检索结果-内蒙古大学图书馆

2025 Conference on Medical Imaging

作者： Barbosa, Luis C. N. Fan, Yiting Zhao Chenxu Lee, Alex P. Moane, Siobhan Vilaca, Joao L. Morais, Pedro IPCA Sch Technol 2AI Appl Artificial Intelligence Lab Barcelos Portugal LASI Assoc Lab Intelligent Syst Guimaraes Portugal TUS Technol Univ CLIFE Biosci Res Inst Midlands Midwest Ireland Shanghai Jiao Tong Univ Shanghai Chest Hosp Dept Cardiol Sch Med Shanghai Peoples R China Prince Wales Hosp Dept Med & Therapeut Div Cardiol Hong Kong Peoples R China Chinese Univ Hong Kong Li Ka Shing Inst Hlth Sci Lab Cardiac Imaging & 3D Printing Fac Med Hong Kong Peoples R China

ISBN: (纸本)9781510686021;9781510686038

The Left Atrial Appendage (LAA) is a complex and variable anatomical structure, where it is a common source of cardiac thrombi. To obtain a detailed assessment of the structure and assess thrombus formation, transesophageal echocardiography (TEE) is the most commonly used imaging modality. For these reasons, segmenting the LAA is of great importance. In this sense, studies have emerged in the literature that propose LAA segmentation methodologies from 3D TEE images. However, some 3D-TEE based methods require a manual initialization, keeping the method semi-automatic. This study aims to automate one state-of-the-art method to 3D segment the LAA in TEE images. For that, deep learning (DL) techniques were investigated to initialize the LAA centerline. In detail, the DL method based on UNET architecture was trained and validated using 188 3D TEE volumes. All 188 volumes were manually initialized by one experienced observer. The manual centerline was used as ground truth. After LAA centerline identification, the state-of-the-art LAA segmentation methodology was applied. The obtained LAA surface was compared with a corrected version, where a manual operator revised and corrected, if deemed, the initial manual centerline. Overall, the results show a high segmentation performance, achieving satisfactory results on the overall test dataset. In terms of metrics, an Average Distance Error of 0.60 +/- 0.46mm was achieved, a Dice Coefficient of 94.45 +/- 4.25%, and a 95% Hausdorff Distance of 2.21 +/- 1.86mm was obtained between the automatic and corrected surfaces. These results show the potential of DL methods to automate the LAA segmentation process through 3D TEE images.

关键词： left atrial appendage segmentation automatic initialization deep learning 3D transesophageal echocardiography

来源：评论

学校读者我要写书评

暂无评论

automatic initialization FOR ACTIVE CONTOUR MODEL IN BREAST CANCER DETECTION UTILIZING CONVENTIONAL ULTRASOUND AND COLOR DOPPLER 39

AUTOMATIC INITIALIZATION FOR ACTIVE CONTOUR MODEL IN BREAST ...

引用

39th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Keatmanee, Chadaporn Makhanov, Stanislav S. Kotani, Kazunori Lohitvisate, Wanrudee Thongvigitmanee, Saowapak S. SIIT Pathum Thani Thailand Japan Adv Inst Sci & Technol Nomi Ishikawa Japan Thammasat Univ Dept Radiol Pathum Thani Thailand Natl Elect & Comp Technol Ctr NECTEC Pathum Thani Thailand

ISBN: (纸本)9781509028092

Regular examination of breasts may prevent and help to cure because breast cancer is treatable when it is detected early. Therefore, a breast cancer screening modality being sensitivity and cost-effective like ultrasonic imaging modality (US), is strongly required. In addition, the combination of a conventional US and its adjunct, Color Doppler has been proved for decreasing the rate of false-positive in breast cancer diagnosis. Thus, combination of these imaging modalities in a breast cancer segmentation would provide some benefits as well. An effective method for feature segmentation, active contour model has been widely utilized for decades. A crucial stage that affects the performance of active contour model is the initialization. This paper proposes a novel method for an automatic initialization of active contour model designed specifically for US-based imaging modalities. The method estimates an initial contour by utilizing the fusion of conventional US and Color Doppler. Examples and comparisons with three state-of-the-art automatic initialization methods are demonstrated to present the advantages of the proposed method. The evaluation results show high accuracy of initialization as well as fast convergence to features of interest.

关键词： Breast cancer segmentation active contour model automatic initialization Ultrasound Color Doppler

来源：评论

学校读者我要写书评

暂无评论

Phase portrait analysis for automatic initialization of multiple snakes for segmentation of the ultrasound images of breast cancer

引用

PATTERN ANALYSIS AND APPLICATIONS 2017年第1期20卷 239-251页

作者： Kirimasthong, Khwunta Rodtook, Annupan Chaumrattanakul, Utairat Makhanov, Stanislav S. Thammasat Univ Sirindhorn Int Inst Technol Sch Informat & Comp Technol Tiwanont Rd A Muang 12000 Pathum Thani Thailand Ramkhamhang Univ Dept Comp Sci Bangkok 10240 Thailand Thammasat Univ Dept Radiol Fac Med 12 Khlong Luang Pathum Thani 12120 Thailand

Segmentation of ultrasound (US) images of breast cancer is one of the most challenging problems of modern medical image processing. A number of popular codes for US segmentation are based on the active contours (snakes) and on a variety of modifications of gradient vector flow. The snakes have been used to locate objects in various applications of medical images. However, the main difficulty in applying the method is initialization. Therefore, we suggest a new method for automatic initialization of active contours based on phase portrait analysis (PPA) of the underlying vector field and a sequential initialization of trial multiple snakes. The PPA makes it possible to exclude the noise and artifacts and properly initialize the multiple snakes. In turn, the trial snakes allow us to differentiate between the seeds initialized inside and outside the desired object. While preceding methods require the manual selection of at least one seed point inside the object or rely on the particular distribution of the gray levels, the proposed method is fully automatic and robust to the noise, as can be seen from the tests with synthetic and real images.

关键词： Active contours Phase portrait analysis automatic initialization

来源：评论

学校读者我要写书评

暂无评论

automatic initialization FOR NAVAL APPLICATION OF GRAPH SEGMENTATION TECHNIQUES: A COMPARATIVE STUDY

AUTOMATIC INITIALIZATION FOR NAVAL APPLICATION OF GRAPH SEGM...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Camino, Irene Zoelzer, Udo Helmut Schmidt Univ Hamburg Germany

ISBN: (纸本)9781479928934

Nowadays, many different image processing applications are of high interest to maritime authorities because of security reasons. Depending on the application, different kinds of images are employed. The extraction of ship silhouettes requires high resolution images in order to obtain accurate results. However, when the characteristics of the naval environment are visible the background complexity increases greatly and automatic approaches fail. In order to overcome these difficulties we propose an automatic initialization for graph segmentation techniques. A comparative study of earlier suggested initializations for different graph segmentation techniques is also presented. It shows that, under such unfavorable image conditions, finding the proper initialization in an automatic way is not trivial. Yet, the precision and recall achieved by our initialization are considerable higher regardless the graph segmentation. Furthermore, the performance is highly increased since the best results are obtained after only the first iteration.

关键词： naval images automatic initialization silhouette extraction graph segmentation

来源：评论

学校读者我要写书评

暂无评论

Anisotropic edge-enhanced active contour model with Gaussian difference for robust multi-category image segmentation

引用

VISUAL COMPUTER 2025年 1-18页

作者： Zhang, Fuzheng Bi, Xiaoyu Wang, Guina Weng, Guirong Chen, Yiyang Soochow Univ Sch Mech & Elect Engn 8 Jixue Rd Suzhou 215137 Jiangsu Peoples R China Univ New South Wales Sch Comp Sci & Engn Sydney NSW 2052 Australia

Active contour model (ACM) is a pivotal approach for image segmentation. However, conventional models are susceptible to noise and weak target boundaries, limiting their practical applications. Furthermore, uncertainty in the initial contour heightens model sensitivity. To address these challenges, we introduce DoG&EED, an active contour model grounded in the anisotropic diffusion equation and Gaussian convolution. The proposed anisotropic diffusion equation, termed EED, enhances noise robustness and edge localization by strengthening gradients along target boundaries while weakening them in noisy regions. Leveraging Gaussian kernel functions, we construct a streamlined energy function, the DoG operator, which efficiently captures essential image information while mitigating model complexity. A novel regularization function, independent of the global energy function, preserves its effectiveness while reducing iteration costs. By integrating YOLOv5 bounding boxes with DoG&EED, we mitigate initial contour sensitivity. Extensive experiments validate that DoG&EED boasts robust anti-noise capabilities and maintains high segmentation accuracy, achieving 81.2 DSI, 76.9 SI, and 78.4 JI in homogeneous experiments, along with 79.3 mIoU, 46.5 AP\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\textrm{AP}$$\end{document}, 66.8 AP50\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\textrm{AP}_{50}$$\end{document}, and 54.3 AP75\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemarg

关键词： Fast image segmentation Active contour method Anisotropic edge-enhanced Gaussian difference automatic initialization

来源：评论

学校读者我要写书评

暂无评论

Deep Center Point Regression Assisted by Active Contour for Instance Segmentation

Deep Center Point Regression Assisted by Active Contour for ...

引用

第43届中国控制会议

作者： Fuzheng Zhang Guirong Weng Yiyang Chen Guina Wang School of Mechanical and Electrical Engineering Soochow University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The field of image segmentation has spawned many research branches,mainly including mask-based and contourbased *** contour segmentation methods are easy to implement and have simple algorithm structures,while the continuous adjustment of parameters limits their *** this paper,a hybrid contour segmentation model,CenterAC,is proposed to solve these *** applies a target detector to generate an initial detection box and inputs it into the active contour model(ACM) to achieve curve *** combination makes the parameters of ACM fixed and the initial contour free from manual *** improve the topology of the initial contour,a hybrid evolution module is designed,and circular convolution is added to further improve the feature extraction and processing effect of contour *** demonstrate the superiority of CenterAC,with AP 31.4 and AP75 28.5 better than other deep learning models,and with the highest average IOU1,IOU2 and DSC among other ACMs.

关键词： Instance segmentation Deep learning Center detection automatic initialization Active contour Curve insensitivity

来源：评论

学校读者我要写书评

暂无评论

An automatic Lung Field Segmentation Algorithm Based on Imp roved Snake Model in X-ray Chest Radiograph 33

An Automatic Lung Field Segmentation Algorithm Based on Imp ...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Hu, Jun Li, Ping Huaqiao Univ Acad Informat Sci & Engn Xiamen 361021 Peoples R China

ISBN: (纸本)9781665440899

In order to solve the problems such as sensitive selection of artificial initial contour and inaccurate segmentation of the concave area when traditional Snake model is applied to segmentation of lung field in X-ray chest radiograph, an automatic segmentation method of lung field in X-ray chest radiograph based on improved Snake model is proposed. First, Otsu method was used to binarize the original image to obtain the binarization image including lung field and background area. After image inversion, connected domain manipulation and morphological processing, the binary image containing only lung field area was obtained. Then, automatic initialization of Snake model contour can be completed through edge detection. Finally, segmentation results can be obtained through the evolution of Snake model. The experimental results show that this method can get rid of the dependence of Snake model on artificial initial contour, improve the robustness of segmentation, and at the same time, segment the sunken area more accurately and have better segmentation effect.

关键词： Snake Model X-ray Chest Radiograph Lung Segmentation Otsu Method automatic initialization

来源：评论

学校读者我要写书评

暂无评论

An automatic Lung Field Segmentation Algorithm Based on Improved Snake Model in X-ray Chest Radiograph

An Automatic Lung Field Segmentation Algorithm Based on Impr...

引用

第33届中国控制与决策会议

作者： Jun Hu Ping Li Academy of Information Science and Engineering Huaqiao University

In order to solve the problems such as sensitive selection of artificial initial contour and inaccurate segmentation of the concave area when traditional Snake model is applied to segmentation of lung field in X-ray chest radiograph,an automatic segmentation method of lung field in X-ray chest radiograph based on improved Snake model is ***,Otsu method was used to binarize the original image to obtain the binarization image including lung field and background *** image inversion,connected domain manipulation and morphological processing,the binary image containing only lung field area was ***,automatic initialization of Snake model contour can be completed through edge ***,segmentation results can be obtained through the evolution of Snake *** experimental results show that this method can get rid of the dependence of Snake model on artificial initial contour,improve the robustness of segmentation,and at the same time,segment the sunken area more accurately and have better segmentation effect.

关键词： Snake Model X-ray Chest Radiograph Lung Segmentation Otsu Method automatic initialization

来源：评论

学校读者我要写书评

暂无评论

Saliency-guided level set model for automatic object segmentation

引用

PATTERN RECOGNITION 2019年 93卷 147-163页

作者： Cai, Qing Liu, Huiying Qian, Yiming Zhou, Sanping Duan, Xiaojun Yang, Yee-Hong Northwestern Polytech Univ Sch Automat Youyi West Rd 127 Xian 710072 Shanxi Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xianning West Rd 28 Xian 710049 Shanxi Peoples R China Northwestern Polytech Univ Natl Key Lab UVA Technol Youyi West Rd 127 Xian 710072 Shanxi Peoples R China

The level set model is a popular method for object segmentation. However, most existing level set models perform poorly in color images since they only use grayscale intensity information to defined their energy functions. To address this shortcoming, in this paper, we propose a new saliency-guided level set model (SLSM), which can automatically segment objects in color images guided by visual saliency. Specifically, we first define a global saliency-guided energy term to extract the color objects approximately. Then, by integrating information from different color channels, we define a novel local multichannel based energy term to extract the color objects in detail. In addition, unlike using a length regularization term in the conventional level set models, we achieve segmentation smoothness by incorporating our SLSM into a graph cuts formulation. More importantly, the proposed SLSM is automatically initialized by saliency detection. Finally, the evaluation on public benchmark databases and our collected database demonstrates that the new SLSM consistently outperforms many state-of-the-art level set models and saliency detecting methods in accuracy and robustness. (C) 2019 Published by Elsevier Ltd.

关键词： Level set model Object segmentation Visual saliency Graph cuts automatic initialization

来源：评论

学校读者我要写书评

暂无评论

AUTOIN: Method of automatic initialization of Active Contours Applied to Lungs in CT Images

引用

IEEE LATIN AMERICA TRANSACTIONS 2012年第4期10卷 1954-1960页

作者： Felix, J. H. S. Cortez, P. C. Cavalcante, T. S. Alexandria, A. R. Holanda, M. A. Univ Fed Ceara Dept Engn Teleinformat Fortaleza Ceara Brazil Univ Fed Ceara Dept Clin Med Fortaleza Ceara Brazil Univ Fed Ceara Dept Engn Teleinformat Fortaleza Ceara Brazil

In this work we present a new method of automatic initialization for the active contours method denominated AUTOIN. This method is applied in 72 computed tomography images of the lungs of healthy volunteers and ill patients. AUTOIN is compared to the method of object center localization. The accuracy obtained is calculated using the average and standard deviation of the distance (mm) between the points localized in each method. The results of AUTOIN for healthy volunteers are for the right lung mean of 12.3mm and standard deviation of 17.9mm, and for the left one mean of 11.7mm and 16.7mm of standard deviation. For the ill patients, the results are mean of 15.8mm and standard deviation of 20.4 mm for the right lung and mean of 14.6mm and 21.3mm of standard deviation for the left one. We conclude that AUTOIN enables to perform automatic definition of the initial contour inside the lungs.

关键词： automatic initialization active contours hybrid projection function computed tomography

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：