检索结果-内蒙古大学图书馆

3rd Workshop on Deep Generative Models for Medical image Computing and Computer Assisted Intervention, DGM4MICCAI 2023 Held in Conjunction with 26th International conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2023

3rd Workshop on Deep Generative Models for Medical Image Com...

引用

3rd Workshop on Deep Generative Models for Medical image Computing and Computer Assisted Intervention, DGM4MICCAI 2023 Held in Conjunction with 26th International conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2023

ISBN: (纸本)9783031537660

The proceedings contain 23 papers. The special focus in this conference is on Deep Generative Models for Medical image Computing and Computer Assisted Intervention. The topics include: Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model;A 3D Generative Model of Pathological Multi-modal MR images and Segmentations;Rethinking a Unified Generative Adversarial Model for MRI Modality Completion;diffusion Models for Generative Histopathology;shape-Guided Conditional Latent Diffusion Models for Synthesising Brain Vasculature;pre-training with Diffusion Models for Dental Radiography Segmentation;ICoNIK: Generating Respiratory-Resolved Abdominal MR reconstructions Using Neural Implicit Representations in k-Space;ultrasound image reconstruction with Denoising Diffusion Restoration Models;privacy Distillation: Reducing Re-identification Risk of Diffusion Models;Diffusion Model Based Knee Cartilage Segmentation in MRI;Semantic image Synthesis for Abdominal CT;CT reconstruction from Few Planar X-Rays with Application Towards Low-Resource Radiotherapy;Reference-Free Isotropic 3D EM reconstruction Using Diffusion Models;federated Multimodal and Multiresolution Graph Integration for Connectional Brain Template Learning;metrics to Quantify Global Consistency in Synthetic Medical images;MIM-OOD: Generative Masked image Modelling for Out-of-Distribution Detection in Medical images;towards Generalised Neural Implicit Representations for image Registration;investigating data Memorization in 3D Latent Diffusion Models for Medical image Synthesis;ViT-DAE: Transformer-Driven Diffusion Autoencoder for Histopathology image Analysis;anomaly Guided Generalizable Super-Resolution of Chest X-Ray images Using Multi-level Information Rendering;importance of Aligning Training Strategy with Evaluation for Diffusion Models in 3D Multiclass Segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deformable ConvNets and Muti-Scale Linear Attention for Brain Tumor Segmentation with Missing Modalities 4

Deformable ConvNets and Muti-Scale Linear Attention for Brai...

引用

4th IEEE International conference on data Science and Computer Application, ICDSCA 2024

作者： Xiong, Yuzhu Du, Hongwei Han, Qiuyi College of Information Science and Technology University of Science and Technology of China Anhui Hefei China

ISBN: (纸本)9798350368239

Brain tumor segmentation extracts meaningful information from various modalities (T1, T1c, T2, and FLAIR), each offering unique insights into brain structure and pathology, essential for accurate tumor subregion delineation. A common clinical challenge is the inability to acquire all modalities due to factors like image corruption or varying protocols. In such cases, most multimodal methods struggle with incomplete inputs, leading to poor performance. This paper proposes a network model, named as DCMLA-Net, using deformable convolution and multi-scale linear attention, effective for any subset of available modalities. Specifically, the deformable convolution extracts modality-specific information, while linear attention fuses multi-scale features, after which the fused features are fed into a deformable convolution decoder to restore spatial resolution and generate the final tumor segmentation. Experiments on the BraTS 2018 dataset show that the proposed method outperforms existing approaches with missing modalities. ©2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Impact of angular sampling interval on image reconstruction from limited-angular-range data

Impact of angular sampling interval on image reconstruction ...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Zhang, Zheng Chen, Buxin Xia, Dan Sidky, Emil Y. Pan, Xiaochuan Univ Chicago Dept Radiol Chicago IL 60637 USA Univ Chicago Dept Radiat & Cellular Oncol Chicago IL 60637 USA

ISBN: (数字)9781510649385

ISBN: (纸本)9781510649385;9781510649378

In computed tomography (CT) imaging, recent developments in reconstruction algorithm and scan configuration design have provided useful tools for image reconstruction from data collected over a limited-angular range (LAR). In this work, we aim to investigate the impact of angular sampling interval on the accuracy of reconstruction from LAR data. In specific, we employ a two-orthogonal-arc scan configuration, and collect data from a numerical chest phantom over an LAR with various angular intervals. We then investigate image reconstruction by using the directional-total-variation (DTV) algorithm and evaluate reconstructions qualitatively and quantitatively. Results show that increased angular sampling interval results in degraded image quality. Results of the simulation study also indicate an appropriate interval for sufficient reconstruction accuracy under specific imaging conditions, which may provide insights for the upper-bound performance of reconstructions in practical use.

关键词： Optimization-based reconstruction directional total variation primal dual algorithm two orthogonal arcs

来源：评论

学校读者我要写书评

暂无评论

6th International Workshop on Graphs in Biomedical image Analysis, GRAIL 2024

6th International Workshop on Graphs in Biomedical Image Ana...

引用

6th International Workshop on Graphs in Biomedical image Analysis, GRAIL 2024

ISBN: (纸本)9783031832420

The proceedings contain 12 papers. The special focus in this conference is on Graphs in Biomedical image Analysis. The topics include: Graph Neural Networks: A Suitable Alternative to MLPs in Latent 3D Medical image Classification?;graph Residual Noise Learner Network for Brain Connectivity Graph Prediction;prediction of Radiological Diagnostic Errors from Eye Tracking data Using Graph Neural Networks and Gaze-Guided Transformers;exploring Graphs as data Representation for Disease Classification in Ophthalmology;GAMMA-PD: Graph-Based Analysis of Multi-Modal Motor Impairment Assessments in Parkinson’s Disease;multi-resolution Histopathology Patch Graphs for Ovarian Cancer Subtyping;histoGraphCoarse: Strategizing Graph Coarsening Techniques for Efficient Analysis of Gigapixel Histopathological images;mesh Registration via Geometric Feature Homogenization and Offset Cross-Attention: Application to 3D Photogrammetry;SANGRIA: Surgical Video Scene Graph Optimization for Surgical Workflow Prediction;DVasMesh: Deep Structured Mesh reconstruction from Vascular images for Dynamics Modeling of Vessels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variational Manifold Learning from incomplete data: Application to Multislice Dynamic MRI

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2022年第12期41卷 3552-3561页

作者： Zou, Qing Ahmed, Abdul Haseeb Nagpal, Prashant Priya, Sarv Schulte, Rolf F. Jacob, Mathews Univ Iowa Dept Elect & Comp Engn Iowa City IA 52242 USA Philips Healthcare Rochester MN 55311 USA Univ Wisconsin Madison Dept Radiol Madison WI 53706 USA Univ Iowa Dept Radiol Iowa City IA 52242 USA Gen Elect Healthcare D-80807 Munich Germany

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. However, fully sampled data is often unavailable in a variety of problems, including the recovery of dynamic and high-resolution magnetic resonance imaging (MRI). We introduce a novel variational approach to learn a manifold from undersampled data. The VAE uses a decoder fed by latent vectors, drawn from a conditional density estimated from the fully sampled images using an encoder. Since fully sampled images are not available in our setting, we approximate the conditional density of the latent vectors by a parametric model whose parameters are estimated from the undersampled measurements using back-propagation. We use the framework for the joint alignment and recovery of multi-slice free breathing and ungated cardiac MRI data from highly undersampled measurements. Experimental results demonstrate the utility of the proposed scheme in dynamic imaging alignment and reconstructions.

关键词： Variational autoencoder generative model CNN manifold approach unsupervised learning free breathing cardiac magnetic resonance imaging (MRI) image reconstruction

来源：评论

学校读者我要写书评

暂无评论

MvAV-pix2pixHD: Multi-view Aerial View image Translation

MvAV-pix2pixHD: Multi-view Aerial View Image Translation

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yu, Jun Lu, Keda Du, Shenshen Xu, Lin Chang, Peng Liu, Houde Lan, Bin Liu, Tianyu Univ Sci & Technol China Hefei Peoples R China Ping An Technol Co Ltd Beijing Peoples R China PAII Inc Beijing Peoples R China Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China Jianghuai Adv Technol Ctr Hefei Peoples R China

ISBN: (纸本)9798350365474

Multi-modal aerial view image translation involves converting aerial images from one modality to another while preserving basic details and features. These modalities encompass Synthetic Aperture Radar (SAR), Infrared (IR), Visible Light (RGB), Electro-Optical (EO), and other image types. Recently, various methods have been proposed to tackle this task, but the focus tends to be on paired image research, overlooking the discrepancies found in aerial images of the same location captured at different times and angles, termed incomplete matching or multi-view image translation. Consequently, we propose MvAV-pix2pixHD to address this issue. For multi-view data sampling, we propose two methods: random sampling and time-priority sampling. Additionally, within the pix2pixHD framework, we introduce an inverse generator to ensure the basic semantic features of the generated images and incorporate three robust loss functions to constrain the authenticity of the generated images. We conduct extensive experiments on two multi-view image translation tasks in the Multi-modal Aerial View imagery Challenge: Translation (MAVIC-T). Experimental results demonstrate the superiority of our proposed method, and we achieved second place in the MAVIC-T competition in the 20th IEEE Workshop on Perception Beyond the Visible Spectrum of the CVPR 2024.

关键词： Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

MARVIS: Motion & Geometry Aware Real and Virtual image Segmentation

MARVIS: Motion & Geometry Aware Real and Virtual Image Segme...

引用

2024 International conference on Intelligent Robots and Systems

作者： Wu, Jiayi Lin, Xiaomin Negandari, Shahriar Fermuller, Cornelia Aloimonos, Yiannis Univ Maryland Maryland Robot Ctr College Pk MD 20742 USA Univ Miami Coral Gables FL 33146 USA

ISBN: (纸本)9798350377712;9798350377705

Tasks such as autonomous navigation, 3D reconstruction, and object recognition near the water surfaces are crucial in marine robotics applications. However, challenges arise due to dynamic disturbances, e.g., light reflections and refraction from the random air-water interface, irregular liquid flow, and similar factors, which can lead to potential failures in perception and navigation systems. Traditional computer vision algorithms struggle to differentiate between real and virtual image regions, significantly complicating tasks. A virtual image region is an apparent representation formed by the redirection of light rays, typically through reflection or refraction, creating the illusion of an object's presence without its actual physical location. This work proposes a novel approach for segmentation on real and virtual image regions, exploiting synthetic images combined with domain-invariant information, a Motion Entropy Kernel, and Epipolar Geometric Consistency. Our segmentation network does not need to be re-trained if the domain changes. We show this by deploying the same segmentation network in two different domains: simulation and the real world. By creating realistic synthetic images that mimic the complexities of the water surface, we provide fine-grained training data for our network (MARVIS) to discern between real and virtual images effectively. By motion & geometry-aware design choices and through comprehensive experimental analysis, we achieve state-of-the-art real-virtual image segmentation performance in unseen real world domain, achieving an IoU over 78% and a F-1-Score over 86% while ensuring a small computational footprint. MARVIS offers over 43 FPS (8 FPS) inference rates on a single GPU (CPU core). Our code and dataset are available here https://***/jiayi-wu-umd/MARVIS.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Estimation of 3D Shape and Volume of Fire Plumes from Multiple Views 4

Estimation of 3D Shape and Volume of Fire Plumes from Multip...

引用

4th European Symposium on Fire Safety Science

作者： Blanco, J. A. Pardas, M. Casas, J. R. Paugam, R. Agueda, A. Wagner, J. Parsons, R. A. Planas, E. Univ Politecn Catalunya BarcelonaTech Image Proc Grp GPI Dept Signal Theory & Commun Jordi Girona 1-3Edifici D5 Barcelona 08034 Spain Univ Politecn Catalunya BarcelonaTech Ctr Technol Risk Studies CERTEC Chem Engn Dept Av Eduard Maristany 16 Barcelona 08019 Spain Univ Montana 406 ISB32 Campus Dr Missoula MT 59812 USA US Forest Serv Fire Sci Lab Rocky Mt Res Stn 5775 W Highway 10 Missoula MT 59801 USA

This study evaluates deep-learning and Shape from Silhouette (SfS) methods for 3D reconstruction of smoke plumes. It demonstrates the deep-learning method's superiority in cases with limited camera views and calibration data, achieving high-quality reconstructions of semi-transparent smoke without precise calibration. The research emphasizes the significance of pre-processing and data appearance for neural network efficacy. By improving 3D reconstruction techniques, this work aids in advancing wildfire tracking and environmental analysis, offering a practical approach for real-world applications in fire science.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

A New Rebinning reconstruction Method for the Low Dose CT Scanners with Flying Focal Spot 22nd

A New Rebinning Reconstruction Method for the Low Dose CT Sc...

引用

22nd International conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Pluta, Piotr Cierniak, Robert Czestochowa Tech Univ Dept Intelligent Comp Syst Czestochowa Poland

ISBN: (纸本)9783031425073;9783031425080

This paper presents an original approach to the image reconstruction problem for spiral CT scanners where the multi-source and/or the Flying Focal Spot (FFS) technology is implemented. The geometry of those scanners causes problems for computed tomography systems based on traditional (FDK) reconstruction methods. Therefore, we propose an original rebinning strategy, where does not occur the problem of non-equiangular X-rays. It is possible to implement this approach in all three types of CT scanners (only Multi-Source, only Flying Focal Spot, mixed Multi-Source with Flying Focal Spot). This approach is divided into two blocks (rebinning and iterative reconstruction procedure). This method is based on statistical model-based iterative reconstruction (MBIR), where the reconstruction problem is formulated as a shift-invariant system (a continuous-to-continuous data model). Our method allows for reducing the X-ray dose absorbed by patients during examinations. The most significant feature of the proposed method is the possibility of parallel implementation using the various GPU graphic card - what we have done for the NVIDIA graphic card. This fact resulted in the acceleration of the calculation and the significantly shortened time for the first reconstructed image.

关键词： X-ray computed tomography multi source tomography flying focal spot statistical method image reconstruction from projections rebinning method

来源：评论

学校读者我要写书评

暂无评论

Partial-Label Contrastive Representation Learning for Fine-Grained Biomarkers Prediction from Histopathology Whole Slide images

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第1期29卷 396-408页

作者： Zheng, Yushan Wu, Kun Li, Jun Tang, Kunming Shi, Jun Wu, Haibo Jiang, Zhiguo Wang, Wei Beihang Univ Beijing Adv Innovat Ctr Biomed Engn Sch Engn Med Beijing 100191 Peoples R China Beihang Univ Image Proc Ctr Sch Astronaut Beijing 100191 Peoples R China Hefei Univ Technol Sch Software Hefei 230009 Peoples R China Univ Sci & Technol China Affiliated Hosp USTC 1 Dept Pathol Div Life Sci & Med Hefei 230036 Peoples R China Univ Sci & Technol China Intelligent Pathol Inst Div Life Sci & Med Hefei 230036 Peoples R China

In the domain of histopathology analysis, existing representation learning methods for biomarkers prediction from whole slide images (WSIs) face challenges due to the complexity of tissue subtypes and label noise problems. This paper proposed a novel partial-label contrastive representation learning approach to enhance the discrimination of histopathology image representations for fine-grained biomarkers prediction. We designed a partial-label contrastive clustering (PLCC) module for partial-label disambiguation and a dynamic clustering algorithm to sample the most representative features of each category to the clustering queue during the contrastive learning process. We conducted comprehensive experiments on three gene mutation prediction datasets, including USTC-EGFR, BRCA-HER2, and TCGA-EGFR. The results show that our method outperforms 9 existing methods in terms of Accuracy, AUC, and F1 Score. Specifically, our method achieved an AUC of 0.950 in EGFR mutation subtyping of TCGA-EGFR and an AUC of 0.853 in HER2 0/1+/2+/3+ grading of BRCA-HER2, which demonstrates its superiority in fine-grained biomarkers prediction from histopathology whole slide images.

关键词： Representation learning Task analysis Biomarkers Histopathology Contrastive learning Annotations Feature extraction Gene mutation prediction partial-label learning. representation learning WSI analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：