Hemsl.) (60 kg P ha), phosphate rock (60 kg P ha), goat manure (60 kg P ha), (20 kg P ha) combined with phosphate rock (40 kg P ha), manure (20 kg P ha) combined with phosphate rock (40 kg P ha), Triple Super Phosphate combined with Calcium Ammonium Nitrate (TSP + CAN) (60 kg P ha) and a control (no input). During the long rains of the 2018 season (LR2018), + phosphate rock had a significantly higher reduction (67%) of exchangeable aluminum than the sole use of Grain yield under TSP + CAN was the highest, followed by the sole organics during the LR2018. + phosphate rock resulted in a 99% and a 90% increase in NaHCO-Pi compared to sole phosphate rock and sole respectively. led to 14% and 62% higher resin-Pi and NaOH-Pi, respectively, compared to manure in the short rains of 2017 (SR2017). The increase in NaOH-Po after the two seasons was statistically significant in sole TSP + CAN. Based on the observed reduced exchangeable aluminum and additional nutrients like Ca, Mg, and K in the soil, sole organic inputs or in combination with phosphate rock treatments are feasible alternatives for sustaining soil phosphorus. Our findings underscore an integrated approach utilizing organic amendments combined with phosphate rock in acidic humic nitisols' phosphorus nutrient management
J A Omenda, K F Ngetich, M N Kiboi, M W Mucheru-Muna, D N Mugendi

1654 related Products with: Phosphorus availability and exchangeable aluminum response to phosphate rock and organic inputs in the Central Highlands of Kenya.

100 UG100 mg100 mg96 wells 25 MG10 mg1 mg

Related Pathways

paperclip

#33865764   2021/04/07 To Up

A Strain-Based Staging Classification of Left Bundle Branch Block-Induced Cardiac Remodeling.

This study speculated that longitudinal strain curves in left bundle branch block (LBBB) could be shaped by the degree of LBBB-induced cardiac remodeling.
Simon Calle, Victor Kamoen, Marc De Buyzere, Jan De Pooter, Frank Timmermans

1080 related Products with: A Strain-Based Staging Classification of Left Bundle Branch Block-Induced Cardiac Remodeling.

100ug Lyophilized1 mg100ug Lyophilized100ug50 ul1 mg2 1 mg0.2 mg100ug Lyophilized

Related Pathways

paperclip

Error loading info... Pleas try again later.