×
  • Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.
Principal Investigator  
Principal Investigator's Name: Wenxin Zhang
Institution: University of California, Berkeley
Department: Statistics
Country:
Proposed Analysis: Application of statistical and deep learning methods to raw neuroimaging data for early detection and classification of Alzheimer's Disease More and more people suffer from Alzheimer's disease (AD). AD is characterized by loss of memory and language ability,associated with aging.Early diagnosis of AD is particularly urgent. Studies have shown that mild cognitive impairment (MCI) has a high probability converted to AD. MCI may be a transition between healthy control (HC)and AD. With the advent of the era of big data,the machine learning algorithm is more and more popular in the diagnosis of disease. We plan to develop a method of deep learning to help us classify AD, MCI and HC. We plan to use data set of magnetic resonance imaging (MRI) from Alzheimer disease neuroimaging initiative (ADNI) as the data set. We will first have images preproccessed and then reduce the dimensionality of the image data. Then use deep convolutional neural network (CNN) to learn the data automatically. Due to the fact that many current architecture of CNN image detecting is not for medical images. So we focus on improving existing neural networks to achieve better diagnostic results for medical data. Here is our initial demand for ADNI data: 1. Clinical Data: Clinical data sets consist of clinical information for each subject, including demographics, physical examination, and cognitive data.The dataset also includes CSF concentrations and rates for these biomarkers. 2. MR Image Data/Standardized MRI Data Sets:MRI can clearly show brain atrophy in epileptic patients, showing excellent results of brain parenchyma and cerebrospinal fluid. 3. PET Image Data:Provide information of metabolic activity, so as to achieve the purpose of diagnosis。 4. Gennetic Data:Genetic factors play an important role in Alzheimer's disease, and the key goal of ADNI is to provide an opportunity to combine genetics with imaging and clinical data to help investigate the mechanisms of the disease.
Additional Investigators  
Investigator's Name: Eldon Chan
Proposed Analysis: 1. Objective and Question We’ll Be Answering o Application of statistical and deep learning methods to raw neuroimaging data for early detection and classification of Alzheimer's Disease o Initial Relevant Literature  https://www.frontiersin.org/articles/10.3389/fnagi.2019.00220/full  https://www.frontiersin.org/articles/10.3389/fncom.2019.00072/full  https://ieeexplore.ieee.org/document/5872590  https://arxiv.org/ftp/arxiv/papers/1904/1904.07773.pdf 2. Commentary on Data Sources, Structure, and Completeness o MRI Data  RAW, PRE- AND POST-PROCESSED IMAGE FILES, FMRI AND DTI  The collection of these images is central to meeting ADNI’s objective of developing biomarkers to track both the progression of Alzheimer’s disease and changes in the underlying pathology.  ADNI provides image data for AD(Alzheimer's disease) and CN(control group) over the project of 48 months. o Clinical Data  The ADNI clinical dataset comprises clinical information about each subject including recruitment, demographics, physical examinations, and cognitive assessment data. The full set of clinical data may be downloaded in bulk as comma separated values (CSV) files. 3. Preliminary Project Plan o Scikit-learn - image classification o Pytorch - Train neural network models in the open-source package PyTorch71 (on graphics processing units if possible)
Investigator's Name: Christopher Lim
Proposed Analysis: 1. Objective and Question We’ll Be Answering o Application of statistical and deep learning methods to raw neuroimaging data for early detection and classification of Alzheimer's Disease o Initial Relevant Literature  https://www.frontiersin.org/articles/10.3389/fnagi.2019.00220/full  https://www.frontiersin.org/articles/10.3389/fncom.2019.00072/full  https://ieeexplore.ieee.org/document/5872590  https://arxiv.org/ftp/arxiv/papers/1904/1904.07773.pdf 2. Commentary on Data Sources, Structure, and Completeness o MRI Data  RAW, PRE- AND POST-PROCESSED IMAGE FILES, FMRI AND DTI  The collection of these images is central to meeting ADNI’s objective of developing biomarkers to track both the progression of Alzheimer’s disease and changes in the underlying pathology.  ADNI provides image data for AD(Alzheimer's disease) and CN(control group) over the project of 48 months. o Clinical Data  The ADNI clinical dataset comprises clinical information about each subject including recruitment, demographics, physical examinations, and cognitive assessment data. The full set of clinical data may be downloaded in bulk as comma separated values (CSV) files. 3. Preliminary Project Plan o Scikit-learn - image classification o Pytorch - Train neural network models in the open-source package PyTorch71 (on graphics processing units if possible)
Investigator's Name: Baishan Guo
Proposed Analysis: 1. Objective o Application of statistical and deep learning methods to raw neuroimaging data for early detection and classification of Alzheimer's Disease o Initial Relevant Literature  https://www.frontiersin.org/articles/10.3389/fnagi.2019.00220/full  https://www.frontiersin.org/articles/10.3389/fncom.2019.00072/full  https://ieeexplore.ieee.org/document/5872590  https://arxiv.org/ftp/arxiv/papers/1904/1904.07773.pdf 2. Commentary on Data Sources, Structure, and Completeness o MRI Data  RAW, PRE- AND POST-PROCESSED IMAGE FILES, FMRI AND DTI  The collection of these images is central to meeting ADNI’s objective of developing biomarkers to track both the progression of Alzheimer’s disease and changes in the underlying pathology.  ADNI provides image data for AD(Alzheimer's disease) and CN(control group) over the project of 48 months. o Clinical Data  The ADNI clinical dataset comprises clinical information about each subject including recruitment, demographics, physical examinations, and cognitive assessment data. The full set of clinical data may be downloaded in bulk as comma separated values (CSV) files. 3. Preliminary Project Plan o Scikit-learn - image classification o Pytorch - Train neural network models in the open-source package PyTorch71 (on graphics processing units if possible)
Investigator's Name: Baishan Guo
Proposed Analysis: 1. Objective o Application of statistical and deep learning methods to raw neuroimaging data for early detection and classification of Alzheimer's Disease o Initial Relevant Literature  https://www.frontiersin.org/articles/10.3389/fnagi.2019.00220/full  https://www.frontiersin.org/articles/10.3389/fncom.2019.00072/full  https://ieeexplore.ieee.org/document/5872590  https://arxiv.org/ftp/arxiv/papers/1904/1904.07773.pdf 2. Commentary on Data Sources, Structure, and Completeness o MRI Data  RAW, PRE- AND POST-PROCESSED IMAGE FILES, FMRI AND DTI  The collection of these images is central to meeting ADNI’s objective of developing biomarkers to track both the progression of Alzheimer’s disease and changes in the underlying pathology.  ADNI provides image data for AD(Alzheimer's disease) and CN(control group) over the project of 48 months. o Clinical Data  The ADNI clinical dataset comprises clinical information about each subject including recruitment, demographics, physical examinations, and cognitive assessment data. The full set of clinical data may be downloaded in bulk as comma separated values (CSV) files. 3. Preliminary Project Plan o Scikit-learn - image classification o Pytorch - Train neural network models in the open-source package PyTorch71 (on graphics processing units if possible)