Basic Science and Pathogenesis

Assessing tau accumulation in early affected areas like the lateral entorhinal cortex (EC) and inferior temporal gyrus (ITG) enables early prediction of disease progression and cognitive decline. However, positron emission tomography (PET) imaging poses radiation exposure and cost concerns. This res...

Full description

Saved in:
Bibliographic Details
Published in:Alzheimer's & dementia Vol. 20 Suppl 1; p. e092140
Main Authors: Kim, Jin-Yang, Song, Yeong-Hun, Lee, Wha Jin, Seong, Joon-Kyung
Format: Journal Article
Language:English
Published: United States 01.12.2024
Subjects:
ISSN:1552-5279
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Assessing tau accumulation in early affected areas like the lateral entorhinal cortex (EC) and inferior temporal gyrus (ITG) enables early prediction of disease progression and cognitive decline. However, positron emission tomography (PET) imaging poses radiation exposure and cost concerns. This research aims to develop a deep learning model predicting tau positivity in these regions using MRI. In this study, we used the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, of which dataset was partitioned into train, validation, and test sets (8:1:1 ratio), encompassing a total of 1010 scans, all of whom underwent T1-weighted magnetic resonance imaging (MRI) and [18F] flortaucipir-PET imaging. For the T1-weighted MRI images, FreeSurfer v7.2 was employed to perform pre-processing and extract cortical thickness measurements. Simultaneously, [18F] flortaucipir-PET imaging was processed to compute voxel-wise regions of interest (ROIs) for 66 specific brain regions. Regional tau positivity was established using a cutoff at a z-score of 1.25, with a focus on cognitive normal (CN) subjects within the train set. To predict early tau accumulation regions, we developed an attention mechanism-based encoder-decoder model by adopting a Transformer model into our problem setting, performing sequential predictions for each of the 66 regions. Notably, the model's predictive performance in initial regions significantly influences subsequent predictions. Consequently, we implemented a prioritization strategy, emphasizing predictions from areas where the model demonstrated high accuracy. This approach was designed to enhance the overall predictive accuracy of the model. Predicting five early tau accumulation regions per hemisphere, our model achieved an average AUC of 0.84 and accuracy of 84% for the test dataset (112 participants). Notably, in critical early disease progression regions (fusiform gyrus and ITG), AUC values of 0.84, 0.85, and accuracies of 84.4%, 84% were observed. Furthermore, the proposed prioritization strategy improved performance compared to predictions using vanilla attention-based model. We developed an attention mechanism-based architecture with an encoder-decoder structure. By predicting outcomes not only based on cortical thickness values but also their cross-attention-based contexture information, we could achieve highly accurate tau prediction in early and challenging regions.
AbstractList Assessing tau accumulation in early affected areas like the lateral entorhinal cortex (EC) and inferior temporal gyrus (ITG) enables early prediction of disease progression and cognitive decline. However, positron emission tomography (PET) imaging poses radiation exposure and cost concerns. This research aims to develop a deep learning model predicting tau positivity in these regions using MRI. In this study, we used the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, of which dataset was partitioned into train, validation, and test sets (8:1:1 ratio), encompassing a total of 1010 scans, all of whom underwent T1-weighted magnetic resonance imaging (MRI) and [18F] flortaucipir-PET imaging. For the T1-weighted MRI images, FreeSurfer v7.2 was employed to perform pre-processing and extract cortical thickness measurements. Simultaneously, [18F] flortaucipir-PET imaging was processed to compute voxel-wise regions of interest (ROIs) for 66 specific brain regions. Regional tau positivity was established using a cutoff at a z-score of 1.25, with a focus on cognitive normal (CN) subjects within the train set. To predict early tau accumulation regions, we developed an attention mechanism-based encoder-decoder model by adopting a Transformer model into our problem setting, performing sequential predictions for each of the 66 regions. Notably, the model's predictive performance in initial regions significantly influences subsequent predictions. Consequently, we implemented a prioritization strategy, emphasizing predictions from areas where the model demonstrated high accuracy. This approach was designed to enhance the overall predictive accuracy of the model. Predicting five early tau accumulation regions per hemisphere, our model achieved an average AUC of 0.84 and accuracy of 84% for the test dataset (112 participants). Notably, in critical early disease progression regions (fusiform gyrus and ITG), AUC values of 0.84, 0.85, and accuracies of 84.4%, 84% were observed. Furthermore, the proposed prioritization strategy improved performance compared to predictions using vanilla attention-based model. We developed an attention mechanism-based architecture with an encoder-decoder structure. By predicting outcomes not only based on cortical thickness values but also their cross-attention-based contexture information, we could achieve highly accurate tau prediction in early and challenging regions.
Author Seong, Joon-Kyung
Kim, Jin-Yang
Lee, Wha Jin
Song, Yeong-Hun
AuthorAffiliation Alzheimer's Disease Neuroimaging Initiative, http://adni.loni.usc.edu/, CA, USA
AuthorAffiliation_xml – name: Alzheimer's Disease Neuroimaging Initiative, http://adni.loni.usc.edu/, CA, USA
Author_xml – sequence: 1
  givenname: Jin-Yang
  surname: Kim
  fullname: Kim, Jin-Yang
  organization: Korea University, Seoul, Korea, Republic of (South)
– sequence: 2
  givenname: Yeong-Hun
  surname: Song
  fullname: Song, Yeong-Hun
  organization: Korea University, Seoul, Korea, Republic of (South)
– sequence: 3
  givenname: Wha Jin
  surname: Lee
  fullname: Lee, Wha Jin
  organization: NeuroXT, Seoul, Korea, Republic of (South)
– sequence: 4
  givenname: Joon-Kyung
  surname: Seong
  fullname: Seong, Joon-Kyung
  organization: NeuroXT, Seoul, Korea, Republic of (South)
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39751223$$D View this record in MEDLINE/PubMed
BookMark eNo1jstKA0EQAAdRzEMvfkDYH9jY3fPYnaMGo0JAwdxD70yPriSTJRMP-vUK6qluVTVRp3mfRakrhDkC0DVvv-bgCQ2cqDFaS7Wlxo_UpJR3AAMt2nM10r6xSKTHanbLpQ_VS-glB6k4x-qZj2_7V8lS-nKhzhJvi1z-carWy7v14qFePd0_Lm5W9eD1sSY2LhGjgEnOhbZ1CWyK0LLx0KEmF0PqfoouSkiYEJmFXOgCp8Y1UU_V7Fc7fHQ7iZvh0O_48Ln5_9TfLZ09wQ
ContentType Journal Article
Copyright 2024 The Alzheimer's Association. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.
Copyright_xml – notice: 2024 The Alzheimer's Association. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.
CorporateAuthor ADNI
CorporateAuthor_xml – name: ADNI
DBID CGR
CUY
CVF
ECM
EIF
NPM
DOI 10.1002/alz.092140
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
DatabaseTitleList MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
DeliveryMethod fulltext_linktorsrc
EISSN 1552-5279
ExternalDocumentID 39751223
Genre Journal Article
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1OC
1~.
1~5
24P
33P
4.4
457
4G.
53G
5VS
7-5
71M
7RV
7X7
8FI
8FJ
8P~
AACTN
AAEDT
AAHHS
AAIKJ
AAKOC
AALRI
AANLZ
AAOAW
AAXLA
AAXUO
AAYCA
ABBQC
ABCQJ
ABCUV
ABIVO
ABJNI
ABMAC
ABMZM
ABUWG
ABWVN
ACCFJ
ACCMX
ACCZN
ACGFS
ACGOF
ACPOU
ACRPL
ACXQS
ADBBV
ADBTR
ADEZE
ADHUB
ADKYN
ADMUD
ADNMO
ADPDF
ADVLN
ADZMN
ADZOD
AEEZP
AEIGN
AEKER
AENEX
AEQDE
AEUYR
AEVXI
AFKRA
AFTJW
AFWVQ
AGHFR
AGUBO
AGWIK
AGYEJ
AITUG
AIURR
AIWBW
AJBDE
AJOXV
AJRQY
AKRWK
ALMA_UNASSIGNED_HOLDINGS
ALUQN
AMFUW
AMRAJ
AMYDB
ANZVX
AZQEC
BENPR
BFHJK
BLXMC
C45
CCPQU
CGR
CUY
CVF
DCZOG
EBS
ECM
EIF
EJD
EMOBN
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FIRID
FNPLU
FYUFA
G-Q
GBLVA
HMCUK
HVGLF
HX~
HZ~
IHE
J1W
K9-
LATKE
LEEKS
M0R
M41
MO0
MOBAO
N9A
NAPCQ
NPM
O-L
O9-
OAUVE
OVD
OVEED
OZT
P-8
P-9
P2P
PC.
PGMZT
PIMPY
PSYQQ
Q38
QTD
RIG
ROL
RPM
RPZ
SDF
SDG
SEL
SES
SSZ
SUPJJ
T5K
TEORI
UKHRP
~G-
ID FETCH-LOGICAL-p93t-2a46f2a1e04f66c886f05fd08a490b1326dcfb5126decf1f11aae26cbcaf767d3
IngestDate Wed Feb 19 02:03:27 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License 2024 The Alzheimer's Association. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-p93t-2a46f2a1e04f66c886f05fd08a490b1326dcfb5126decf1f11aae26cbcaf767d3
PMID 39751223
ParticipantIDs pubmed_primary_39751223
PublicationCentury 2000
PublicationDate 2024-Dec
PublicationDateYYYYMMDD 2024-12-01
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-Dec
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Alzheimer's & dementia
PublicationTitleAlternate Alzheimers Dement
PublicationYear 2024
SSID ssj0040815
Score 2.4102077
Snippet Assessing tau accumulation in early affected areas like the lateral entorhinal cortex (EC) and inferior temporal gyrus (ITG) enables early prediction of...
SourceID pubmed
SourceType Index Database
StartPage e092140
SubjectTerms Aged
Alzheimer Disease - diagnostic imaging
Alzheimer Disease - pathology
Carbolines
Cognitive Dysfunction - diagnostic imaging
Cognitive Dysfunction - pathology
Deep Learning
Disease Progression
Entorhinal Cortex - diagnostic imaging
Entorhinal Cortex - pathology
Female
Humans
Magnetic Resonance Imaging
Male
Neuroimaging - methods
Positron-Emission Tomography
tau Proteins - metabolism
Temporal Lobe - diagnostic imaging
Temporal Lobe - pathology
Title Basic Science and Pathogenesis
URI https://www.ncbi.nlm.nih.gov/pubmed/39751223
Volume 20 Suppl 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Consumer Health Database (ProQuest)
  databaseCode: M0R
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/familyhealth
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  databaseCode: 7X7
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/healthcomplete
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Nursing & Allied Health Database
  databaseCode: 7RV
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/nahs
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  databaseCode: BENPR
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: https://www.proquest.com/central
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  databaseCode: PIMPY
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: http://search.proquest.com/publiccontent
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: ProQuest
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  databaseCode: 24P
  dateStart: 20240101
  customDbUrl:
  isFulltext: true
  eissn: 1552-5279
  dateEnd: 99991231
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  omitProxy: false
  ssIdentifier: ssj0040815
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bS8MwFA7eEF9E8X4ZffBtVJs0bdNHFUVERWTg9jTSJnGF2RW3ifrrPUnTbmwI-uBLCbm1yZeenBNOzofQCUm1nqojAEjpu1QJ5bKASTeQjEifw4pITZzZu-jhgbXb8aPlcB8aOoEoz9nHR1z8K9SQB2Drq7N_gLvuFDIgDaDDE2CH56-Av-Aw8fU_ay4DgJY3eNFCLRtOK6Pn_a-ezAx9SjQ0a0CYw8KsFtWWa_k2y90Ot3ucPo6xfrwdCQn3Zjzr1vPc47pNXV3Wfr-ar_hzbHuyhw2ETjluSCsgA228lgQwlQQlXtNwkDbxlCiUXkxwGYppTkyXYV95_-t0vhLMZvFqsAFVCdSR8jryTFDsqmgRLZMoiLU4u_eeqi2Ygp4T1LFoydnkRWtotWo6Y0cYfaK1gdatIeCclwBuogWZb6GGAc-x4DkAnjMN3jZqXV-1Lm9cy2DhFrE_cgmnoSIcS4-qMEwZC5UXKOExTmMvwaA5i1Ql8DWhkKnCCmPOJQnTJOUqCiPh76ClfJDLPeQILERCoURQpk1ILrjSsWATRrCgvtpHu-VoukUZpaRbjfPgx5JDtDbB-Agtjd7G8hitpO-jbPjWMDP6Dai9Jjg
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Basic+Science+and+Pathogenesis&rft.jtitle=Alzheimer%27s+%26+dementia&rft.au=Kim%2C+Jin-Yang&rft.au=Song%2C+Yeong-Hun&rft.au=Lee%2C+Wha+Jin&rft.au=Seong%2C+Joon-Kyung&rft.date=2024-12-01&rft.eissn=1552-5279&rft.volume=20+Suppl+1&rft.spage=e092140&rft_id=info:doi/10.1002%2Falz.092140&rft_id=info%3Apmid%2F39751223&rft.externalDocID=39751223