检索结果-内蒙古大学图书馆

Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks

Medical Image Analysis 2022年 78卷 102396-102396页

作者： Subramaniam, Pooja Kossen, Tabea Ritter, Kerstin Hennemuth, Anja Hildebrand, Kristian Hilbert, Adam Sobesky, Jan Livne, Michelle Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar Madai, Vince I. CLAIM - Charité Lab for AI in Medicine Charité Universitätsmedizin Berlin Germany Department of Computer Engineering and Microelectronics Computer Vision & Remote Sensing Technical University Berlin Berlin Germany Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine Charité Universitätsmedizin Berlin Berlin Germany Fraunhofer MEVIS Max-von-Laue-Str. 2 Bremen Germany Department VI Computer Science and Media Beuth University of Applied Sciences Berlin Germany Johanna-Etienne-Hospital Neuss Germany Centre for Stroke Research Berlin Charité Universitätsmedizin Berlin Berlin Germany Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Mind Brain Body Institute Berlin School of Mind and Brain Humboldt University Berlin Berlin Germany Berlin Institute of Health Berlin Germany School of Computing and Digital Technology Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom QUEST-Center for Transforming Biomedical Research Berlin Institute of Health Charité Universitätsmedizin Berlin Charitéplatz 1 Berlin10117 Germany

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Mammogram Classification using Small Dataset

Deep Learning-based Mammogram Classification using Small Dat...

引用

International Conference on Electronics, computer and Computation (ICECCO)

作者： Adeyinka P. ADEDIGBA Steve A. ADESHINAT Abiodun M. AIBINU Department of Mechatronics Engineering Federal University of Technology Minna Nigeria Computer Vision Lab Nile University of Nigeria Abuja

ISBN: (数字)9781728151601

ISBN: (纸本)9781728151618

Breast Cancer is one of the most diagnosed cancer and the leading cause of death among women worldwide, second only to lung cancer. Mammographic screening has been the most successful screening technology capable of detecting up to 90% of all breast cancer even before a lump growth can be felt using breast exam. However, mammogram is a low intensity image and the heterogeneous nature of breast can make healthy breast tissue appears as cancerous, this is most common among women with dense breast (aged 40-44). Thus, the sensitivity for early detection of breast cancer from mammogram has been estimated to 85-90%. This result can be improved by Deep CNN, however, to achieve good generalization, it must be train with high voluminous dataset whereas, mammographic dataset exists in smaller volume. In this paper, we present a method of training deep CNN with few datasets to achieve high training result and good generalization. An augmentation technique that increase both size and variance of the dataset is presented herewith, the augmented dataset was used to train five state of the art models. Highest training and validation accuracy (99.01% and 99.99% respectively) were achieved with DensNet. Meanwhile, SqueezeNet, a deep CNN model with fewer parameter also shows promising result, which means soon this model can be deployed into microcontroller and FPGAs for clinical applications.

关键词： biological organs biological tissues cancer convolutional neural nets gynaecology image classification learning (artificial intelligence) mammography medical image processing patient diagnosis Digital Mammography biological organs patient diagnosis Medical image processing Gynecology Cancer Screening TISSUES (BIOLOGY) Image classification Dataset Breast Cancer state of the art Breast tissue Cause of Death breast examinations grayscale images

来源：评论

学校读者我要写书评

暂无评论

A transfer learning approach to heatmap regression for action unit intensity estimation

arXiv

引用

arXiv 2020年

作者： Ntinou, Ioanna Sanchez, Enrique Bulat, Adrian Valstar, Michel Tzimiropoulos, Georgios Computer Vision Lab. School of Computer Science University of Nottingham NG8 1BB United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London E1 4NS United Kingdom Samsung AI Center CambridgeCB1 2RE United Kingdom

Action Units (AUs) are geometrically-based atomic facial muscle movements known to produce appearance changes at specific facial locations. Motivated by this observation we propose a novel AU modelling problem that consists of jointly estimating their localisation and intensity. To this end, we propose a simple yet efficient approach based on Heatmap Regression that merges both problems into a single task. A Heatmap models whether an AU occurs or not at a given spatial location. To accommodate the joint modelling of AUs intensity, we propose variable size heatmaps, with their amplitude and size varying according to the labelled intensity. Using Heatmap Regression, we can inherit from the progress recently witnessed in facial landmark localisation. Building upon the similarities between both problems, we devise a transfer learning approach where we exploit the knowledge of a network trained on large-scale facial landmark datasets. In particular, we explore different alternatives for transfer learning through a) fine-tuning, b) adaptation layers, c) attention maps, and d) reparametrisation. Our approach effectively inherits the rich facial features produced by a strong face alignment network, with minimal extra computational cost. We empirically validate that our system sets a new state-of-the-art on three popular datasets, namely BP4D, DISFA, and FERA2017. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

TSNet: Deep Network for Human Action Recognition in Hazy Videos

TSNet: Deep Network for Human Action Recognition in Hazy Vid...

引用

2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

作者： Chaudhary, Sachin Murala, Subrahmanyam Computer Vision and Pattern Recognition Lab Depatment of Electrical Engineering Indian Institute of Technology Ropar India

ISBN: (纸本)9781538666500

The all-weather intelligent surveillance system is the prime challenge for computer vision researchers. The surveillance is mostly done to analyze the human activity in a particular region. Several extreme weather conditions like rain, snow, haze, fog etc. halts the surveillance process and thus decreases the reliability of the surveillance system. Here, an attempt is made to tackle one of these weather situation i.e. haze in case of surveillance. Haze distorts the quality of images and videos captured by camera. Due to poor quality, it is difficult to analyze the haze degraded video for the human activities using the existing state-of-the-art methods for human action Recognition (HAR). Therefore, in this paper, a new two level saliency based end-to-end network (TSNet) for HAR in hazy videos is proposed. De-hazing approaches given in [1]-[9] have certain limitations and therefore we fine-tuned the de-hazing network given in [10] for HAR. The concept of rank pooling given in [11] is further utilized to efficiently represent the temporal saliency of the video. The transmission map information is utilized here to fix the spatial saliency in each frame. As currently, there is no dataset available for HAR in hazy video, here a new dataset of hazy video is generated from two benchmark datasets namely HMDB51 [12] and UCF101 [13] by adding synthetic haze. The existing methods for HAR proposed in [11], [14], [15] are applied and compared with the proposed method on proposed hazy-HMDB51 and hazy-UCF101. The proposed method clearly outperforms the above mentioned methods in terms of average Recognition rate (ARR). © 2018 IEEE.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Single noisy image super resolution by minimizing nuclear norm in virtual sparse domain 6th

Single noisy image super resolution by minimizing nuclear no...

引用

6th National Conference on computer vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2017

作者： Mandal, Srimanta Rajagopalan, A.N. Image Processing and Computer Vision Lab Department of Electrical Engineering IIT Madras Chennai600036 India

ISBN: (纸本)9789811300196

Super-resolving a noisy image is a challenging problem, and needs special care as compared to the conventional super resolution approaches, when the power of noise is unknown. In this scenario, we propose an approach to super-resolve single noisy image by minimizing nuclear norm in a virtual sparse domain that tunes with the power of noise via parameter learning. The approach minimizes nuclear norm to explore the inherent low-rank structure of visual data, and is further augmented with coarse-to-fine information by adaptively re-aligning the data along the principal components of a dictionary in virtual sparse domain. The experimental results demonstrate the robustness of our approach across different powers of noise. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Group shift pointwise convolution for volumetric medical image segmentation

arXiv

引用

arXiv 2021年

作者： He, Junjun Ye, Jin Li, Cheng Song, Diping Chen, Wanli Wang, Shanshan Gu, Lixu Qiao, Yu School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Shanghai AI Lab Shanghai China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Chinese University of Hong Kong Hong Kong Peng Cheng Laboratory Guangdong Shenzhen China Pazhou Lab Guangdong Guangzhou China

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models employing 3D convolutions introduce more trainable parameters and are more computationally complex, which may lead easily to model overfitting especially for medical applications with limited available training data. This paper aims to improve the effectiveness and efficiency of 3D convolutions by introducing a novel Group Shift Pointwise Convolution (GSP-Conv). GSP-Conv simplifies 3D convolutions into pointwise ones with 1 × 1 × 1 kernels, which dramatically reduces the number of model parameters and FLOPs (e.g. 27× fewer than 3D convolutions with 3 × 3 × 3 kernels). Naïve pointwise convolutions with limited receptive fields cannot make full use of the spatial image context. To address this problem, we propose a parameter-free operation, Group Shift (GS), which shifts the feature maps along different spatial directions in an elegant way. With GS, pointwise convolutions can access features from different spatial locations, and the limited receptive fields of pointwise convolutions can be compensated. We evaluate the proposed methods on two datasets, PROMISE12 and BraTS18. Results show that our method, with substantially decreased model complexity, achieves comparable or even better performance than models employing 3D convolutions. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Abnormal Data Cleaning for Wind Turbines by Image Segmentation Based on Active Shape Model and Class Uncertainty

SSRN

引用

SSRN 2022年

作者： Liang, Guoyuan Su, Yahao Wu, Xinyu Ma, Jiajun Long, Huan Song, Zhe Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China School of Electrical Engineering Southeast University Jiang Su Province Nanjing China School of Business Nanjing University Jiang Su Province Nanjing China

Wind power curve describes the relationship between wind speed and output power of wind turbine, which may be contaminated due to various unexpected factors. Following the idea of image segmentation in our previous work, in this paper, we propose a novel image-based abnormal data cleaning algorithm aiming to provide high quality data for wind power curve modeling and relevant applications. For image binarization, a multiscale space is built to determine the optimal scale at which the most stable as well as informative shape representations are extracted. The Active Shape Model is utilized to model the power curve shape and generate a set of segmentation candidates for filtering abnormal data. To measure the cost of each candidate, the Class Uncertainty map based on dual feature images is built. And eventually the optimal segmentation boundary is determined by the optimization in the energy space. A series of comparative experiments conducted over the real-world datasets of 37 wind turbines have validated the superior performance of the proposed algorithm. © 2022, The Authors. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

arXiv

引用

arXiv 2019年

作者： Vipparthi, Santosh Kumar Mishra, Abhishek Dhar, Vansh Mandal, Murari Vision Intelligence Lab Department of Computer Science and Engineering Jaipur India School of Computing and Information Technology Manipal University Jaipur

In this paper we propose an end-to-end swift 3D feature reductionist framework (3DFR) for scene independent change detection. The 3DFR framework consists of three feature streams: a swift 3D feature reductionist stream (AvFeat), a contemporary feature stream (ConFeat) and a temporal median feature map. These multilateral foreground/background features are further refined through an encoder-decoder network. As a result, the proposed framework not only detects temporal changes but also learns high-level appearance features. Thus, it incorporates the object semantics for effective change detection. Furthermore, the proposed framework is validated through a scene independent evaluation scheme in order to demonstrate the robustness and generalization capability of the network. The performance of the proposed method is evaluated on the benchmark CDnet 2014 dataset. The experimental results show that the proposed 3DFR network outperforms the state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Object Detection based on Region Decomposition and Assembly

arXiv

引用

arXiv 2019年

作者： Bae, Seung-Hwan Computer Vision Lab. Department of Computer Science and Engineering Incheon National University 119 Academy-ro Yeonsu-gu Incheon22012 Korea Republic of

Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been flourishing and provided the promising detection results. However, the detection accuracy is degraded often because of the low discriminability of object CNN features caused by occlusions and inaccurate region proposals. In this paper, we therefore propose a region decomposition and assembly detector (R-DAD) for more accurate object detection. In the proposed R-DAD, we first decompose an object region into multiple small regions. To capture an entire appearance and part details of the object jointly, we extract CNN features within the whole object region and decomposed regions. We then learn the semantic relations between the object and its parts by combining the multi-region features stage by stage with region assembly blocks, and use the combined and high-level semantic features for the object classification and localization. In addition, for more accurate region proposals, we propose a multi-scale proposal layer that can generate object proposals of various scales. We integrate the R-DAD into several feature extractors, and prove the distinct performance improvement on PASCAL07/12 and MSCOCO18 compared to the recent convolutional detectors. Copyright © 2019, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Effective fusion of deep multitasking representations for robust visual tracking

arXiv

引用

arXiv 2020年

作者： Marvasti-Zadeh, Seyed Mojtaba Ghanei-Yakhdan, Hossein Kasaei, Shohreh Nasrollahi, Kamal Moeslund, Thomas B. Department of Electrical Engineering Yazd University Yazd Iran Sharif University of Technology Tehran Iran Vision and Learning Lab. University of Alberta Edmonton Canada Department of Electrical Engineering Yazd University Yazd Iran Department of Computer Engineering Sharif University of Technology Tehran Iran Department of Architecture Design and Media Technology Aalborg University Aalborg Denmark

Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters (DCFs) employ feature extraction networks (FENs) to model the target appearance during the learning process. However, using deep feature maps extracted from FENs based on different residual neural networks (ResNets) has not previously been investigated. This paper aims to evaluate the performance of twelve state-of-the-art ResNet-based FENs in a DCF-based framework to determine the best for visual tracking purposes. First, it ranks their best feature maps and explores the generalized adoption of the best ResNet-based FEN into another DCF-based method. Then, the proposed method extracts deep semantic information from a fully convolutional FEN and fuses it with the best ResNet-based feature maps to strengthen the target representation in the learning process of continuous convolution filters. Finally, it introduces a new and efficient semantic weighting method (using semantic segmentation feature maps on each video frame) to reduce the drift problem. Extensive experimental results on the well-known OTB-2013, OTB-2015, TC-128, and VOT-2018 visual tracking datasets demonstrate that the proposed method effectively outperforms state-of-the-art methods in terms of precision and robustness of visual tracking. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

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：