检索结果-南通市图书馆

MCIF-Transformer Mask RCNN:Multi-Branch Cross-Scale Interactive Feature Fusion Transformer Model for PET/CT Lung Tumor Instance Segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4371-4393页

作者： Huiling Lu Tao Zhou School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China School of Computer Science and Engineering North Minzu UniversityYinchuan750021China Key Laboratory of image and graphics Intelligent Processing of State Ethnic Affairs Commission NorthMinzu UniversityYinchuan750021China

The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided ***,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are *** solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung *** pixel dependence relationship is established in local and non-local fields to improve the model perception ***,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained ***,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic ***,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image *** results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this *** method has positive significance for the detection of lung tumors.

关键词： PET/CT images instance segmentation mask RCNN interactive fusion transformer

Apatite Fission-Track Thermochronology in the Tamusu Area,Bayingobi Basin,NW China,and its Geological Significance

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Geologica Sinica(English Edition) 2024年第3期98卷 585-601页

作者： TONG Qinlong QIN Mingkuan YE Fawang CNNC Beijing Research institute of Uranium Geology National Key Laboratory of Remote Sensing Information and Image Analysis TechnologyBeijing 100029China

The Bayingobi basin is located in the middle of Central Asia Orogenic Belt,at the intersection of Paleo-Asian Ocean and Tethys Ocean,as well as the junction of multiple tectonic *** unique tectonic setting underpins the basin's intricate history of tectonic *** unravel the multifaceted tectono-thermal evolution within the southwestern region of the basin and to elucidate the implications of sandstone-hosted uranium mineralization,granitic and clastic rock samples were collected from the Zongnai *** and Yingejing depression,and apatite fission track(AFT)dating and thermal history simulation analysis were *** dating findings reveal that the apparent ages of all samples fall within the range of 244 Ma to 112 *** particular,the bedrock of the Zongnai *** Jurassic detrital apatite fission tracks have undergone complete annealing,capturing the uplift-cooling ***,the AFT ages of Cretaceous detrital rocks are either equivalent to or notably exceed the age of sedimentary strata,signifying the cooling age of the provenance.A comprehensive examination of AFT ages and palaeocurrent direction analyses suggests that the Cretaceous source in the Tamusu area predominantly originated from the central and southern sectors of the Zongnai ***,at a certain juncture during the Late Early Cretaceous,the Cretaceous provenance expanded to include the northern part of the Zongnai *** on the results of thermal history simulations and previous studies,it is considered that the Tamusu area has undergone four distinct tectonic uplift events since the Late *** first is the Late Permian to Early Triassic(260-240 Ma),which is associated with the closure of the Paleo-Asian Ocean and the accretionary orogeny within the Alxa *** second uplift event took place in the Early Jurassic(190-175 Ma)and corresponded to intraplate orogeny following the closure of the Paleo-Asian *** third uplift event is the Lat

关键词： apatite fission-track tectono-thermal history sandstone-hosted uranium deposit Bayingobi basin Central Asian Orogenic Belt

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4863-4882页

作者： Tao Zhou Yujie Guo Caiyue Peng Yuxia Niu Yunfeng Pan Huiling Lu School of Computer Science and Engineering North Minzu UniversityYinchuan750021China School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China Key Laboratory of image and graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu UniversityYinchuan750021China

Computer-aided diagnosis of pneumonia based on deep learning is a research ***,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this *** main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale *** MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features ***,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature ***,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different *** verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried *** the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,*** the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,*** model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

关键词： Pneumonia X-ray image ResNet multi-scale feature direction feature transformer

Combined UAMP and MF Message Passing Algorithm for Multi-Target Wideband DOA Estimation with Dirichlet Process Prior

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第4期29卷 1069-1081页

作者： Shanwen Guan Xinhua Lu Ji Li Rushi Lan Xiaonan Luo Guangxi Key Laboratory of image and Graphic Intelligent Processing Guilin University of Electronic TechnologyGuilin 541004China Guilin Huigu institute of AI Industrial Technology Guilin 541004China School of Information Engineering Nanyang Institute of TechnologyNanyang 473000China

When estimating the direction of arrival (DOA) of wideband signals from multiple sources, the performance of sparse Bayesian methods is influenced by the frequency bands occupied by signals in different directions. This is particularly true when multiple signal frequency bands overlap. Message passing algorithms (MPA) with Dirichlet process (DP) prior can be employed in a sparse Bayesian learning (SBL) framework with high precision. However, existing methods suffer from either high complexity or low precision. To address this, we propose a low-complexity DOA estimation algorithm based on a factor graph. This approach introduces two strong constraints via a stretching transformation of the factor graph. The first constraint separates the observation from the DP prior, enabling the application of the unitary approximate message passing (UAMP) algorithm for simplified inference and mitigation of divergence issues. The second constraint compensates for the deviation in estimation angle caused by the grid mismatch problem. Compared to state-of-the-art algorithms, our proposed method offers higher estimation accuracy and lower complexity.

关键词： wideband direction of arrival(DOA)estimation sparse Bayesian learning(SBL) unitary approximate message passing(UAMP)algorithm Dirichlet process(DP)

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第9期80卷 4813-4832页

作者： Tao Zhou Yunfeng Pan Huiling Lu Pei Dang Yujie Guo Yaxing Wang School of Computer Science and Engineering North Minzu UniversityYinchuan750021China School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China Key Laboratory of image and graphics Intelligent Processing of State Ethnic Affairs Commission NorthMinzuUniversityYinchuan750021China

Multimodal lung tumor medical images can provide anatomical and functional information for the same *** as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and *** to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key *** solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this ***,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate ***,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after ***,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic ***,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local *** proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,*** is of great significance for computer-aided diagnosis.

关键词： Medical image segmentation U-Net saliency feature guidance cross-modal feature enhancement cross-dimension feature enhancement

A CSP-based retraining framework for motor imagery based brain-computer interfaces

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 349-350页

作者： Xue JIANG Lubin MENG Xinru CHEN Dongrui WU Key Laboratory of image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research institute

Motor imagery(MI) is a classic paradigm of electroencephalogram(EEG)-based brain-computer interfaces(BCIs). It entails individuals mentally imagining the movement of a body part without physically performing it. EEG s... 详细信息

关键词： Classification (of information)

Applications of artificial intelligence to lipid nanoparticle delivery

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第7期90卷 88-97页

作者： Ye Yuan Yuqi Wu Jiabei Cheng Kaiyuan Yang Yilin Xia Hongguang Wu Xiaoyong Pan institute of image Processing and Pattern Recognition Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of ChinaChina Songjiang Research institute Songjiang District Central HospitalShanghai Jiao Tong University School of MedicineShanghaiChina

Lipid nanoparticles(LNPs)are nanocarriers composed of four lipid components and can be used for gene therapy,protein replacement,and vaccine ***,LNPs also face several challenges,such as toxicity,immune activation,and low delivery *** overcome these challenges,artificial intelligence can be used to optimize the design and formulation of LNPs,as well as to predict their properties and ***,antibody-targeted conjugation can be used to enhance the specificity and selectivity of LNPs by attaching an antibody that recognizes a specific antigen on the cell surface to LNPs.

关键词： Artificial intelligence Lipid nanoparticles Antibody Targeted conjugation

Multi-point temperature measurements in packed beds using phosphor thermometry and ray tracing simulations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第2期85卷 77-88页

作者： Guangtao Xuan Mirko Ebert Simson Julian Rodrigues Nicole Vorhauer-Huget Christian Lessig Benoit Fond institute of Fluid Dynamics and Thermodynamics OVGU MagdeburgUniversitaetsplatz 2Magdeburg39106Saxony-AnhaltGermany institute of Simulations and graphics OVGU MagdeburgUniversitaetsplatz 2Magdeburg39106Saxony-AnhaltGermany institute of Process Engineering OVGU MagdeburgUniversitaetsplatz 2Magdeburg39106Saxony-AnhaltGermany ONERA The French Aerospace LabDepartment of AerodynamicsAeroelasticity and Aeroacoustics(DAAA)Paris-Saclay University8rue des VertugadinsMeudon92190France

Packed bed reactors are commonly found in the process industry,for example in flame-assisted calci-nation for cement *** the heat transfer inside the bed is essential for process control,product quality and energy *** we propose a technique to determine the internal temperature distribution of packed beds based on a combination of lifetime-based phosphor ther-mometry,ray tracing simulations,and assimilation of temperature data using finite element heat transfer *** establish and validate the technique,we considered a reproducible regular packing of 6 mm diameter aluminum spheres,with one of the spheres in the top layer being electrically *** a sphere inside the packing is coated with thermographic phosphors and excitation light is directed to-wards the packing,luminescence from the coated sphere exits the packed bed after multiple reflection and the sphere's temperature can be *** measurements showed that the temper-ature obtained by phosphor thermometry is independent of the luminescent sphere *** imaging the luminescence on a camera,the luminescence distribution in recorded image depended,however,on the position of the ***,in setups with multiple phosphor-coated spheres,their signals can be separated using a least squares *** demonstrate the approach using a setup with three luminescent spheres and validated the temperature readings against thermocouple *** obtain the spatial signatures for individual sphere positions required for the least squares fit,ray tracing simulations were *** provide an efficient alternative to single sphere measurements that are only practical for regular spherical packed ***-point measurements were used as input to a finite element heat transfer simulations to determine parameters such as particle-to-particle air gap *** these,the full temperature distribution inside the bed could be assimilated from the meas

关键词： Packed beds Phosphor thermometry Ray tracing Heat transfer simulation Data assimilation

EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 130-146页

作者： Yingjian LIU Jiang LI Xiaoping WANG Zhigang ZENG School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Key Laboratory of image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education institute of Artificial Intelligence Huazhong University of Science and Technology

Emotion recognition in conversation(ERC) has attracted growing attention in recent years as a result of the advancement and implementation of human-computer interface technologies. In this paper,we propose an emotional inertia and contagion-driven dependency modeling approach(EmotionIC) for ERC tasks. Our EmotionIC consists of three main components, i.e., identity masked multi-head attention(IMMHA), dialogue-based gated recurrent unit(DiaGRU), and skip-chain conditional random field(SkipCRF).Compared to previous ERC models, EmotionIC can model a conversation more thoroughly at both the feature-extraction and classification levels. The proposed model attempts to integrate the advantages of attention-and recurrence-based methods at the feature-extraction level. Specifically, IMMHA is applied to capture identity-based global contextual dependencies, while Dia GRU is utilized to extract speaker-and temporal-aware local contextual information. At the classification level, SkipCRF can explicitly mine complex emotional flows from higher-order neighboring utterances in the conversation. Experimental results show that our method can significantly outperform the state-of-the-art models on four benchmark *** ablation studies confirm that our modules can effectively model emotional inertia and contagion.

关键词： emotion recognition in conversation emotional inertia and contagion multi-head attention gated recurrent unit conditional random field