检索结果-内蒙古大学图书馆

2024 International conference on Intelligent Robots and Systems

作者： Tan, Longyue Deng, Zhaokun Hao, Mingrui Zhang, Pengcheng Hou, Xilong Chen, Chen Gu, Xiaolin Zhou, Xiao-Hu Hou, Zeng-Guang Wang, Shuangyi Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci Ctr Artificial Intelligence & Robot Hong Kong Inst Sci & Innovat Hong Kong Peoples R China Lingshu Med Co Suzhou 215123 Peoples R China

ISBN: (纸本)9798350377712;9798350377705

Ultrasound (US) imaging of the carotid artery (CA) is a non-invasive diagnostic tool widely used in the medical field to assess the condition of the carotid artery, thereby predicting the risk of cardiovascular and cerebrovascular diseases. However, implementing this method in primary healthcare can be challenging due to the requirement for professionally trained sonographers. With the adoption of US robotic devices, the probe pose can be acquired while scanning, offering the possibility for 3D reconstruction and providing analyses that are not dependent on operator experience. This article introduces a method to semi-automatically acquire serialized US images of the common carotid artery (CCA). The method involves a specially designed robotic device built with a 6-RSU parallel mechanism, which is controlled according to robot pose, force sensor data and synchronous US images. To validate the images acquired, a method is proposed to segment the intima-media of CCA and calculate the intima-media thickness (IMT), which is a key indicator for cerebrovascular events prediction. After that, we propose an algorithm to reconstruct CCA into 3D voxel data with patient movement and cardiac cycle compensated, and a longitudinal view US image of CCA can be resliced from the voxel. The methods are tested on human subjects and the results indicate that the system and workflow can provide both quantitative and qualitative information of CCA for further diagnosis.

关键词： Ultrasonic imaging

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

Super-resolution knowledge-distillation-based low-resolution steel defect images classification

Super-resolution knowledge-distillation-based low-resolution...

引用

2023 International conference on Computer Graphics, Artificial Intelligence, and data Processing, ICCAID 2023

作者： Zhang, Shun Pei, Zixiang Ren, Zekai Shihezi University 221 Beisi Road Xiangyang Street Xinjiang Uygur Autonomous Region Shihezi City832003 China

ISBN: (纸本)9781510677685

Due to cost and equipment limitations, steel surface defect images are often of low resolution, significantly impairing the recognizability of key features within the images and thereby reducing the accuracy of automated detection. To address this issue, this paper proposes a classification method for low-resolution steel defect images based on super-resolution knowledge distillation. This method initially employs advanced super-resolution techniques to reconstruct low-resolution images, aiming to restore critical image details and features. Subsequently, knowledge distilled from deep learning models trained on high-resolution images is transferred to models specifically designed for low-resolution images. This approach combines the advantages of super-resolution image reconstruction and the efficiency of knowledge distillation. It not only enhances the quality of low-resolution images but also maintains the lightweight nature of the model, making it suitable for real-time detection scenarios. A series of experiments conducted on publicly available steel defect dataset demonstrate that the method proposed effectively enhances the classification accuracy of low-resolution steel defect images. This achievement is of significant importance in advancing industrial automated defect detection technologies and provides a new research direction in the field of low-resolution image processing. © 2024 SPIE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Compressive Sensing Magnetic Resonance image reconstruction and Denoising using Convolutional Neural Network 1

Compressive Sensing Magnetic Resonance Image Reconstruction ...

引用

1st International conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2021

作者： Singh, Ram Kaur, Lakhwinder Department of Computer Science and Engineering Punjabi University Patiala India

Restoration of high-quality brain Magnetic Resonance image (MRI) from the sparse under-sampled complex k-space signal is a widely studied ill-posed inverse transform problem. A deep learning-based data-adaptive and data-driven convolutional technique has been proposed for high-quality MRI recovery from its under-sampled complex domain k-space signal. The uniform subsampling process is very slow in phase-encoding to generate high-resolution images. The longer scan times degrade the perceptual image quality. Various factors contribute to image degradation during data acquisition such as the inception of body motion artifacts, the thermal energy effects of the body, and random noise artifacts due to voltage fluctuations. Keeping in view the patient's critical condition and comfort, longer scan times are not preferred in practice. To reduce the image acquisition time, noise levels, and motion artifacts in the MR images, Compressive Sensing (CS) provides an accelerated way to reconstructs the high-quality MR image from very limited signal measurements acquired much below the Nyquist rate. However, such data acquisition strategies require advanced computer algorithms for the reconstruction of high-quality MRI from the undersampled MRI data. An improved CNN-based MRI reconstructed algorithm has been presented in this paper which shows better performance to reconstruct high-quality MRI than similar other MR image reconstruction algorithms. The performance of the proposed algorithm is measured by image quality checking tools such as normalized-MSE, PSNR, and SSIM. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Potential of Deep Learning for image Processing 11

Potential of Deep Learning for Image Processing

引用

11th International conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Gill, Rupali Logeshwaran, J. Aggarwal, Priyanshi Srivastava, Durgesh Verma, Aditya Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Sri Eshwar College of Engineering Department of Ece Coimbatore641202 India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun248002 India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350350357

Deep learning has emerged as an effective tool for fixing a diffusion of image processing responsibilities such as object detection, category, segmentation, and reconstruction. This technique involves using synthetic neural networks to learn features and styles immediately from a big data set, rather than relying on predefined rules or handmade capabilities. It has resulted in enormous enhancements in performance for photo processing duties, surpassing traditional strategies in accuracy and performance. One key gain of deep getting to know for image processing is its capacity to deal with complicated and excessive-dimensional records, including photos, with many parameters. It permits the creation of extra complicated and accurate models that can deal with numerous records and produce better outcomes. Additionally, deep studying fashions can continuously enhance and adapt as they are uncovered to greater statistics, making them greater sturdy and flexible in processing picks. © 2024 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised image-to-image Translation with Style Consistency 6th

Unsupervised Image-to-Image Translation with Style Consisten...

引用

6th Chinese conference on Pattern Recognition and Computer Vision (PRCV)

作者： Lai, Binxin Wang, Yuan-Gen Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou Peoples R China

ISBN: (纸本)9789819985364;9789819985371

Unsupervised image-to-image Translation (UNIT) has gained significant attention due to its strong ability of data augmentation. UNIT aims to generate a visually pleasing image by synthesizing an image's content with another's style. However, current methods cannot ensure that the style of the generated image matches that of the input style image well. To overcome this issue, we present a new two-stage framework, called Unsupervised image-to-image Translation with Style Consistency (SC-UNIT), for improving the style consistency between the image of the style domain and the generated image. The key idea of SC-UNIT is to build a style consistency module to prevent the deviation of the learned style from the input one. Specifically, in the first stage, SC-UNIT trains a content encoder to extract the multiple-layer content features wherein the last-layer's feature can represent the abstract domain-shared content. In the second stage, we train a generator to integrate the content features with the style feature to generate a new image. During the generation process, dynamic skip connections and multiple-layer content features are used to build multiple-level content correspondences. Furthermore, we design a style reconstruction loss to make the style of the generated image consistent with that of the input style image. Numerous experimental results show that our SC-UNIT outperforms state-of-the-art methods in image quality, style diversity, and style consistency, even for domains with significant visual differences. The code is available at https://***/GZHU-DVL/SC-UNIT.

关键词： Unsupervised image-to-image Translation Prior Distillation Generative Adversarial Network Style Consistency

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Attentive Pixels Network in Face Super-Resolution at Scale Factor of 16 20

Efficient Deep Attentive Pixels Network in Face Super-Resolu...

引用

20th International conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Aung, Hein Htet Aramvith, Supavadee Faculty of Engineering Chulalongkorn University Multimedia Data Analytics and Processing Research Unit Department of Electrical Engineering Bangkok Thailand

ISBN: (纸本)9798350310467

Nowadays, Face Super-Resolution (FSR) models utilize the fusion approach, which combines the attention technique with the super-resolution network. The fusion approach has been proposed and solves the problem of FSR. Facial attributes have been effectively used to guide low-level information of the face to perform robust face image restoration. Iterative techniques appraised the value of facial landmarks to boost the reconstruction capability of the super-resolution network. Nevertheless, the network parameters in FSR are high, while the learning rate is still low. This paper proposes an attention mechanism combined with the Face Alignment Network (FAN). The proposed attention mechanism consists of channel attention and a non-local module. Our proposed model outperforms at the scale of $\times 16$ compared to the other state-of-the-art models. © 2023 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Research on spatial technology of distribution network digital twin model based on multimodule data fusion 2

Research on spatial technology of distribution network digit...

引用

2nd International conference on Physics, Photonics, and Optical Engineering, ICPPOE 2023

作者： Li, Fan He, Zhimin Tian, Yingjie Song, Jie Su, Yun State Grid Shanghai Municipal Electric Power Company Shanghai200000 China State Grid Smart Grid Research Institute Co. LTD Jiangsu Nanjing210003 China

ISBN: (纸本)9781510674684

In this paper, the generation technology of distribution network digital twin scene based on multi-module data fusion is studied. Firstly, multi-module data fusion is carried out in complex dynamic operating environment of distribution. Aiming at the deficiency of constructing digital twins from a single model source, various digital model resources in distribution link are collected and integrated to support the construction of hierarchical digital twin model of distribution network. The second step is to carry out the multi-source comprehensive reconstruction and entity hierarchical processing of the distribution network, establish the multi-source digital model of the universal distribution network equipment, and realize the global and local multi-level and multi-scale model display of the distribution network environment on the basis of comprehensive reconstruction;The third step is to configure the digital twin spatial mapping based on the distribution network's panoramic data fusion to realize the panoramic mapping between the real image, spatial coordinates and equipment monitoring data and the digital twin model, as well as multi-layer semantic information embedding such as equipment, region and job, forming the corresponding characteristics of multi-block, multi-level and multi-type digital twins. Finally, the distribution network panoramic digital twin model is dynamically updated to realize the projection of various real-time perception data to the digital twin, and the digital twin is updated synchronously and grown dynamically. © COPYRIGHT 2024 SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Volumetric, dual-domain x-ray CT reconstruction with deep learning

Volumetric, dual-domain x-ray CT reconstruction with deep le...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Clark, Darin P. Badea, Cristian T. Duke Univ Dept Radiol Quantitat Imaging & Anal Lab Med Ctr Durham NC 27710 USA

ISBN: (数字)9781510649385

ISBN: (纸本)9781510649385;9781510649378

Novel deep learning (DL) methods have produced state-of-the-art results in nearly every area of x-ray CT data processing. However, DL-driven, iterative reconstruction remains challenging because of the volumetric nature of many reconstruction problems: the system matrix relating the projection and image domains is too large to incorporate into network training. Past approaches for 2D reconstruction include consecutive projection and image domain processing in a single pass, employing a known analytical operator between domains, and unrolling an established iterative method, solving a series of sub-problems with separately trained networks. Here, we synergize these approaches within the split Bregman optimization framework. Specifically, we formulate a cost function and supervised training approach which yield an analytical reconstruction sub-step, to transform between domains, and a regularization sub-step, which is consistent between iterations. Combined with projection and image domain splitting, these properties reduce the number of free parameters which must be learned, making volumetric, dual-domain data processing more practical. Here, we simultaneously train 3D image and projection domain regularizers using supervised learning during iterative reconstruction with promising algorithm convergence results. Our trained reconstruction framework outperforms a more traditional iterative reconstruction method when starting from 90 noisy projections of the MOBY mouse phantom (image SSIM: iterative, 0.65;DL, 0.86). Furthermore, we successfully apply the model to similarly sampled in vivo mouse data acquired with micro-CT, reducing noise from 277 HU in an initial reconstruction to 41 HU in the DL reconstruction compared with 63 HU of noise in a fully sampled reference reconstruction.

关键词： machine learning x-ray CT image reconstruction small animal imaging

来源：评论

学校读者我要写书评

暂无评论

Warmstart Approach for Accelerating Deep image Prior reconstruction in Dynamic Tomography 5

Warmstart Approach for Accelerating Deep Image Prior Reconst...

引用

5th International conference on Medical Imaging with Deep Learning (MIDL)

作者： Knopp, Tobias Grosser, Mirco Univ Med Ctr Hamburg Eppendorf Sect Biomed Imaging Hamburg Germany Hamburg Univ Technol Inst Biomed Imaging Hamburg Germany

Deep image prior (DIP) has been successfully used in the field of tomography to obtain high-quality images from under-sampled and noisy measurements. The key advantage of DIP compared to conventional deep-learning based image reconstruction techniques is that it requires no training data and thus can be used in a flexible manner without incorporating domain specific knowledge. The downside of DIP is that it shifts the training step to reconstruction time where usually fast algorithms are required to reduced the latency between acquisition and display of the reconstructed image. In this work we tackle this problem for dynamic tomography scenarios in which a large number of temporally resolved images are taken over time. By initializing the DIP network using a previous frame of the time series, it is possible to significantly reduce the overall reconstruction time. To cope with abrupt changes in the captured time-series, we propose to use an adaptive restart method having the ability to switch between warm- and coldstart depending on the amount of inter-frame changes.

关键词： deep image prior image reconstruction dynamic tomography warmstart magnetic particle imaging

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：