权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Higher Order Convolutional Neural Network for Classification of Lewy-body Diseases and Alzheimers Disease

用于路易体病和阿尔茨海默病分类的高阶卷积神经网络

基本信息

批准号：
10363781
负责人：
Baba C Vemuri
金额：
$ 70.23万
依托单位：
UNIVERSITY OF FLORIDA
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-02-15 至 2024-01-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10363781
关键词：
Affect Alzheimer&apos s Disease Alzheimer&apos s disease patient Alzheimer&apos s disease related dementia Architecture Atrophic Biological Markers Brain Brain region Brain scan Classification Clinical Communities Complex Computer Vision Systems Consensus Consult Control Groups Counseling Country Data Data Sources Dementia Dementia with Lewy Bodies Detection Development Diagnosis Diagnostic Diagnostic Imaging Differential Diagnosis Diffusion Diffusion Magnetic Resonance Imaging Discrimination Disease Euclidean Space Exhibits Fiber Geometry Goals Gold Grant Image Imaging Techniques Individual Lead Lewy Body Dementia Lewy Body Disease Literature MRI Scans Magnetic Resonance Imaging Measures Medical Imaging Methods Modeling Nationalities Neurodegenerative Disorders Neurologist Neurology Parkinson Disease Patients Population Research Research Priority Resolution Sampling Scanning Selection Bias Sensitivity and Specificity Series Signal Transduction Site Specialist Statistical Methods Symptoms Techniques Testing Time Tissues Validation Work base clinical diagnosis cohort convolutional neural network data space deep learning deep neural network design detection method diagnostic accuracy diffusion weighted disorder control imaging approach improved learning network learning strategy mathematical model multimodal data multimodality neurorestoration novel programs progression marker rapid diagnosis success vector

项目摘要

PROJECT SUMMARY Dementia with Lewy body (DLB), Parkinsons Disease (PD) and Alzheimers Disease (AD) are among the most debilitating neurodegenerative disorders that afﬂict patients in all countries and of all nationalities. One of the Alzheimer related dementias (ADRD) national research priorities for DLB is to develop and validate imaging techniques to improve the differential diagnostic accuracy of DLB versus other diseases. Magnetic Resonance Imaging (MRI) is currently one of the most widely used diagnostic imaging techniques for detection of neuro- degenerative disorders. However, standard T1 and T2-MRI may not provide the needed sensitivity and speciﬁcity for differential diagnosis of DLB vs. AD and PD. Recently, Diffusion MRI (dMRI), speciﬁcally Diffusion Tensor Imaging (DTI), has exhibited better sensitivity to the detection of some of these disorders. However, DTI is known for its inability to cope with complex ﬁber geometries prevalent in the brain. This limitation can however be over- come by using sophisticated mathematical models in conjunction with high angular resolution diffusion imaging (HARDI). Our preliminary data suggests that learned micro-structural features from HARDI lead to high sensitivity and speciﬁcity in differentiating PD vs. control and others in literature have shown discrimina- tion between different stages of AD using macro-structural features derived from T1-MRI. This motivates us to combine micro- and macro-structural features via a multi-modality approach to differentiate DLB vs. PD, AD and controls. Differentiating between DLB, PD and AD is challenging because of possible overlap in clinical symptoms leading to misdiagnosis. Further, differentiating between them is of high signiﬁcance since treatments including counseling for each are distinct. We propose a multi-modal approach that combines the advantages of T1- and diffusion-MRI to achieve this goal. Recently, convolutional neural nets (CNNs) have had great success in image classiﬁcation tasks in computer vision and medical imaging. CNNs however can not cope with HARDI data in its native form, which are samples of functions deﬁned on non-Euclidean (curved) domains. This motivates us to develop a novel higher order CNN that is a parameter efﬁcient, inter- pretable geometric deep learning network possessing improved model capacity, which we call the VolterraNet. The VolterraNet will be designed for such data with the goal of facilitating the classiﬁcation of DLB, PD and AD groups. Further, VolterraNet will automatically localize the regions in the brain that are signiﬁcantly discriminatory of these patient groups. We will test the VolterraNet on HARDI scans acquired from a cohort of 356 Controls, 355 PD, 216 DLB and 240 AD scans obtained from a medley of data sites including the PDBP, 1Florida-ADRC and PPMI. The VolterraNet will be validated using the standard leave-k-out cross-validation method with the precision recall measure. The gold standard used will be the specialist-assigned clinical diagnosis from contributing stud- ies (e.g. consensus assignment from ADRCs). The VolterraNet will have signiﬁcant beneﬁts to the Neurology community through better detection and diagnosis of several neurodegenerative disorders.

项目总结