检索结果-内蒙古大学图书馆

Non-rigid medical image registration using image field in demons algorithm

PATTERN RECOGNITION LETTERS 2019年 125卷 98-104页

作者： Lan, Sheng Guo, Zhenhua You, Jane Tsinghua Univ Dept Automat Beijing Peoples R China Tsinghua Univ Grad Sch Shenzhen Shenzhen Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

In medical imaging application, non-rigid registration is an important step that requires both accuracy and efficiency to align the deformed query image with the reference image. For non-rigid registration, demons is generally used as an effective algorithm. However, since the computational model of demons uses only the gradient information, the directional information of the image has not been fully utilized. In this paper, we proposed a novel non-rigid registration method for processing medical images by introducing the image field to the demons algorithm. As direction information is very important for spatial transformation in registration and the image fields contain the direction of the image, by combing image fields with the traditional model based registration algorithm, we introduce the orientation field directly to the model for estimating the distortion, and thus make a better use of the direction information of images and simplify the deformation model. Different performance measures are used to evaluate the qualitative measures of the proposed scheme. Experiments on brain images and fundus images show the improvement of the proposed algorithm compared to the other existing state-of-the-art methods. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Medical image Non-rigid Registration demons algorithm Image field

来源：评论

学校读者我要写书评

暂无评论

Application of demons algorithm in Ultrasound Elastography using B-Mode Ultrasound Images

Application of Demons Algorithm in Ultrasound Elastography u...

引用

Conference on Photons Plus Ultrasound - Imaging and Sensing

作者： Tehrani, Ali Kafaei Zad Mozaffarzadeh, Moein Mardi, Zahra Hozhabr, Seyed Hani Mehrmohammadi, Mohammad Makkiabadi, Bahador Amirkabir Univ Technol Dept Elect Engn Tehran Iran Tarbiat Modares Univ Dept Biomed Engn Tehran Iran Univ Tehran Med Sci Sch Med Dept Med Phys & Biomed Engn Tehran Iran Wayne State Univ Dept Biomed Engn Detroit MI USA Inst Adv Med Technol Res Ctr Biomed Technol & Robot Tehran Iran

ISBN: (纸本)9781510623996

UltraSound Elastography (USE) has been widely used to obtain mechanical properties of tissues. Radio frequency (RF) data is usually used in USE to estimate the displacement. However, RF data is not available in all ultrasound imaging devices. B-mode images which are basically the envelope of the RF data are the most well-known output of the common ultrasound imaging devices. In B-mode images, the phase information of RF data is lost. Consequently, USE can be more challenging and the strain image quality would be degraded. The aim of this paper is to employ demons algorithm, which is a powerful non-rigid image registration algorithm, to estimate displacement using B-mode images. In USE, the post-compression image may have large deformations in axial direction which deteriorates the demons algorithm performance. In order to compensate the large deformations, an optimization algorithm is proposed to find and compensate the mean value axial deformation. Experimental and numerical phantoms are used to verify the algorithm performance in normal and severe situations. The results are compared with the common normalized cross correlation (NCC) algorithm. The results confirm that demons algorithm is an appropriate algorithm for USE for B-mode images considering the fact that phase information are not available.

关键词： Ultrasound Elastography Displacement estimation demons algorithm non-rigid image registration

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional lung medical image registration based on improved demons algorithm

引用

OPTIK 2016年第4期127卷 1893-1899页

作者： Lu, Xiaoqi Yu, Hefeng Zhao, Ying Hou, He Li, Yinhui Inner Mongolia Univ Sci & Technol Sch Informat Engn Baotou 014010 Peoples R China

To put forward an accurate and effective registration method based on improved demons algorithm, and to register three-dimensional pulmonary medical images of the same individual whose lung has the deformation under different respiration state. The experimental data are the maximum and minimum respiratory phase of the three-dimensional pulmonary images within a cycle of respiratory movement. First, images for registration are registered globally and non-rigidly. Feature points are extracted and matched by scale invariant feature transform algorithm. Afterwards, the global registration is finished according to the transformation parameter computed based on matching results. Finally, images after global registration are registered non-rigidly utilizing improved demons algorithm. Image registration of human lung is realized employing improved method. The mean-square error between images before registration is 25,835.3 and it is reduced to 11,790.9 after registration. After further deal with improved demons algorithm, the mean-square error between images is reduced to 3726.31 and the descent rate of mean-square is up to 85.58%. The proposed method effectively registers three-dimensional pulmonary images, which provides a solid foundation for doctors to estimate pulmonary respiratory movement and analyze respiratory function. (C) 2015 Published by Elsevier GmbH.

关键词： Lung Registration 3D medical image Scale invariant feature transform demons algorithm

来源：评论

学校读者我要写书评

暂无评论

VLSI-Assisted Nonrigid Registration Using Modified demons algorithm

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2015年第12期23卷 2913-2921页

作者： Mishra, Ashutosh Mondal, Pulak Banerjee, Swapna Indian Inst Technol Dept Elect & Elect Commun Engn Kharagpur 721302 W Bengal India

Increasing demand of high-speed portable modules for multimedia applications has motivated the development of hardware-based solutions for image processing applications. Most of the nonrigid image registration algorithms are found to be unsuitable for hardware implementation because of their nonlinearity and computationally intensive nature. In this paper, an algorithm for nonrigid image registration based on demons approximation is proposed. The algorithm has been simulated in MATLAB and results show a 15% improvement in peak-signal-to-noise-ratio with a 17% reduction in registration time for 256 x 256 image over the original demons algorithm. The proposed algorithm is synthesized in Virtex6-xc6vlx760-2-ff1760 and maximum synthesized frequency is found to be 174 MHz. The proposed architecture provides the low cost, high-speed solution for the registration process, which is also helpful for making a portable system.

关键词： demons algorithm image registration nonrigid registration

来源：评论

学校读者我要写书评

暂无评论

Infrared image non-rigid registration based on regional information entropy demons algorithm

Infrared image non-rigid registration based on regional info...

引用

International Conference on Photonics and Optical Engineering (icPOE)

作者： Lu Chaoliang Ma Lihua Yu Ming Cui Shumin Wu Qingrong Air Force Engn Univ Sch Informat & Nav Xian 710077 Shanxi Peoples R China 95269Army Guangzhou 510071 Guangdong Peoples R China

ISBN: (纸本)9781628415650

Infrared imaging fault detection which is treated as an ideal, non-contact, non-destructive testing method is applied to the circuit board fault detection. Since Infrared images obtained by handheld infrared camera with wide-angle lens have both rigid and non-rigid deformations. To solve this problem, a new demons algorithm based on regional information entropy was proposed. The new method overcame the shortcomings of traditional demons algorithm that was sensitive to the intensity. First, the information entropy image was gotten by computing regional information entropy of the image. Then, the deformation between the two images was calculated that was the same as demons algorithm. Experimental results demonstrated that the proposed algorithm has better robustness in intensity inconsistent images registration compared with the traditional demons algorithm. Achieving accurate registration between intensity inconsistent infrared images provided strong support for the temperature contrast.

关键词： image processing fault detection demons algorithm information entropy non-rigid registration regional information entropy

来源：评论

学校读者我要写书评

暂无评论

Performance-aware programming for intraoperative intensity-based image registration on graphics processing units

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2021年第3期16卷 375-386页

作者： Leong, Martin C. W. Lee, Kit-Hang Kwan, Bowen P. Y. Ng, Yui-Lun Liu, Zhiyu Navab, Nassir Luk, Wayne Kwok, Ka-Wai Univ Hong Kong Dept Mech Engn Pok Fu Lam Hong Kong Peoples R China Imperial Coll London Dept Comp London SW7 2AZ England Tech Univ Munich Comp Aided Med Proc & Augmented Real D-85748 Munich Germany

Purpose Intensity-based image registration has been proven essential in many applications accredited to its unparalleled ability to resolve image misalignments. However, long registration time for image realignment prohibits its use in intra-operative navigation systems. There has been much work on accelerating the registration process by improving the algorithm's robustness, but the innate computation required by the registration algorithm has been unresolved. Methods Intensity-based registration methods involve operations with high arithmetic load and memory access demand, which supposes to be reduced by graphics processing units (GPUs). Although GPUs are widespread and affordable, there is a lack of open-source GPU implementations optimized for non-rigid image registration. This paper demonstrates performance-aware programming techniques, which involves systematic exploitation of GPU features, by implementing the diffeomorphic log-demons algorithm. Results By resolving the pinpointed computation bottlenecks on GPU, our implementation of diffeomorphic log-demons on Nvidia GTX Titan X GPU has achieved similar to 95 times speed-up compared to the CPU and registered a 1.3-M voxel image in 286 ms. Even for large 37-M voxel images, our implementation is able to register in 8.56 s, which attained similar to 258 times speed-up. Our solution involves effective employment of GPU computation units, memory, and data bandwidth to resolve computation bottlenecks. Conclusion The computation bottlenecks in diffeomorphic log-demons are pinpointed, analyzed, and resolved using various GPU performance-aware programming techniques. The proposed fast computation on basic image operations not only enhances the computation of diffeomorphic log-demons, but is also potentially extended to speed up many other intensity-based approaches. Our implementation is open-source on GitHub at https ://***/2PYZxQz..

关键词： demons algorithm Image-guided treatment Non-rigid registration Parallel computing Surgical guidance

来源：评论

学校读者我要写书评

暂无评论

Validation of an Improved 'Diffeomorphic demons' algorithm for Deformable Image Registration in Image-Guided Radiation Therapy

Validation of an Improved 'Diffeomorphic Demons' Algorithm f...

引用

2nd International Conference on Biomedical Engineering and Biotechnology (iCBEB)

作者： Zhou, Lu Zhou, Linghong Zhang, Shuxu Zhen, Xin Yu, Hui Zhang, Guoqian Wang, Ruihao Guangzhou Med Univ Affiliated Tumor Hosp Radiotherapy Ctr Guangzhou 510095 Guangdong Peoples R China Southern Med Univ Dept Biomed Engn Guangzhou 510095 Guangdong Peoples R China

Deformable image registration (DIR) was widely used in radiation therapy, such as in automatic contour generation, dose accumulation, tumor growth or regression analysis. To achieve higher registration accuracy and faster convergence, an improved 'diffeomorphic demons' registration algorithm was proposed and validated. Based on Brox et al.'s gradient constancy assumption and Malis's efficient second-order minimization (ESM) algorithm, a grey value gradient similarity term and a transformation error term were added into the demons energy function, and a formula was derived to calculate the update of transformation field. The limited Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm was used to optimize the energy function so that the iteration number could be determined automatically. The proposed algorithm was validated using mathematically deformed images and physically deformed phantom images. Compared with the original 'diffeomorphic demons' algorithm, the registration method proposed achieve a higher precision and a faster convergence speed. Due to the influence of different scanning conditions in fractionated radiation, the density range of the treatment image and the planning image may be different. In such a case, the improved demons algorithm can achieve faster and more accurate radiotherapy.

关键词： demons algorithm deformable registration gradient constancy assumption efficient second-order minimization L-BFGS algorithm

来源：评论

学校读者我要写书评

暂无评论

Object-Oriented Motion Estimation using Edge-Based Image Registration 22

Object-Oriented Motion Estimation using Edge-Based Image Reg...

引用

22nd IEEE International Workshop on Multimedia Signal Processing (MMSP)

作者： Asikuzzaman, Md Rajamohan, Deepak Pickering, Mark R. Univ New South Wales Sch Engn & Informat Technol Canberra ACT Australia

ISBN: (纸本)9781728193205

Video data storage and transmission cost can be reduced by minimizing the temporally redundant information among frames using an appropriate motion-compensated prediction technique. In the current video coding standard, the neighbouring frames are exploited to predict the motion of the current frame using global motion estimation-based approaches. However, the global motion estimation of a frame may not produce the actual motion of individual objects in the frame as each of the objects in a frame usually has its own motion. In this paper, an edge-based motion estimation technique is presented that finds the motion of each object in the frame rather than finding the global motion of that frame. In the proposed method, edge position difference (EPD) similarity measure-based image registration between the two frames is applied to register each object in the frame. A superpixel search is then applied to segment the registered object. Finally, the proposed edge-based image registration technique and demons algorithm are applied to predict the objects in the current frame. Our experimental analysis demonstrates that the proposed algorithm can estimate the motions of individual objects in the current frame accurately compared to the existing global motion estimation-based approaches.

关键词： Image registration superpixel edge position difference (EPD) motion estimation demons algorithm

来源：评论

学校读者我要写书评

暂无评论

Simultaneous respiratory motion correction and image reconstruction in 4D-multi pinhole small animal SPECT

引用

MEDICAL PHYSICS 2019年第11期46卷 5047-5054页

作者： Naseri, Maryam Rajabi, Hossein Wang, Jing Abbasi, Mehrshad Kalantari, Faraz Louisiana State Univ Dept Phys & Astron Med Phys Program Baton Rouge LA 70803 USA Tarbiat Modares Univ Fac Med Dept Med Phys Tehran Iran UT Southwestern Med Ctr Dallas Dept Radiat Oncol Dallas TX USA Univ Tehran Med Sci Vali Asr Hosp Dept Nucl Med Tehran Iran Univ Arkansas Med Sci Dept Radiat Oncol Little Rock AR 72205 USA

Purpose Respiratory motion in the chest region during single photon emission computed tomography (SPECT) is a major degrading factor that reduces the accuracy of image quantification. This effect is more notable when the tumor is very small, or the spatial resolution of the imaging system is less than the respiratory motion amplitude. Small animals imaging systems with sub-millimeter spatial resolution need more attention to the respiratory motion for quantitative studies. We developed a motion-embedded four-dimensional (4D)-multi pinhole SPECT (MPS) reconstruction algorithm for respiratory motion correction. This algorithm makes full use of projection statistics for reconstruction of every individual frame. Methods The ROBY phantom with small tumors in liver was generated in eight different phases during one respiratory cycle. The MPS projections were modeled using a fast ray tracing method simulating an MPS acquisition. Individual frames were reconstructed and used for motion estimation. The demons non-rigid registration algorithm was used to calculate deformation vector fields (DVFs) for simultaneous motion correction and image reconstruction. A motion-embedded 4D-MPS method was used to reconstruct images using all the projections and corresponding DVFs, simultaneously. The 4D-MPS reconstructed images were compared to the low-count single frame (LCSF) reconstructed image, the three-dimensional (3D)-MPS images reconstructed using individual frames, and post reconstruction registration (PRR) that aligns all individual phases to a reference frame using demons-derived DVFs. The tumor volume relative error (TVE), tumor contrast relative error (TCE), and dice index (DI) for 2, 3, and 4 mm liver were calculated and compared for different reconstruction methods. Results For the 4D-MPS reconstruction method, TVE was reduced and DI was higher compared to PRR, 3D-MPS, and LCSF. The extent of the improvement was higher for the small tumor size (i.e. 2 mm). For the biggest tu

关键词： deformation vector fields demons algorithm multi pinhole SPECT respiratory motion correction

来源：评论

学校读者我要写书评

暂无评论

Validation of an Improved 'Diffeomorphic demons' algorithm for Deformable Image Registration in Image-Guided Radiation Therapy

引用

BIO-MEDICAL MATERIALS AND ENGINEERING 2014年第1期24卷 373-382页

关键词： demons algorithm deformable registration gradient constancy assumption efficient second-order minimization L-BFGS algorithm

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：