检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,467 篇 会议
111 篇 期刊文献
2 册 图书
2 篇 专利

馆藏范围

1,581 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

997 篇 工学
- 409 篇 计算机科学与技术...
- 213 篇 软件工程
- 199 篇 电气工程
- 165 篇 机械工程
- 144 篇 生物医学工程（可授...
- 121 篇 信息与通信工程
- 106 篇 仪器科学与技术
- 98 篇 光学工程
- 73 篇 核科学与技术
- 67 篇 控制科学与工程
- 57 篇 生物工程
- 56 篇 测绘科学与技术
- 53 篇 电子科学与技术（可...
- 20 篇 材料科学与工程（可...
- 19 篇 航空宇航科学与技...
- 13 篇 土木工程
- 13 篇 化学工程与技术
532 篇 理学
- 400 篇 物理学
- 117 篇 数学
- 52 篇 生物学
- 34 篇 统计学（可授理学、...
- 28 篇 系统科学
- 21 篇 化学
- 16 篇 地球物理学
- 12 篇 天文学
347 篇 医学
- 239 篇 临床医学
- 150 篇 特种医学
- 27 篇 基础医学(可授医学...
53 篇 管理学
- 43 篇 管理科学与工程(可...
22 篇 农学
- 19 篇 作物学
6 篇 教育学
4 篇 法学
4 篇 艺术学
3 篇 经济学
1 篇 文学
1 篇 军事学

主题

646 篇 image reconstruc...
86 篇 three-dimensiona...
79 篇 cameras
63 篇 computed tomogra...
57 篇 tomography
56 篇 positron emissio...
54 篇 reconstruction a...
54 篇 image processing
53 篇 magnetic resonan...
53 篇 image resolution
51 篇 compressed sensi...
51 篇 training
50 篇 surface reconstr...
48 篇 image segmentati...
46 篇 image quality
42 篇 shape
41 篇 image coding
40 篇 detectors
40 篇 solid modeling
36 篇 images

机构

8 篇 washington univ ...
8 篇 univ canterbury ...
8 篇 univ british col...
7 篇 department of ra...
6 篇 dartmouth coll t...
6 篇 los alamos natl ...
6 篇 univ canterbury ...
4 篇 centre for space...
4 篇 univ nevada dept...
4 篇 prism computat s...
4 篇 infn sezione di ...
4 篇 pontificia unive...
4 篇 the barcelona in...
4 篇 department of as...
4 篇 simon fraser uni...
4 篇 univ chicago dep...
4 篇 univ n carolina ...
4 篇 faculty of engin...
4 篇 lawrence livermo...
4 篇 mpi informat saa...

作者

14 篇 wang lihong v.
14 篇 anastasio mark a...
9 篇 g.t. gullberg
8 篇 v. panin
8 篇 millane rp
7 篇 m. conti
7 篇 v.y. panin
7 篇 v. y. panin
7 篇 rueckert daniel
6 篇 jitapunkul s.
6 篇 sossi vesna
6 篇 pistorius stephe...
6 篇 s. jitapunkul
6 篇 g.l. zeng
6 篇 v. sossi
5 篇 berti a.
5 篇 barrio j.a.
5 篇 v. patanavijit
5 篇 asano k.
5 篇 huang chao

语言

1,541 篇 英文
31 篇 其他
10 篇 中文

检索条件"任意字段=Conference on Image Reconstruction from Incomplete Data V"

共 1582 条记录，以下是221-230 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Med-DANet v2: A Flexible Dynamic Architecture for Efficient Medical volumetric Segmentation

Med-DANet V2: A Flexible Dynamic Architecture for Efficient ...

引用

IEEE Workshop on Applications of Computer vision (WACv)

作者： Haoran Shen Yifu Zhang Wenxuan Wang Chen Chen Jing Liu Shanshan Song Jiangyun Li School of Automation and Electrical Engineering University of Science and Technology Beijing Center for Research in Computer Vision University of Central Florida National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Code will be available at https://***/Rubics-Xuan/Med-DANet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NvINS: Robust visual Inertial Navigation Fused with NeRF-augmented Camera Pose Regressor and Uncertainty Quantification

NVINS: Robust Visual Inertial Navigation Fused with NeRF-aug...

引用

IEEE/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Juyeop Han Lukas Lao Beyer Guilherme v. Cavalheiro Sertac Karaman Laboratory for Information and Decision Systems (LIDS) Massachusetts Institute of Technology Cambridge MA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In recent years, Neural Radiance Fields (NeRF) have emerged as a powerful tool for 3D reconstruction and novel view synthesis. However, the computational cost of NeRF rendering and degradation in quality due to the presence of artifacts pose significant challenges for its application in real-time and robust robotic tasks, especially on embedded systems. This paper introduces a novel framework that integrates NeRF-derived localization information with visual-Inertial Odometry (vIO) to provide a robust solution for real-time robotic navigation. By training an absolute pose regression network with augmented image data rendered from a NeRF and quantifying its uncertainty, our approach effectively counters positional drift and enhances system reliability. We also establish a mathematically sound foundation for combining visual inertial navigation with camera localization neural networks, considering uncertainty under a Bayesian framework. Experimental validation in a photorealistic simulation environment demonstrates significant improvements in accuracy compared to a conventional vIO approach.

关键词： Location awareness Training visualization Uncertainty Robot vision systems Inertial navigation Neural radiance field Cameras Real-time systems Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Simplifying Horizon Picking Using Single-Class Semantic Segmentation Networks 34

Simplifying Horizon Picking Using Single-Class Semantic Segm...

引用

34th SIBGRAPI conference on Graphics, Patterns and images (SIBGRAPI)

作者： Calhes, Danilo Kobayashi, Felipe K. Mattos, Andrea Britto Macedo, Maysa M. G. Oliveira, Dario A. B. IBM Corp Rua Tutoia 1157 Sao Paulo Brazil Fed Univ ABC Ave Estados 5001 Santo Andre SP Brazil IBM Res Rua Tutoia 1157 Sao Paulo Brazil

ISBN: (纸本)9781665423540

Seismic image processing plays a significant role in geological exploration as it conditions much of the interpretation performance. The interpretation process comprises several tasks, and Horizon Picking is one of the most time-consuming. Thereat, several works proposed methods for picking horizons automatically, mostly focusing on increasing the accuracy of data-driven approaches, by employing, for instance, semantic segmentation networks. However, these works often rely on a training process that requires several annotated samples, which are known to be scarce in the seismic domain, due to the overwhelming effort associated with manually picking several horizons in a seismic cube. This paper aims to evaluate the simplification of the labeling process required for training, by using training samples composed of disconnected horizons tokens, therefore relaxing the requirement of annotating the full set of horizons from each training sample, as commonly observed in previous works employing semantic segmentation networks. We assessed two state-of-art neural networks for general-purpose domains (PSP-Net and Deeplab v3+) using public seismic data (Netherlands F3 Block dataset). Our results report a minor impact in the performance using our proposed incomplete token training scheme compared to the complete one, moreover, we report that these networks outperform the current state-of-art for horizon picking from small training sets. Thus, our approach proves to be advantageous for the interpreter, given that using partial results instead of providing a full annotation can reduce the user effort during the labeling process required for training the models.

关键词： Training Graphics image segmentation Annotations Geology Semantics Neural networks

来源：评论

学校读者我要写书评

暂无评论

Transfer-Learning and YOLO v7 Hybridised for Human Cropping for Deepfake Detection Algorithms

Transfer-Learning and YOLO V7 Hybridised for Human Cropping ...

引用

IEEE International conference on Smart Instrumentation, Measurement and Applications (ICSIMA)

作者： Nawaf Waqas Sairul Izwan Safie Kushsairy A. Kadir Sheroz Khan Abdul Ali Khan Universiti Kuala Lumpur British Malaysian Institute Kuala Lumpur Malaysia Universiti Kuala Lumpur Malaysian Institute of Industrial Technology Johor Malaysia College of Engineering and Information Technology Onaizah Colleges Saudi Arabia

The advent of deep learning technology has created images and videos convincingly fake to appeal viewers enough in appearing close to real. Such image and video modalities, known as Deepfakes, can cause harm to individuals, communities, and countries. Detecting Deepfakes is essential to prevent their negative impacts, and several detection techniques that utilize deep learning algorithms have been developed over the recent past years. The algorithms reduce the target modality to dimensional latent space to include features important for subsequent reconstruction of the same modality from the developed latent distribution data. However, manual data preprocessing such as splitting frames and cropping regions from Deepfake videos for the facial features can be tedious and time-consuming. This article proposes YOLO v7 hybridised with transfer-learning to automate the cropping process in Deepfake videos and frames splitting, making it easier to extract facial features from videos. various popular datasets have been used for Deepfake detection, and this article explores the benefits of the proposed approach. The results present a comparison of the proposed approach with state-of-the-art models from the levels of Precision, Recall, and mAP@.5 to demonstrate the robustness of the proposed technique. Notably, it is evident that our approach outperforms other models, boasting a precision value of 0.9009, a recall value of 0.8979, and an mAP@.5 value of 0.8745.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Average Consistency: A Superior Way of Using the Composite image to Boost Dynamic CT reconstruction

Average Consistency: A Superior Way of Using the Composite I...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Tao, Xi Wang, Yongbo Hong, Zixuan Fu, Shuai Zhang, Hua Ma, Jianhua Southern Med Univ Sch Biomed Engn Guangzhou 510515 Guangdong Peoples R China

ISBN: (纸本)9781510633926

Dynamic imaging (such as computed tomography (CT) perfusion, dynamic CT angiography, dynamic positron emission tomography, four-dimensional CT, etc.) is widely used in the clinic. The multiple-scan mechanism of dynamic imaging results in greatly increased radiation dose and prolonged acquisition time. To deal with these problems, low-mAs or sparse-view protocols are usually adopted, which lead to noisy or incomplete data for each frame. To obtain high-quality images from the corrupted data, a popular strategy is to incorporate the composite image that reconstructed using the full dataset into the iterative reconstruction procedure. Previous studies have tried to enforce each frame to approach the composite image in each iteration, which, however, introduces mixed temporal information into each frame. In this paper, we propose an average consistency (AC) model for dynamic CT image reconstruction. The core idea of AC is to enforce the average of all frames to approach the composite image in each iteration, which preserves image edges and noise characteristics while avoids the invasion of mixed temporal information. Experiment on a dynamic phantom and a patient for CT perfusion imaging shows that the proposed method obtains the best qualitative and quantitative results. We conclude that the AC model is a general framework and a superior way of using the composite image for dynamic CT reconstruction.

关键词： Computed tomography Dynamic imaging image reconstruction Average consistency Composite image

来源：评论

学校读者我要写书评

暂无评论

Ctapipe - Prototype Open Event reconstruction Pipeline for the Cherenkov Telescope Array 38

Ctapipe - Prototype Open Event Reconstruction Pipeline for t...

引用

38th International Cosmic Ray conference, ICRC 2023

作者： Linhoff, Maximilian Beiske, Lukas Biederbeck, Noah Fröse, Stefan Kosack, Karl Nickel, Lukas Abe, K. Abe, S. Acharyya, A. Adam, R. Aguasca-Cabot, A. Agudo, I. Alfaro, J. Alvarez-Crespo, N. Alves Batista, R. Amans, J.-P. Amato, E. Ambrosino, F. Angüner, E.O. Antonelli, L.A. Aramo, C. Arcaro, C. Arrabito, L. Asano, K. Aschersleben, J. Ashkar, H. Augusto Stuani, L. Baack, D. Backes, M. Balazs, C. Balbo, M. Baquero Larriva, A. Barbosa Martins, v. de Almeida, U. Barres Barrio, J.A. Bastieri, D. Batista, P.I. Batkovic, I. Batzofin, R. Baxter, J. Beck, G. Becker Tjus, J. Beiske, L. Belardinelli, D. Benbow, W. Bernardini, E. Bernete Medrano, J. Bernlöhr, K. Berti, A. Beshley, v. Bhattacharjee, P. Bhattacharyya, S. Bi, B. Biederbeck, N. Biland, A. Bissaldi, E. Blanch, O. Blazek, J. Boisson, C. Bolmont, J. Bonnoli, G. Bordas, P. Bosnjak, Z. Bradascio, F. Braiding, C. Bronzini, E. Brose, R. Brown, A.M. Brun, F. Brunelli, G. Bulgarelli, A. Burelli, I. Burmistrov, L. Burton, M. Bylund, T. Calisse, P.G. Campoy-Ordaz, A. Cantlay, B.K. Capalbi, M. Caproni, A. Capuzzo-Dolcetta, R. Carlile, C. Caroff, S. Carosi, A. Carosi, R. Carrasco, M.-S. Cascone, E. Cassol, F. Castrejon, N. Catalani, F. Cerasole, D. Cerruti, M. Chaty, S. Chen, A.W. Chernyakova, M. Chiavassa, A. Chudoba, J. Coimbra Araujo, C.H. Conforti, v. Conte, F. Contreras, J.L. Cossou, C. Costa, A. Costantini, H. Cristofari, P. Cuevas, O. Curtis-Ginsberg, Z. D'Amico, G. D'Ammando, F. Dadina, M. Dalchenko, M. David, L. Davids, I.D. Dazzi, F. De Angelis, A. de Bony de Lavergne, M. De Caprio, v. De Cesare, G. de Gouveia Dal Pino, E.M. De Lotto, B. De Lucia, M. de Menezes, R. de Naurois, M. de Ona Wilhelmi, E. De Simone, N. de Souza, v. del Peral, L. del valle, M.v. Delagnes, E. Delgado Giler, A.G. Delgado, C. Dell'aiera, M. Della Ceca, R. Della valle, M. della volpe, D. Depaoli, D. Dettlaff, A. Di Girolamo, T. Di Piano, A. Di Pierro, F. Di Tria, R. Di venere, L. Díaz-Bahamondes, C. Dib, C. Diebold, S. Dima, R. Dinesh, A. Djannati-Ataï, A. Djuvsland, J. Department of Physics Tokai University 4-1-1 Kita-Kaname Kanagawa Hiratsuka259-1292 Japan Institute for Cosmic Ray Research University of Tokyo 5-1-5 Kashiwa-no-ha Kashiwa Chiba277-8582 Japan University of Alabama Tuscaloosa Department of Physics and Astronomy Gallalee Hall Box 870324 TuscaloosaAL35487-0324 United States Université Côte d'Azur Observatoire de la Côte d'Azur CNRS Laboratoire Lagrange France Laboratoire Leprince-Ringuet CNRS IN2P3 École polytechnique Institut Polytechnique de Paris Palaiseau91120 France Departament de Física Quàntica i Astrofísica Institut de Ciències del Cosmos Universitat de Barcelona IEEC-UB Martí i Franquès 1 Barcelona08028 Spain Instituto de Astrofísica de Andalucía CSIC Glorieta de la Astronomía s/n Granada18008 Spain Pontificia Universidad Católica de Chile Av. Libertador Bernardo O'Higgins 340 Santiago Chile IPARCOS-UCM Instituto de Física de Partículas y del Cosmos EMFTEL Department Universidad Complutense de Madrid MadridE-28040 Spain Instituto de Física Teórica UAM CSIC Departamento de Física Teórica Universidad Autónoma de Madrid c/ Nicolás Cabrera 13-15 Campus de Cantoblanco UAM Madrid28049 Spain LUTH GEPI LERMA Observatoire de Paris Université PSL Université Paris Cité CNRS 5 place Jules Janssen Meudon92190 France INAF Osservatorio Astrofisico di Arcetri Largo E. Fermi 5 Firenze50125 Italy INAF Osservatorio Astronomico di Roma Via di Frascati 33 Monteporzio Catone 00040 Italy TÜBITAK Research Institute for Fundamental Sciences Gebze Kocaeli41470 Turkey INFN Sezione di Napoli Via Cintia ed. G Napoli80126 Italy INFN Sezione di Padova Via Marzolo 8 Padova35131 Italy Laboratoire Univers et Particules de Montpellier Université de Montpellier CNRS IN2P3 CC 72 Place Eugène Bataillon 5 MontpellierF-34095 Cedex France Kapteyn Astronomical Institute University of Groningen Landleven 12 Groningen9747 AD Netherlands Instituto de Física de São Carlos Universidade de

The Cherenkov Telescope Array Observatory (CTAO) is the next-generation ground-based gamma-ray observatory currently under construction. It will improve over the current generation of imaging atmospheric Cherenkov telescopes (IACTs) by a factor of five to ten in sensitivity and it will be able to observe the whole sky from a combination of two sites: a northern site in La Palma, Spain, and a southern one in Paranal, Chile. CTAO will also be the first open ground-based gamma-ray observatory. Accordingly, the CTAO data processing pipeline is developed as open-source software and ctapipe will be a core package therein. The event reconstruction pipeline accepts raw data of the telescopes and processes it to produce suitable input for the higher-level science tools. Its primary tasks include reconstructing the physical properties of each recorded air shower and providing the corresponding instrument response functions. ctapipe is a python framework providing algorithms and command-line tools to facilitate raw data calibration, image extraction, image parametrization and event reconstruction. Its current main focus is the analysis of simulated data but it has also been successfully applied for the analysis of data obtained with the CTA prototype telescopes, and first science results have now been obtained by the LST-1 collaboration using ctapipe. A plugin system also allows the processing of nonCTA data. Recent updates, including event reconstruction using machine learning and a new plugin system as well as the roadmap towards a 1.0 release will be presented. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Deep image reconstruction for Reducing Limited-Angle Artifacts in a Dual-Panel TOF PET

Deep Image Reconstruction for Reducing Limited-Angle Artifac...

引用

2020 IEEE Nuclear Science Symposium and Medical Imaging conference, NSS/MIC 2020

作者： Li, Yusheng Matej, Samuel The Department of Radiology University of Pennsylvania 3620 Hamilton Walk PhiladelphiaPA19104 United States

ISBN: (纸本)9781728176932

Dual-panel PET scanners have many advantages in dedicated breast imaging and on-board imaging applications since the compact scanners can be combined with other imaging and treatment modalities. The major challenges of dual-panel PET imaging are the incomplete sampling and data truncation, which can cause severe limited-angle artifacts. In this incomplete sampling case, time-of-flight (TOF) provides new information and thus reduces the artifacts, however, the problem is still quite challenging even with 200 to 300 ps timing resolution. In this work, we explore deep learning based image reconstruction for limited-angle artifacts reduction for dual-panel TOF PET imaging. The deep image reconstruction consists of two components, namely, TOF ordered subsets expectation maximization (OSEM) reconstruction, and a deep neural network for limited-angle artifacts reduction. We adopt and optimize a U-net based architecture for limited-angle artifacts reduction (LaU-net) to predict expected images from limited-angle TOF reconstructions. We perform numerical simulations with a generic 2D dual-panel TOF PET system with timing resolution of 300 ps and angular coverage of 90°. We generate 640 2D training datasets by performing TOF ordered subsets expectation maximization (OSEM) reconstructions from randomly generated phantom images. Then 3 additional folds of datasets were obtained using data augmentation by flipping horizontal and vertical dimensions for each dataset. We used Kullback-Leibler divergence as loss function for nonnegative images, and the Adam optimizer for training. We show from both random phantoms and a high resolution hot-rod phantom that the deep reconstruction can substantially reduce limited-angle artifacts and improve quantitative accuracy of reconstructed images. © 2020 IEEE

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Rapider-YOLOv7: Lightweight Infrared Object Detection Network

Rapider-YOLOv7: Lightweight Infrared Object Detection Networ...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International conference on

作者： Pucheng Xu Yuecheng Yu Rundong Zou Jinlong Shi Yongzheng Li School of Computer Science Jiangsu University of Science and Technology Zhenjiang China School of Naval Architecture and Ocean Engineering Jiangsu University of Science and Technology Zhenjiang China

ISBN: (数字)9798350350890

ISBN: (纸本)9798350350906

YOLOv7-tiny, as a lightweight variant of YOLOv7, boasts advantages of fast runtime and fewer parameters. However, when directly applied to infrared object detection, YOLOv7-tiny still faces challenges such as weak extraction of fine details, loss of semantic information, and high resource consumption. To address these issues, we propose a comprehensive balance between detection speed and accuracy in the Rapider-YOLOv7 object detection network. Firstly, it introduces the Exponential Spatial Pyramid Pooling with Channel Spatial Pyramid (Soft-SPPCSP) module to enhance the capability of the original model in extracting low contrast information from infrared images. Secondly, it designs the FO-CA attention module to strengthen the model's feature extraction capability for infrared images with weak textures. Furthermore, it devises the lightweight SFaster-net network, which incorporates SPDconv convolution for feature extraction to accelerate the model's feature extraction speed and enhance its capability to extract features from low-resolution images. Experimental results on the FLIR-v2 infrared dataset demonstrate that the mAP of the Rapider-YOLOv7 model reaches 62.6%, which is 2.9% higher than that of the original YOLOv7-tiny. Moreover, the FPS value on the RTX4060ti reaches 93.

关键词： Runtime Semantics Redundancy Object detection Feature extraction Real-time systems Neck data mining Spatial resolution image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound reconstruction 24th

Self Context and Shape Prior for Sensorless Freehand 3D Ultr...

引用

International conference on Medical image Computing and Computer Assisted Intervention (MICCAI)

作者： Luo, Mingyuan Yang, Xin Huang, Xiaoqiong Huang, Yuhao Zou, Yuxin Hu, Xindi Ravikumar, Nishant Frangi, Alejandro F. Ni, Dong Shenzhen Univ Hlth Sci Ctr Sch Biomed Engn Natl Reg Key Technol Engn Lab Med Ultrasound Shenzhen Peoples R China Shenzhen Univ Med Ultrasound Image Comp MUSIC Lab Shenzhen Peoples R China Shenzhen Univ Marshall Lab Biomed Engn Shenzhen Peoples R China Nanjing Med Univ Sch Biomed Engn & Informat Nanjing Peoples R China Univ Leeds Ctr Computat Imaging & Simulat Technol Biomed CIS Leeds W Yorkshire England Univ Leeds Leeds Inst Cardiovasc & Metab Med Leeds W Yorkshire England Katholieke Univ Leuven Med Imaging Res Ctr MIRC Leuven Belgium

ISBN: (纸本)9783030872311;9783030872304

3D ultrasound (US) is widely used for its rich diagnostic information. However, it is criticized for its limited field of view. 3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan. The existing deep learning based methods only focus on the basic cases of skill sequences, and the model relies on the training data heavily. The sequences in real clinical practice are a mix of diverse skills and have complex scanning paths. Besides, deep models should adapt themselves to the testing cases with prior knowledge for better robustness, rather than only fit to the training cases. In this paper, we propose a novel approach to sensorless freehand 3D US reconstruction considering the complex skill sequences. Our contribution is three-fold. First, we advance a novel online learning framework by designing a differentiable reconstruction algorithm. It realizes an end-to-end optimization from section sequences to the reconstructed volume. Second, a self-supervised learning method is developed to explore the context information that reconstructed by the testing data itself, promoting the perception of the model. Third, inspired by the effectiveness of shape prior, we also introduce adversarial training to strengthen the learning of anatomical shape prior in the reconstructed volume. By mining the context and structural cues of the testing data, our online learning methods can drive the model to handle complex skill sequences. Experimental results on developmental dysplasia of the hip US and fetal US datasets show that, our proposed method can outperform the start-of-the-art methods regarding the shift errors and path similarities.

关键词： Self context Shape prior Freehand 3D ultrasound

来源：评论

学校读者我要写书评

暂无评论

Sparse Range-Doppler image Construction with Neural Networks

Sparse Range-Doppler Image Construction with Neural Networks

引用

IEEE International Radar conference (RADAR)

作者： Akhtar, Jabran Norwegian Def Res Estab FFI Kjeller Norway

ISBN: (数字)9781728168135

ISBN: (纸本)9781728168135

The principles outlined by compressed sensing can permit a sensor to collect reduced amount of data and still reconstruct an exact outcome. This can for example be used to generate super-resolution sparse range-Doppler radar images while emitting a reduced number of pulses within a coherent processing interval. In this paper, we investigate the use of neural networks as a mean to solve the sparse reconstruction problem with specific emphasis towards range-Doppler images. The neural networks are trained to generate a sparse Doppler profile from incomplete time domain data in line with traditional sparse L-1-norm minimization. We show that this approach is viable through fully connected feed forwarding networks and the results closely mimic sparse recovered range-Doppler maps.

关键词： Range-Doppler discrete Fourier transform compressed sensing sparse reconstruction neural networks

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共159页 << < 19 20 21 22 23 24 25 26 27 28 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：