Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.

The early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance imaging (fMRI) data. However, we fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiao Zhou, Sanchita Kedia, Ran Meng, Mark Gerstein
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0312848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850106190532444160
author Xiao Zhou
Sanchita Kedia
Ran Meng
Mark Gerstein
author_facet Xiao Zhou
Sanchita Kedia
Ran Meng
Mark Gerstein
author_sort Xiao Zhou
collection DOAJ
description The early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance imaging (fMRI) data. However, we found that the genetic factors do not notably enhance the AD prediction by imaging. Thus, we focus on building an effective imaging-only model. In particular, we utilize data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a 3D Convolutional Neural Network (CNN) to analyze fMRI scans. Despite the limitations posed by our dataset (small size and imbalanced nature), our CNN model demonstrates accuracy levels reaching 92.8% and an ROC of 0.95. Our research highlights the complexities inherent in integrating multimodal medical datasets. It also demonstrates the potential of deep learning in medical imaging for AD prediction.
format Article
id doaj-art-ef3bc24103ee45f1973f6efda1f3d2c8
institution OA Journals
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-ef3bc24103ee45f1973f6efda1f3d2c82025-08-20T02:38:52ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e031284810.1371/journal.pone.0312848Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.Xiao ZhouSanchita KediaRan MengMark GersteinThe early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance imaging (fMRI) data. However, we found that the genetic factors do not notably enhance the AD prediction by imaging. Thus, we focus on building an effective imaging-only model. In particular, we utilize data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a 3D Convolutional Neural Network (CNN) to analyze fMRI scans. Despite the limitations posed by our dataset (small size and imbalanced nature), our CNN model demonstrates accuracy levels reaching 92.8% and an ROC of 0.95. Our research highlights the complexities inherent in integrating multimodal medical datasets. It also demonstrates the potential of deep learning in medical imaging for AD prediction.https://doi.org/10.1371/journal.pone.0312848
spellingShingle Xiao Zhou
Sanchita Kedia
Ran Meng
Mark Gerstein
Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
PLoS ONE
title Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
title_full Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
title_fullStr Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
title_full_unstemmed Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
title_short Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability.
title_sort deep learning analysis of fmri data for predicting alzheimer s disease a focus on convolutional neural networks and model interpretability
url https://doi.org/10.1371/journal.pone.0312848
work_keys_str_mv AT xiaozhou deeplearninganalysisoffmridataforpredictingalzheimersdiseaseafocusonconvolutionalneuralnetworksandmodelinterpretability
AT sanchitakedia deeplearninganalysisoffmridataforpredictingalzheimersdiseaseafocusonconvolutionalneuralnetworksandmodelinterpretability
AT ranmeng deeplearninganalysisoffmridataforpredictingalzheimersdiseaseafocusonconvolutionalneuralnetworksandmodelinterpretability
AT markgerstein deeplearninganalysisoffmridataforpredictingalzheimersdiseaseafocusonconvolutionalneuralnetworksandmodelinterpretability