检索结果-内蒙古大学图书馆

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

Research on 3D point cloud registration algorithm based on FPFH and ColorICP

Research on 3D point cloud registration algorithm based on F...

引用

2024 International conference on Optical and Photonic Engineering, icOPEN 2024

作者： Pan, Junjie Zhang, Xu School of Mechatronic Engineering and Automation Shanghai University Shanghai China

ISBN: (数字)9781510688117

ISBN: (纸本)9781510688100

With the rapid development of 3D reconstruction, point cloud registration technology, a key step in 3D data processing, has garnered significant attention. Existing 3D point cloud registration technologies face issues such as low matching rates in coarse registration, misidentification of feature points, lengthy registration times, and low registration accuracy. Consequently, an improved registration algorithm that combines Fast Point Feature Histogram (FPFH) for coarse registration and Colored Iterative Closest Point (ColorICP) for fine registration has been proposed. The process begins with pre-processing the point cloud through downsampling filtration;next, point cloud features are extracted using FPFH to achieve feature matching and obtain the initial transformation matrix;finally, ColorICP is used for fine point cloud registration. Experiments on the Stanford bunny dataset from the standard point cloud library and real-world point cloud data demonstrate that the proposed registration algorithm effectively utilizes both color and geometric features of the point cloud, achieving significant improvements in registration accuracy and duration compared to traditional registration algorithms. © 2025 SPIE.

关键词： Point clouds image registration Histograms Detection and tracking algorithms reconstruction algorithms Nondestructive evaluation Picosecond phenomena Cameras RGB color model Algorithm development

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks in medical image reconstruction: A systematic literature review

引用

Computers in Biology and Medicine 2025年 191卷 110094-110094页

作者： Hussain, Jabbar Båth, Magnus Ivarsson, Jonas Dept. of Applied IT University of Gothenburg Forskningsgången 6 417 56 Sweden Department of Medical Radiation Sciences University of Gothenburg Sweden

Purpose: Recent advancements in generative adversarial networks (GANs) have demonstrated substantial potential in medical image processing. Despite this progress, reconstructing images from incomplete data remains a challenge, impacting image quality. This systematic literature review explores the use of GANs in enhancing and reconstructing medical imaging data. Method: A document survey of computing literature was conducted using the ACM Digital Library to identify relevant articles from journals and conference proceedings using keyword combinations, such as "generative adversarial networks or generative adversarial network," "medical image or medical imaging," and "image reconstruction." Results: Across the reviewed articles, there were 122 datasets used in 175 instances, 89 top metrics employed 335 times, 10 different tasks with a total count of 173, 31 distinct organs featured in 119 instances, and 18 modalities utilized in 121 instances, collectively depicting significant utilization of GANs in medical imaging. The adaptability and efficacy of GANs were showcased across diverse medical tasks, organs, and modalities, utilizing top public as well as private/synthetic datasets for disease diagnosis, including the identification of conditions like cancer in different anatomical regions. The study emphasized GAN's increasing integration and adaptability in diverse radiology modalities, showcasing their transformative impact on diagnostic techniques, including cross-modality tasks. The intricate interplay between network size, batch size, and loss function refinement significantly impacts GAN's performance, although challenges in training persist. Conclusions: The study underscores GANs as dynamic tools shaping medical imaging, contributing significantly to image quality, training methodologies, and overall medical advancements, positioning them as substantial components driving medical advancements. © 2025 The Authors

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

GTA-HDR: A Large-Scale Synthetic dataset for HDR image reconstruction

GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Recon...

引用

2025 IEEE/CVF Winter conference on Applications of Computer Vision, WACV 2025

作者： Barua, Hrishav Bakul Stefanov, Kalin Wong, KokSheik Dhall, Abhinav Krishnasamy, Ganesh Monash University Australia Tcs Research India

ISBN: (纸本)9798331510831

High Dynamic Range (HDR) content (i.e., images and videos) has a broad range of applications. However, capturing HDR content from real-world scenes is expensive and time-consuming. Therefore, the challenging task of reconstructing visually accurate HDR images from their Low Dynamic Range (LDR) counterparts is gaining attention in the vision research community. A major challenge is the lack of datasets, which capture diverse scene conditions (e.g., lighting, weather, locations) and various image features (e.g., color, contrast, saturation). To address this gap, we introduce GTA-HDR, a large-scale synthetic dataset of photo-realistic HDR images sampled from the GTA-V video game. We perform thorough evaluation of the proposed dataset, which enables significant qualitative and quantitative improvements of the state-of-the-art HDR image reconstruction methods. Furthermore, we demonstrate the effectiveness of the proposed dataset and its impact on additional computer vision tasks including 3D human pose estimation, human body part segmentation, and holistic scene segmentation. The dataset, data collection pipeline, and evaluation code are available at: https://***/HrishavBakulBarua/GTA-HDR. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

PROJECTION DECONVOLUTION ALGORITHM FOR image-reconstruction from incomplete SPECTRUM data

引用

APPLIED OPTICS 1988年第18期27卷 3800-3805页

作者： CHU, TH LEE, PC []The authors are with National Taiwan University Electrical Engineering Department Taipei Taiwan China.

We present an efficient algorithm—the projection deconvolution algorithm—to reconstruct a 2-D image from the accessed incomplete spectrum data and thereby improve the image resolution. This algorithm uses a sequence of 1-D discrete deconvolution operations to process a 2-D image (or higher-dimensional signal) on their projections. This algorithm is shown to be efficient in numerical calculation. Examples of numerical results are also presented.

关键词： Discrete Fourier transforms Fourier transforms image processing image resolution Matrix methods reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumor using Transfer Learning using Conventional Autoencoder with Long Short Term Memory Method 6

Detection of Brain Tumor using Transfer Learning using Conve...

引用

6th International conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Agalya, D. Kamalakkannan, S. Department of Computer Science School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India

ISBN: (纸本)9798331522667

Brain tumor (BT) has generate a significant health challenge by putting pressure on healthy brain parts or spreading into other areas as well as blocking the flow of fluid around the brain. BT diagnosis is an extensive and time consumption process that depends primarily on radiologists experience and interpretive capabilities. For the area of medical imaging, automatic segmentation of images by means of Deep Learning (DL) approaches. The DL approaches assist in transforming the sector, resulted in improving precision and effectiveness of investigations. However, there are various feature extraction mechanisms available. Therefore, the Recurrent Neural Network (RNN) is utilized for feature extraction and image classification. In model execution, the data have trained in transforming the test image as well as data features for minimizing the domain shift is calculated through the Convolutional Autoencoder (CAE) for reconstruction loss. This research has concentrated in building a model with VGG16 as a single test that subjected at inference and existing method is adopted as neural networks for AE as Transfer Learning (TL) that performs an image analysis task such as segmentation and even set as an adopter for pre training the model. The AE used to train from the source dataset and perform as the adaptors in optimizing during testing using a test subject for effective computation. Moreover, the Long Short Term Memory (LSTM) is utilized as RNN model with CAE for providing improved detection of BT in healthcare industries. Hence, the proposed CAE with LSTM is compared with AE with Convolutional Neural Network (CNN) for evaluating BT detection using MRI dataset with various BT type classifications. © 2025 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

QID2: An image-Conditioned Diffusion Model for Q-Space Up-Sampling of DWI data 15th

QID2: An Image-Conditioned Diffusion Model for Q-Space Up-S...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Chen, Zijian Wang, Jueqi Venkataraman, Archana Department of Electrical and Computer Engineering Boston University Boston United States

ISBN: (纸本)9783031869198

We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID2, takes as input a set of low angular resolution DWI data and uses this information to estimate the DWI data associated with a target gradient direction. We leverage a U-Net architecture with cross-attention to preserve the positional information of the reference images, further guiding the target image generation. We train and evaluate QID2 on single-shell DWI samples curated from the Human Connectome Project (HCP) dataset. Specifically, we sub-sample the HCP gradient directions to produce low angular resolution DWI data and train QID2 to reconstruct the missing high angular resolution samples. We compare QID2 with two state-of-the-art GAN models. Our results demonstrate that QID2 not only achieves higher-quality generated images, but it consistently outperforms state-of-the-art baseline methods in downstream tensor estimation across multiple metrics and in generalizing to downsampling scenario during testing. Taken together, this study highlights the potential of diffusion models, and QID2 in particular, for q-space up-sampling, thus offering a promising toolkit for clinical and research applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep Learning Diffusion Models Diffusion Weighted Imaging Q-Space Up-sampling Tensor reconstruction

来源：评论

学校读者我要写书评

暂无评论

image-reconstruction from incomplete PROJECTION data - ITERATIVE reconstruction-REPROJECTION TECHNIQUES

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1983年第12期30卷 838-841页

作者： HEFFERNAN, PB ROBB, RA Biodynamics Research Unit Department of Physiology and Biophysics Mayo Foundation Rochester MN USA

This paper addresses the task of image reconstruction from an incomplete set of projection data. Several methods which first estimate the missing data and then utilize standard reconstruction algorithms to obtain an image are investigated. Results from simulations are presented which illustrate the difficulty in comparing algorithms objectively, particularly when a simple test phantom is chosen. The incorporation of a priori information into the algorithm, an approach which has previously been discussed in the literature, is shown to produce faster convergence.

关键词： image reconstruction Heart Computed tomography reconstruction algorithms Biomedical measurements Iterative algorithms Control system synthesis Sensitivity analysis Linear systems Computational modeling

来源：评论

学校读者我要写书评

暂无评论

VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-view 3D reconstruction 17th

VIPNet: Combining Viewpoint Information and Shape Priors fo...

引用

17th Asian conference on Computer Vision, ACCV 2024

作者： Ye, Weining Li, Zhixuan Jiang, Tingting School of Computer Science Peking University Beijing100871 China College of Computing and Data Science Nanyang Technological University Singapore Singapore National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science National Biomedical Imaging Center Peking University Beijing100871 China

ISBN: (纸本)9789819609680

While the multi-view 3D reconstruction task has made significant progress, existing methods simply fuse multi-view image features without effectively leveraging available auxiliary information, especially the viewpoint information for guiding and associating features of different views. To this end, we propose to enhance multi-view 3D reconstruction with the power of viewpoint information. Specifically, a simple-yet-effective viewpoint estimator is designed to learn and provide comprehensive viewpoint knowledge for locating and associating learned features from different views. Moreover, to improve the 3D reconstruction quality when 2D images of only very few viewpoints are available, we propose to learn the shape prior knowledge to provide sufficient shape information for compensating the limited 2D observations. Overall, we present VIPNet, benefiting from Viewpoint Information and Shape Prior learning for high-quality multi-view 3D reconstruction. Extensive experiments validate the effectiveness of the proposed VIPNet, which achieves state-of-the-art performance on challenging datasets and shows well generalization ability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Back to the Future: Challenges of Sparse and Irregular Medical image Time Series

Back to the Future: Challenges of Sparse and Irregular M...

引用

Workshop on Longitudinal Disease Tracking and Modeling with Medical images and data, LDTM 2024, 5th International Workshop on Multiscale Multimodal Medical Imaging, MMMI 2024, 1st Workshop on Machine Learning for Multimodal/-sensor Healthcare data, ML4MHD2024 and Workshop on Multimodal Learning and Fusion Across Scales for Clinical Decision Support, ML-CDS 2024 held in conjunction with the 27th International conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Disch, Nico Albert Peretzke, Robin Roy, Saikat Ulrich, Constantin Zimmerer, David Stiefelhagen, Rainer Kleesiek, Jens Maier-Hein, Klaus Division of Medical Image Computing German Cancer Research Center Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Faculty of Mathematics and Computer Science University of Heidelberg Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany Karlsruhe Institute of Technology Karlsruhe Germany University Hospital Essen Essen Germany University Hospital Essen West German Cancer Center Essen Essen Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany

ISBN: (纸本)9783031845246

In longitudinal medical image analysis, most work focuses on regularly sampled images, or on tasks like regression or classification. However, in the clinical context, images are frequently generated irregularly due to factors such as cost constraints. This work tackles the problem of irregularly sampled longitudinal medical imaging by evaluating methods in segmentation and reconstruction tasks. We examine the reconstruction for real-life MRI from patients with Alzheimer’s Disease (AD), where the model predicts future MRI scans from an arbitrary number of input images sampled at irregular intervals. However, experiments show that most models cannot surpass the performance of using an image from the same patient at a different time point as a baseline. Therefore, we conducted experiments on a synthetic dataset to better isolate effects in temporal learning. These experiments offer insights into model behavior and serve as a benchmark for validating models’ longitudinal learning capability, thus providing a straightforward method to assess temporal understanding in a controlled environment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

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：