检索结果-内蒙古大学图书馆

Conference on Medical Imaging - image Processing

作者： Bai, Yunkun Sun, Guangmin Li, Yu Le Shen Li Zhang Beijing Univ Technol Fac Informat Technol 100 PingLeYuan Beijing 100124 Peoples R China Tsinghua Univ Minist Educ Key Lab Particle & Radiat Imaging Beijing Peoples R China Tsinghua Univ Dept Engn Phys Beijing 100084 Peoples R China

ISBN: (纸本)9781510640221

Deep learning based segmentation algorithms for medical image require massive training datasets with accurate annotations, which is costly since it takes much human effort to manually labeling from scratch. Therefore, interactive image segmentation is important and may greatly improve the efficiency and accuracy of medical image labeling. Some interactive segmentation methods (e.g. Deep Extreme Cut and Deepgrow) may improve the labeling through minimal interactive input. However these methods only utilize the initial manually input information, while existing segmentation results (such as annotations produced by nonprofessionals or conventional segmentation algorithms) cannot be utilized In this paper, an interactive segmentation method is proposed to make use of both existing segmentation results and human interactive information to optimize the segmentation results progressively. In this framework, the user only needs to click on the foreground or background of the target individual on the medical image, the algorithm could adaptively learn the correlation between them, and automatically completes the segmentation of the target. The main contributions of this paper are: (1) We adjusted and applied a convolutional neural network which takes medical image data and user's clicks information as input to achieve more accurate segmentation of medical images. (2) We designed an iterative training strategy to realize the applicability of the model to deal with different number of clicks data input. (3) We designed an algorithm based on false positive and false negative regions to simulate the user's clicks, so as to provide enough training data. By applying the proposed method, users can easily extract the region of interest or modify the segmentation results by multiple clicks. The experimental results of 6 medical image segmentation tasks show that the proposed method achieves more accurate segmentation results by at most five clicks.

关键词： medical image annotation interactive image segmentation convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Rock CT image Fracture segmentation Based on Convolutional Neural Networks

引用

ROCK MECHANICS AND ROCK ENGINEERING 2024年第8期57卷 5883-5898页

作者： Lei, Jian Fan, Yufei Anhui Univ Sci & Technol Sch Earth & Environm Huainan 232001 Peoples R China

image-based automatic fracture extraction methods have many practical applications in geological and engineering. Fracture identification and quantitative characterization require the means of interpreting and statistically analyzing image data. In comparison to traditional digital image processing methods, supervised semantic segmentation methods based on Convolutional Neural Networks (CNN) offer distinct advantages in extracting fractures from CT images. The study analyzes the characteristics of fracture areas in CT images and compares the results obtained through traditional threshold segmentation methods with those achieved using deep learning techniques. An integrated approach combining interactive image segmentation was proposed in this study to extract the fractures, in which deep learning methods were to determine the fracture areas, as well as morphological operation and threshold segmentation methods were adopted to extract the fractures from the small target areas. The implementation of this method significantly enhances the efficiency of extraction results compared to manual fracture extractions. This study selected CT images of igneous rock with a resolution of 0.7 um as the research object. DeepLab V3 + and UNet3 + network models in the PaddleSeg framework were used for the deep learning process. The characteristics of fracture morphology, opening degree and gray level in CT images of rock are *** effects of traditional segmentation algorithm and deep learning algorithm in fracture extraction were compared.A new method combining deep learning and threshold segmentation is proposed to extract fractures.

关键词： Fracture extraction Convolutional neural networks Threshold segmentation interactive image segmentation DeepLab V3+ UNet3+

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation based on synthetic graph coordinates

引用

PATTERN RECOGNITION 2013年第11期46卷 2940-2952页

作者： Panagiotakis, Costas Papadakis, Harris Grinias, Elias Komodakis, Nikos Fragopoulou, Paraskevi Tziritas, Georgios Technol Educ Inst Crete Dept Commerce & Mkt Ierapetra 72200 Crete Greece Technol Educ Inst Crete Dept Appl Informat & Multimedia Iraklion Greece Ecole Ponts ParisTech F-77455 Champs Sur Marne France CNRS Lab Informat Gaspard Monge F-77454 Marne La Vallee 2 France Technol Educ Inst Serres Dept Geoinformat & Surveying Serres 62124 Greece Univ Crete Dept Comp Sci Khania Greece Technol Educ Inst Serres Dept Informat & Commun Serres 62124 Greece Inst Comp Sci Fdn Res & Technol Hellas Iraklion 70013 Crete Greece

In this paper, we propose a framework for interactive image segmentation. The goal of interactive image segmentation is to classify the image pixels into foreground and background classes, when some foreground and background markers are given. The proposed method minimizes a min-max Bayesian criterion that has been successfully used on image segmentation problem and it consists of several steps in order to take into account visual information as well as the given markers, without any requirement of training. First, we partition the image into contiguous and perceptually similar regions (superpixels). Then, we construct a weighted graph that represents the superpixels and the connections between them. An efficient algorithm for graph clustering based on synthetic coordinates is used yielding an initial map of classified pixels. This method reduces the problem of graph clustering to the simpler problem of point clustering, instead of solving the problem on the graph data structure, as most of the known algorithms from literature do. Finally, having available the data modeling and the initial map of classified pixels, we use a Markov Random Field (MRF) model or a flooding algorithm to get the image segmentation by minimizing a min-max Bayesian criterion. Experimental results and comparisons with other methods from the literature are presented on LHI, Gulshan and Zhao datasets, demonstrating the high performance and accuracy of the proposed scheme. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： image segmentation interactive image segmentation Network coordinates Community detection Markov Random Field

来源：评论

学校读者我要写书评

暂无评论

SIMSAM: ZERO-SHOT MEDICAL image segmentation VIA SIMULATED INTERACTION 21

SIMSAM: ZERO-SHOT MEDICAL IMAGE SEGMENTATION VIA SIMULATED I...

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Towle, Benjamin Chen, Xin Zhou, Ke Univ Nottingham Sch Comp Sci Nottingham England Nokia Bell Labs Murray Hill NJ USA

ISBN: (纸本)9798350313345;9798350313338

The recently released Segment Anything Model (SAM) has shown powerful zero-shot segmentation capabilities through a semi-automatic annotation setup in which the user can provide a prompt in the form of clicks or bounding boxes. There is growing interest around applying this to medical imaging, where the cost of obtaining expert annotations is high, privacy restrictions may limit sharing of patient data, and model generalisation is often poor. However, there are large amounts of inherent uncertainty in medical images, due to unclear object boundaries, low-contrast media, and differences in expert labelling style. Currently, SAM is known to struggle in a zero-shot setting to adequately annotate the contours of the structure of interest in medical images, where the uncertainty is often greatest, thus requiring significant manual correction. To mitigate this, we introduce Simulated Interaction for Segment Anything Model (SIMSAM), an approach that leverages simulated user interaction to generate an arbitrary number of candidate masks, and uses a novel aggregation approach to output the most compatible mask. Crucially, our method can be used during inference directly on top of SAM, without any additional training requirement. Quantitatively, we evaluate our method across three publicly available medical imaging datasets, and find that our approach leads to up to a 15.5% improvement in contour segmentation accuracy compared to zero-shot SAM. Our code is available at https://***/BenjaminTowle/SimSAM.

关键词： medical imaging Segment Anything Model interactive image segmentation zero-shot

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation by improved maximal similarity based region merging

Interactive image segmentation by improved maximal similarit...

引用

IEEE International Conference on Medical Imaging Physics and Engineering (ICMIPE)

作者： Jian, Chen Bin, Yan Hua, Jiang Lei, Zeng Li, Tong Natl Digital Switching Syst Engn & Technol R&D Ct Zhengzhou 450002 Peoples R China

ISBN: (纸本)9781467358873

In medical image processing, interactive image segmentation is an important part, because it can obtain accurate segment results with less human effort compared with manual scribing. We proposed an improved algorithm of maximal similarity based region merging, compared with the algorithm proposed in [3], our algorithm use SLIC superpixels segmentation to obtain presegmented regions, using SLIC superpixles, it is easy to control the number of presegmentation regions. We also introduce the texture features differeces while rigion merging, so we can obtain the accuracy of similarity measurement. Experimental results show that our algorithm can obtain comparable results.

关键词： interactive image segmentation Superpixels image merging

来源：评论

学校读者我要写书评

暂无评论

interactive color image segmentation via iterative evidential labeling

引用

INFORMATION FUSION 2014年第1期20卷 292-304页

作者： Chen, Yin Cremers, Armin B. Cao, Zhiguo Huazhong Univ Sci & Technol Sch Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Peoples R China Univ Bonn Inst Comp Sci 3 D-53117 Bonn Germany

We develop an interactive color image segmentation method in this paper. This method makes use of the conception of Markov random fields (MRFs) and D-S evidence theory to obtain segmentation results by considering both likelihood information and priori information under Bayesian framework. The method first uses expectation maximization (EM) algorithm to estimate the parameter of the user input regions, and the Bayesian information criterion (BIC) is used for model selection. Then the beliefs of each pixel are assigned by a predefined scheme. The result is obtained by iteratively fusion of the pixel likelihood information and the pixel contextual information until convergence. The method is initially designed for two-label segmentation, however it can be easily generalized to multi-label segmentation. Experimental results show that the proposed method is comparable to other prevalent interactive image segmentation algorithms in most cases of two-label segmentation task, both qualitatively and quantitatively. (C) 2014 Elsevier B.V. All rights reserved.

关键词： interactive image segmentation Markov random fields (MRFs) Dempster-Shafer's (DS) theory of evidence Bayesian information criterion (BIC) Information fusion

来源：评论

学校读者我要写书评

暂无评论

Selective Intra-image Similarity for Personalized Fixation-Based Object segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第11期32卷 7910-7923页

作者： Zhou, Huajun Yang, Lingxiao Xie, Xiaohua Lai, Jianhuang Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China

Personalized Fixation-based Object segmentation (PFOS) aims at segmenting the gazed objects in images conditioned on personalized fixations. However, the performances of existing PFOS methods are degraded when facing anomalous fixation maps (some fixations fall in the background) or enormous objects because of their poor localization ability. In this paper, we propose a novel Selective Intra-image Similarity Network (SISNet) that achieves significant performance by precisely localizing the gazed objects. First, we propose a Response Purifying Module (RPM) to eliminate the false response regions caused by anomalous fixations in the background. By suppressing these false responses, we can significantly reduce the negative impacts caused by anomalous fixations. Second, we propose an intra-image similarity module (ISM) to better localize large objects by integrating more long-range information. In addition, we propose a new Discriminative Intersection-over-Union metric that evaluates whether PFOS methods can produce distinctive predictions for varying fixations. Experiments on the PFOS and our proposed OSIE-CFPS-UN datasets prove that our network achieves remarkable improvements and outperforms existing state-of-the-art methods. Code has been published at https://***/moothes/SISNet.

关键词： image segmentation Task analysis Object segmentation Observers image edge detection Object detection Measurement Fixation-based segmentation intra-image similarity interactive image segmentation evaluation metric

来源：评论

学校读者我要写书评

暂无评论

ROBOT USERS FOR THE EVALUATION OF BOUNDARY-TRACKING APPROACHES IN interactive image segmentation

ROBOT USERS FOR THE EVALUATION OF BOUNDARY-TRACKING APPROACH...

引用

IEEE International Conference on image Processing

作者： Thiago V. Spina Alexandre X. Falcao Institute of Computing University of Campinas (UNICAMP)

ISBN: (纸本)9781479957521

Recent advances in interactive image segmentation focused on eliminating the user bias during evaluation by simulating their behavior using robot users. However, these robots only work for region-based methods, excluding the important class of approaches that rely on the boundary-tracking paradigm. We propose completely novel robot users that are able to simulate the human user behavior when segmenting an image through the addition of anchor points close to the object's boundary. Our robots constantly evaluate the optimum-boundary segment being computed from a previously selected anchor point to the current virtual mouse position, seeking for the longest possible segment with minimum acceptable error. A new anchor is added when the error is too high and the robots iterate until closing the contour, just like real users. We validate our robots by conducting a user study and extensive experiments, considering two boundary-tracking methods: live-wire-on-the-fly and Riverbed. We further show how our robot users can be used to assess hybrid approaches that combine boundary-tracking with region-based delineation, such as LiveMarkers, while conjecturing that robots might lead to new methods for automatic foreground segmentation.

关键词： Robot users interactive image segmentation Boundary-tracking Live wire Riverbed image Foresting Transform

来源：评论

学校读者我要写书评

暂无评论

interactive Skin Lesion segmentation Considering Behavioral Preference in Clicking

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2025年第1期20卷 89-100页

作者： Zhao, Shuofeng Gu, Chunzhi Yu, Jun Akashi, Takuya Zhang, Chao Univ Fukui Dept Engn 3-9-1 Bunkyo Fukui Fukui 9502181 Japan Toyohashi Univ Technol Dept Comp Sci & Engn 1-1 HibarigaokaTempaku Cho Toyohashi Aichi 4418580 Japan Niigata Univ Inst Sci & Technol 8050 Ikarashi 2 No ChoNishi Ku Niigata Niigata 9502181 Japan Okayama Univ Sch Engn 2-1-1 TsushimanakaKita Ku Okayama 7008530 Japan Univ Toyama Fac Engn 3190 Gofuku Toyama 9308555 Japan

interactive Medical image segmentation (IMIS) aims to improve the accuracy of image segmentation by incorporating human guidance, primarily through click-based interactions. IMIS for skin lesion segmentation is a challenging task because the edges of lesion regions on the skin are often ambiguous, and training IMIS models requires the generation of pseudo-clicks to simulate human clicks. Most previous methods generate pseudo-clicks by sampling from the entire mis-segmented region. However, such clicks are inconsistent with human behavior, resulting in performance degradation, particularly for skin lesion segmentation. In this study, we address this issue by integrating human preference into the process of generating pseudo clicks to train the segmentation model, which is simple yet effective. Specifically, through a user study, we find that people are more inclined to click on larger mis-segmented regions during interactive segmentation. Inspired by this, a roulette selection strategy is used to generate the pseudo-clicks based on the area of the mis-segmented subregions. Our proposed method, BehaviorClick, can be easily integrated with existing interactive segmentation models to improve the performance. The accuracy improvement on four dermoscopic datasets under six state-of-the-art interactive segmentation methods is confirmed, which demonstrates the generalizability and effectiveness of our approach. (c) 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： skin lesion image segmentation user behavior interactive image segmentation

来源：评论

学校读者我要写书评

暂无评论

DeeplGeoS: A Deep interactive Geodesic Framework for Medical image segmentation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2019年第7期41卷 1559-1572页

作者： Wang, Guotai Zuluaga, Maria A. Li, Wenqi Pratt, Rosalind Patel, Premal A. Aertsen, Michael Doel, Tom David, Anna L. Deprest, Jan Ourselin, Sebastien Vercauteren, Tom UCL Translat Imaging Grp Wellcome EPSRC Ctr Intervent & Surg Sci WEISS London WC1E 6BT England UCL Inst Womens Hlth London WC1E 6BT England Katholieke Univ Leuven Univ Hosp Dept Radiol B-3000 Leuven Belgium Katholieke Univ Leuven Dept Obstet Univ Hosp B-3000 Leuven Belgium

Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

关键词： interactive image segmentation convolutional neural network geodesic distance conditional random fields

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：