Multimodal image registration by proxy image synthesis

通过代理图像合成进行多模态图像配准

• 批准号: 8919113
• 负责人: Jerry L Prince
• 金额: $ 34.18万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-09-30 至 2017-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8919113
• 关键词: Adopted; Affect; Aging; Algorithms; Appearance; Area; Atlases; Clinical; Clinical Medicine; Communities; Computer Vision Systems; Computer software; Data; Data Collection; Databases; Development; Diffusion Magnetic Resonance Imaging; Disease; Environment; Evaluation; Functional Imaging; Functional Magnetic Resonance Imaging; Geometry; Goals; Grant; Growth; Health; Image; Java; Lead; Liquid substance; Magnetic Resonance Imaging; Manufacturer Name; Measures; Medical Imaging; Medical Research; Methods; Modality; Modeling; Motion; Multimodal Imaging; Neurosciences; Operative Surgical Procedures; Pathology; Performance; Physiologic pulse; Plague; Population; Positron-Emission Tomography; Predisposition; Procedures; Process; Proxy; Radial; Research; Research Personnel; Resources; Scanning; Science; Shapes; Specific qualifier value; Sum; Surface; Testing; Therapeutic; Tissues; Validation; Variant; Weight; Work; Writing; X-Ray Computed Tomography; base; clinical Diagnosis; computer code; cone-beam computed tomography; image reconstruction; image registration; imaging software; improved; intraoperative imaging; longitudinal analysis; neuroimaging; novel strategies; open source; outcome forecast; public health relevance; shape analysis; statistics; success; targeted imaging; theories; tool; vector; web site

DESCRIPTION (provided by applicant): Image registration is a fundamentally important capability in modern neuroscience and clinical medicine. Normalization in functional imaging studies, studies of shape changes in growth, aging, and disease, overlaying surgical plans on intraoperative images, and geometric distortion correction are examples of important applications of image registration. There are dozens of needs for registration in both intrasubject and intersubject applications as well. Therefore, any improvement in image registration performance will have an immediate impact on the scientific and clinical communities. Despite numerous advances in image reconstruction algorithms, the use of multiple modalities (or tissue contrasts) to carry out image registration is a virtually untapped area. The vastly dominant framework is to register a single image of the subject to another single image of the target, and if multiple images are available of either subject or target, they are registered by using the transformation derived from the single image registration. The proposed research will develop, evaluate, and validate a very simply explained but quite radical idea for multi-modal registration. The basic idea is to synthesize a "proxy" image from the subject image that has the same tissue contrast and intensity range as the target image and then use a conventional metric such as sum-of-square difference to carry out the registration between the subject proxy and target. Preliminary results demonstrate significant benefits in this approach. In the grant we will: 1) Optimize "proxy" multimodal image registration by exploring its theoretical justification as well a key parameters of the overall approach; 2) Apply "proxy" multimodal image registration to three key applications in neuroscience in order to validate the method and develop principles of best practice; and 3) Write open source software to carry out image synthesis, similarity computation, and rigid and deformable registration using the "proxy" image concept. Both the software to synthesize images for use in a user's favorite image registration method as well as software to carry out the entire "proxy" registration process in an optimized way will be made publicly available as open source computer code. The results of this research will lead to a new era in image registration by changing the way researchers and practitioners acquire and use data for neuroscientific studies and clinical medicine.

描述（由申请人提供）：图像注册是现代神经科学和临床医学的根本重要能力。功能成像研究中的归一化，对生长，衰老和疾病的形状变化的研究，术中图像上的手术计划覆盖了外科手术计划以及几何失真校正是图像注册的重要应用的示例。两个主体中都有数十个注册需求 和主体间应用程序。因此，图像注册绩效的任何改进都将对科学和临床社区产生直接影响。尽管图像重建算法取得了许多进步，但使用多种模式（或组织对比）进行图像注册是一个几乎没有开发的区域。极大的主导框架是将主体的单个图像注册为目标的另一个单个图像，如果主题或目标的多个图像可用，则使用从单个图像注册中得出的转换进行注册。拟议的研究将开发，评估和验证一个非常简单的解释，但对多模式登记进行了非常激进的想法。 基本思想是从主题图像中合成具有与目标图像相同的组织对比度和强度范围的“代理”图像，然后使用常规度量，例如平方差差，以在主体代理和目标之间进行注册。初步结果显示在这种方法中有显着的好处。在赠款中，我们将：1）通过探索其理论理由以及整体方法的关键参数来优化“代理”多模式图像注册； 2）将“代理”多模式图像注册应用于神经科学中的三个关键应用程序，以验证方法并制定最佳实践的原理； 3）编写开源软件，以使用“代理”图像概念进行图像综合，相似性计算以及刚性和可变形的注册。综合图像的软件都将用于用户喜欢的图像注册方法以及以优化的方式执行整个“代理”注册过程的软件，将作为开源计算机代码公开提供。这项研究的结果将通过改变研究人员和从业人员获取和使用数据进行神经科学研究和临床医学的方式，从而导致图像注册的新时代。

项目成果

Efficient Multi-Atlas Registration using an Intermediate Template Image.

使用中间模板图像进行高效的多图集配准。

• DOI: 10.1117/12.2256147
• 发表时间: 2017
• 期刊: Proceedings of SPIE--the International Society for Optical Engineering
• 作者: Dewey,BlakeE;Carass,Aaron;Blitz,AriM;Prince,JerryL
• 通讯作者: Prince,JerryL

A supervoxel based random forest synthesis framework for bidirectional MR/CT synthesis.

• DOI: 10.1007/978-3-319-68127-6_4
• 发表时间: 2017-09
• 期刊: Simulation and synthesis in medical imaging : ... International Workshop, SASHIMI ..., held in conjunction with MICCAI ..., proceedings. SASHIMI (Workshop)
• 作者: Zhao C;Carass A;Lee J;Jog A;Prince JL
• 通讯作者: Prince JL

Self Super-resolution for Magnetic Resonance Images.

• DOI: 10.1007/978-3-319-46726-9_64
• 发表时间: 2016-10
• 期刊: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
• 作者: Jog A;Carass A;Prince JL
• 通讯作者: Prince JL

Effects of Spatial Resolution on Image Registration.

空间分辨率对图像配准的影响。

• DOI: 10.1117/12.2217322
• 发表时间: 2016
• 期刊: Proceedings of SPIE--the International Society for Optical Engineering
• 作者: Zhao,Can;Carass,Aaron;Jog,Amod;Prince,JerryL
• 通讯作者: Prince,JerryL

Simulation and Synthesis in Medical Imaging.

• DOI: 10.1109/tmi.2018.2800298
• 发表时间: 2018-03
• 期刊: IEEE transactions on medical imaging
• 影响因子: 10.6
• 作者: Frangi AF;Tsaftaris SA;Prince JL
• 通讯作者: Prince JL