Computer Aided Diagnosis and Followup of Alzheimer's Disease

阿尔茨海默病的计算机辅助诊断和随访

• 批准号: 7898894
• 负责人: Tianming Liu
• 金额: $ 11.9万
• 依托单位: UNIVERSITY OF GEORGIA
• 依托单位国家: 美国
• 财政年份: 2007
• 资助国家: 美国
• 起止时间: 2007-08-20 至 2012-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7898894
• 关键词: Aging; Algorithms; Alzheimer' s Disease; Automobile Driving; Autopsy; Award; Biological Markers; Biometry; Brain; Characteristics; Clinical; Cognitive; Computer-Assisted Diagnosis; Computing Methodologies; Data; Data Set; Detection; Development; Diagnosis; Diffusion; Disease; Early Diagnosis; Emotional; Evaluation; Explosion; Family; Follow-Up Studies; Future; General Population; Hand; Healthcare; Image; Imagery; Knowledge; Least-Squares Analysis; Magnetic Resonance Imaging; Maps; Measurement; Measures; Medical Imaging; Methods; Modeling; Monitor; Neuroanatomy; Neurobiology; Neurologic; Neurology; Patients; Physicians; Play; Population; Principal Investigator; Process; Property; Public Health; Reproducibility; Research; Role; Sample Size; Scanning; Series; Societies; Solutions; Specialist; Surface; Systems Analysis; Thick; Time; Tissues; Training; Translating; base; career; career development; clinical Diagnosis; clinical practice; computer framework; computerized tools; cost; disability; experience; follow-up; gray matter; neurogenetics; neuroimaging; neuropathology; novel; predictive modeling; programs; reconstruction; social; theories; tool; vector

DESCRIPTION (provided by applicant): The aging of the population over the next quarter century will increase the already substantial personal, social and governmental costs of Alzheimer's disease. The future of healthcare of AD lies in the early diagnosis and treatment of AD. Neuroimaging is playing an increasingly critical role in research and clinical practice as valid early markers could be developed for both disease detection and monitoring. This research will come up with novel computational tools for computer aided diagnosis and followup of Alzheimer's disease, which is a substantial contribution to an important problem of general public health. During the award period, the applicant's career development focuses on developing novel computational methods for computer aided diagnosis and follow-up of AD. The applicant's career training focuses on 1) obtaining in-depth knowledge and hands-on experience in medical imaging; 2) obtaining in- depth knowledge in clinical neuroanatomy; 3) obtaining in-depth understanding of clinical diagnosis and follow-up of AD; 4) obtaining in-depth knowledge of biostatistics; 5) obtaining moderate knowledge in neuropathology, neurobiology, neurology, neurogenetics of AD. In this 4-year K01 proposal, the applicant will develop novel neuroimage analysis algorithms for Computer Aided Diagnosis and Follow-up of Alzheimer's Diseases (CADFAD). Specifically, we will 1) Develop and validate novel high-dimensional volume registration method based on deformation invariant attribute vectors (DIAV); (2) Develop and validate novel cortical surface based quantitation methods, including cortical surface reconstruction, registration, cortical attributes mapping, statistical inference, and visualization; and (3) Develop and validate novel gray matter diffusivity quantitation methods.

描述（由申请人提供）： 在接下来的四分之一世纪，人口的老龄化将增加阿尔茨海默氏病的个人，社会和政府成本。 AD医疗保健的未来在于早期诊断和治疗AD。神经影像学在研究和临床实践中起着越来越重要的作用，因为可以为疾病检测和监测开发有效的早期标记。这项研究将提供用于计算机辅助诊断和对阿尔茨海默氏病的随访的新型计算工具，这是对一般公共卫生的重要问题的实质性贡献。在奖励期间，申请人的职业发展着重于开发用于计算机辅助诊断和AD随访的新型计算方法。申请人的职业培训重点是1）获得医学成像方面的深入知识和动手经验； 2）获得临床神经解剖学的深度知识； 3）深入了解AD的临床诊断和随访； 4）获得深入的生物统计学知识； 5）在AD的神经病理学，神经生物学，神经学，神经遗传学方面获得适度的知识。在这项为期4年的K01提案中，申请人将开发用于计算机辅助诊断和随访阿尔茨海默氏病（CADFAD）的新型神经图像分析算法。具体而言，我们将基于变形不变属性向量（DIAV）开发和验证新型的高维高体积注册方法； （2）开发和验证基于皮质表面的新型定量方法，包括皮质表面重建，注册，皮质属性映射，统计推断和可视化； （3）开发和验证新型的灰质扩散率定量方法。

项目成果

A computational model of cerebral cortex folding.

• DOI: 10.1007/978-3-642-04271-3_56
• 发表时间: 2009
• 期刊: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

Automatic cortical sulcal parcellation based on surface principal direction flow field tracking.

• DOI: 10.1016/j.neuroimage.2009.03.039
• 发表时间: 2009-07-15
• 期刊: NeuroImage
• 影响因子: 5.7
• 作者: Li G;Guo L;Nie J;Liu T
• 通讯作者: Liu T

Optimization of functional brain ROIs via maximization of consistency of structural connectivity profiles.

通过最大化结构连接配置文件的一致性来优化功能性大脑投资回报率。

• DOI: 10.1016/j.neuroimage.2011.08.037
• 发表时间: 2012
• 期刊: NeuroImage
• 影响因子: 5.7
• 作者: Zhu,Dajiang;Li,Kaiming;Faraco,CarlosCesar;Deng,Fan;Zhang,Degang;Guo,Lei;Miller,LStephen;Liu,Tianming
• 通讯作者: Liu,Tianming

Dynamic functional connectomics signatures for characterization and differentiation of PTSD patients.

用于表征和区分 PTSD 患者的动态功能连接组学特征

• DOI: 10.1002/hbm.22290
• 发表时间: 2014-04
• 期刊: HUMAN BRAIN MAPPING
• 影响因子: 4.8
• 作者: Li, Xiang;Zhu, Dajiang;Jiang, Xi;Jin, Changfeng;Zhang, Xin;Guo, Lei;Zhang, Jing;Hu, Xiaoping;Li, Lingjiang;Liu, Tianming
• 通讯作者: Liu, Tianming

Predicting cortical ROIs via joint modeling of anatomical and connectional profiles.

通过解剖和连接轮廓的联合建模来预测皮质 ROI

• DOI: 10.1016/j.media.2013.03.007
• 发表时间: 2013-08
• 期刊: MEDICAL IMAGE ANALYSIS
• 影响因子: 10.9
• 作者: Zhang, Tuo;Zhu, Dajiang;Jiang, Xi;Ge, Bao;Hu, Xintao;Han, Junwei;Guo, Lei;Liu, Tianming
• 通讯作者: Liu, Tianming