Deep learning‐based model for diagnosing Alzheimer's disease and tauopathies

Aims This study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau‐immunostained digital slide images. Methods We trai...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neuropathology and applied neurobiology Ročník 48; číslo 1; s. e12759 - n/a
Hlavní autoři: Koga, Shunsuke, Ikeda, Akihiro, Dickson, Dennis W.
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Wiley Subscription Services, Inc 01.02.2022
John Wiley and Sons Inc
Témata:
ISSN:0305-1846, 1365-2990, 1365-2990
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Aims This study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau‐immunostained digital slide images. Methods We trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13‐immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers. Results The resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13‐ and AT8‐stained slides. Conclusion Our diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision‐making in neuropathological diagnoses of tauopathies. We developed a deep learning‐based tool for diagnosing Alzheimer’s disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick’s disease (PiD), based on tau‐immunostained digital slide images. Combining an object detection model that could recognize and count five tau lesion types and a random forest classifier could successfully differentiate four tauopathies. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases showed >95% diagnostic accuracy in both CP13‐ and AT8‐stained slides.
AbstractList AimsThis study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau‐immunostained digital slide images.MethodsWe trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13‐immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers.ResultsThe resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13‐ and AT8‐stained slides.ConclusionOur diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision‐making in neuropathological diagnoses of tauopathies.
Aims This study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau‐immunostained digital slide images. Methods We trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13‐immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers. Results The resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13‐ and AT8‐stained slides. Conclusion Our diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision‐making in neuropathological diagnoses of tauopathies. We developed a deep learning‐based tool for diagnosing Alzheimer’s disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick’s disease (PiD), based on tau‐immunostained digital slide images. Combining an object detection model that could recognize and count five tau lesion types and a random forest classifier could successfully differentiate four tauopathies. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases showed >95% diagnostic accuracy in both CP13‐ and AT8‐stained slides.
We developed a deep learning‐based tool for diagnosing Alzheimer’s disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick’s disease (PiD), based on tau‐immunostained digital slide images. Combining an object detection model that could recognize and count five tau lesion types and a random forest classifier could successfully differentiate four tauopathies. A validation study using hold‐out datasets of CP13‐ and AT8‐stained slides from 50 cases showed >95% diagnostic accuracy in both CP13‐ and AT8‐stained slides.
This study aimed to develop a deep learning-based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau-immunostained digital slide images. We trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13-immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers. The resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold-out datasets of CP13- and AT8-stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13- and AT8-stained slides. Our diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision-making in neuropathological diagnoses of tauopathies.
This study aimed to develop a deep learning-based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau-immunostained digital slide images.AIMSThis study aimed to develop a deep learning-based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and Pick's disease (PiD), based on tau-immunostained digital slide images.We trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13-immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers.METHODSWe trained the YOLOv3 object detection algorithm to detect five tau lesion types: neuronal inclusions, neuritic plaques, tufted astrocytes, astrocytic plaques and coiled bodies. We used 2522 digital slide images of CP13-immunostained slides of the motor cortex from 10 cases each of AD, PSP and CBD for training. Data augmentation was performed to increase the size of the training dataset. We next constructed random forest classifiers using the quantitative burdens of each tau lesion from motor cortex, caudate nucleus and superior frontal gyrus, ascertained from the object detection model. We split 120 cases (32 AD, 36 PSP, 31 CBD and 21 PiD) into training (90 cases) and test (30 cases) sets to train random forest classifiers.The resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold-out datasets of CP13- and AT8-stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13- and AT8-stained slides.RESULTSThe resultant random forest classifier achieved an average test score of 0.97, indicating that 29 out of 30 cases were correctly diagnosed. A validation study using hold-out datasets of CP13- and AT8-stained slides from 50 cases (10 AD, 17 PSP, 13 CBD and 10 PiD) showed >92% (without data augmentation) and >95% (with data augmentation) diagnostic accuracy in both CP13- and AT8-stained slides.Our diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision-making in neuropathological diagnoses of tauopathies.CONCLUSIONOur diagnostic model trained with CP13 also works for AT8; therefore, our diagnostic tool can be potentially used by other investigators and may assist medical decision-making in neuropathological diagnoses of tauopathies.
Author Koga, Shunsuke
Dickson, Dennis W.
Ikeda, Akihiro
AuthorAffiliation 1 Department of Neuroscience Mayo Clinic Jacksonville FL USA
2 School of Medicine Osaka City University Osaka Japan
AuthorAffiliation_xml – name: 2 School of Medicine Osaka City University Osaka Japan
– name: 1 Department of Neuroscience Mayo Clinic Jacksonville FL USA
Author_xml – sequence: 1
  givenname: Shunsuke
  orcidid: 0000-0001-8868-9700
  surname: Koga
  fullname: Koga, Shunsuke
  email: koga.shunsuke@mayo.edu
  organization: Mayo Clinic
– sequence: 2
  givenname: Akihiro
  orcidid: 0000-0002-6158-130X
  surname: Ikeda
  fullname: Ikeda, Akihiro
  organization: Osaka City University
– sequence: 3
  givenname: Dennis W.
  orcidid: 0000-0001-7189-7917
  surname: Dickson
  fullname: Dickson, Dennis W.
  organization: Mayo Clinic
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34402107$$D View this record in MEDLINE/PubMed
BookMark eNp1kc1OGzEUha2KqgTaRV-gGqkL6GLAP2O73iBFFNpKKGzateV47iRGHju1Z6joqo_AM_IkGBKqgsAbS77fOTrXZwdthRgAofcEH5ByDoMJB4RKrl6hCWGC11QpvIUmmGFek8-N2EY7OV9gjLkU6g3aZk2DKcFygmZfAFaVB5OCC4ubv9dzk6Gt-tiCr7qYqtaZRYi5DKup_7ME10Pay-U5QyErE9pqMGNcmWHpIL9FrzvjM7zb3Lvo5-nJj-Nv9dn51-_H07PacqxUTTgWChqwTJlOzKVl0jYEqLBClD0a1iplVcM6yuRcgiTAOEgDrMNFCcB20dHadzXOe2gthCEZr1fJ9SZd6WicfjwJbqkX8VIrqhimvBjsbwxS_DVCHnTvsgXvTYA4Zk25oJRxeY9-fIJexDGFsp6mgmJMGkxkoT78n-hflIevLsDhGrAp5pyg09YNZnDxLqDzmmB9V6YuZer7Movi0xPFg-lz7Mb9t_Nw9TKoZ9PZWnELZJ-ulQ
CitedBy_id crossref_primary_10_1111_neup_12880
crossref_primary_10_1111_bpa_13207
crossref_primary_10_3390_app12010013
crossref_primary_10_1007_s11845_024_03721_6
crossref_primary_10_1136_jnnp_2021_328586
crossref_primary_10_1002_alz_14628
crossref_primary_10_1093_jnen_nlac127
crossref_primary_10_1002_alz_14626
crossref_primary_10_1007_s13042_025_02748_0
crossref_primary_10_1002_nbm_5323
crossref_primary_10_1080_19768354_2023_2285826
crossref_primary_10_1186_s40478_023_01584_z
crossref_primary_10_1002_mp_16218
crossref_primary_10_1016_j_heliyon_2024_e41137
crossref_primary_10_3390_brainsci15050486
crossref_primary_10_3390_s22124609
crossref_primary_10_1093_jnen_nlae048
crossref_primary_10_1093_jnen_nlaf098
crossref_primary_10_1002_nop2_1429
crossref_primary_10_1007_s40120_023_00526_0
crossref_primary_10_1016_j_ajpath_2024_12_018
crossref_primary_10_1111_bpa_13175
crossref_primary_10_1186_s40478_024_01827_7
crossref_primary_10_1007_s11831_022_09870_0
crossref_primary_10_1016_j_labinv_2023_100127
crossref_primary_10_1038_s41598_022_25385_x
crossref_primary_10_1093_jnen_nlaf108
crossref_primary_10_1093_jnen_nlaf047
crossref_primary_10_1111_nan_12997
crossref_primary_10_1038_s41598_023_28081_6
crossref_primary_10_1093_jnen_nlac094
crossref_primary_10_3389_fbinf_2025_1567219
crossref_primary_10_1097_ICU_0000000000000881
crossref_primary_10_1016_j_anndiagpath_2024_152392
crossref_primary_10_1038_s41598_023_45972_w
crossref_primary_10_1038_s41582_021_00562_0
crossref_primary_10_1016_j_asoc_2023_110804
crossref_primary_10_1186_s40478_023_01674_y
crossref_primary_10_1038_s42003_023_05031_6
crossref_primary_10_1111_bcpt_14003
Cites_doi 10.1093/jnen/61.11.935
10.1097/00005072-199710000-00002
10.1186/s13195-014-0085-y
10.1038/s41380-018-0342-8
10.1212/WNL.58.12.1791
10.1002/prot.24988
10.1093/brain/awm104
10.1212/WNL.44.11.2015
10.1002/mds.26809
10.1002/mds.27198
10.3389/fmed.2019.00185
10.2174/15672050113109990002
10.1007/s12031-011-9589-0
10.1007/s00401-019-02080-2
10.1371/journal.pone.0218808
10.1093/jnen/nlab005
10.1038/s41374-019-0202-4
10.1186/s40478-020-00927-4
10.1001/jamanetworkopen.2019.4337
10.3390/diagnostics9030072
10.1016/j.jalz.2011.04.011
10.1016/j.csbj.2018.01.001
10.1038/s41467-019-10212-1
10.1007/s00401-013-1171-0
10.1111/nan.12710
10.1001/archneur.58.11.1803
10.1186/s40478-020-01035-z
10.1007/s13246-020-00913-z
10.1097/00005072-199601000-00010
10.1016/j.ajpath.2019.05.007
10.1007/BF00308809
10.1111/nan.12208
10.1016/j.jalz.2018.06.3063
10.1007/s00401-020-02158-2
10.1007/s00702-017-1702-2
10.1007/s00401-018-1878-z
10.1093/brain/awx328
10.1038/s41551-020-0593-y
10.1109/CVPR.2016.91
10.4103/2153-3539.186902
ContentType Journal Article
Copyright 2021 The Authors. published by John Wiley & Sons Ltd on behalf of British Neuropathological Society.
2021 The Authors. Neuropathology and Applied Neurobiology published by John Wiley & Sons Ltd on behalf of British Neuropathological Society.
2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2021 The Authors. published by John Wiley & Sons Ltd on behalf of British Neuropathological Society.
– notice: 2021 The Authors. Neuropathology and Applied Neurobiology published by John Wiley & Sons Ltd on behalf of British Neuropathological Society.
– notice: 2021. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 24P
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7TK
K9.
7X8
5PM
DOI 10.1111/nan.12759
DatabaseName Wiley Online Library Open Access (Activated by CARLI)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Neurosciences Abstracts
ProQuest Health & Medical Complete (Alumni)
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
ProQuest Health & Medical Complete (Alumni)
Neurosciences Abstracts
MEDLINE - Academic
DatabaseTitleList ProQuest Health & Medical Complete (Alumni)


MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 24P
  name: Wiley - Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
DocumentTitleAlternate Deep learning‐based diagnostic model for tauopathies
EISSN 1365-2990
EndPage n/a
ExternalDocumentID PMC9293025
34402107
10_1111_nan_12759
NAN12759
Genre article
Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: Rainwater Charitable Trust
– fundername: Jaye F. and Betty F. Dyer Foundation
– fundername: CurePSP Foundation
– fundername: National Institutes of Health
  funderid: UG3 NS104095; R01 AG062348; U54 NS100693
– fundername: Mayo Clinic Foundation for Medical Research
– fundername: NIH HHS
  grantid: U54 NS100693
– fundername: NIH HHS
  grantid: UG3 NS104095
– fundername: NIH HHS
  grantid: R01 AG062348
– fundername: ;
– fundername: ;
  grantid: UG3 NS104095; R01 AG062348; U54 NS100693
GroupedDBID ---
.3N
.GA
.GJ
.Y3
05W
0R~
10A
123
1OB
1OC
24P
29N
31~
33P
36B
3SF
3UE
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5HH
5LA
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABEML
ABJNI
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACGFS
ACGOF
ACMXC
ACPOU
ACPRK
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AHEFC
AHMBA
AIACR
AITYG
AIURR
AIWBW
AJBDE
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CAG
COF
CS3
D-6
D-7
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
EAD
EAP
EAS
EBC
EBD
EBS
EBX
EJD
EMB
EMK
EMOBN
ESX
EX3
F00
F01
F04
F5P
FEDTE
FUBAC
G-S
G.N
GODZA
GSXLS
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
IHE
IX1
J0M
K48
KBYEO
L7B
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
Q~Q
R.K
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
SV3
TEORI
TUS
UB1
W8V
W99
WBKPD
WH7
WHWMO
WIH
WIJ
WIK
WOHZO
WOW
WQJ
WRC
WUP
WVDHM
WXI
WXSBR
XG1
YFH
ZGI
ZXP
ZZTAW
~IA
~WT
AAMMB
AAYXX
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
CGR
CUY
CVF
ECM
EIF
NPM
7TK
K9.
7X8
5PM
ID FETCH-LOGICAL-c5099-15069e4ec39af6b7c37c41e26c6627543d99c943f237b7e71e35e7ae3f0506ee3
IEDL.DBID 24P
ISICitedReferencesCount 40
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000693183200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0305-1846
1365-2990
IngestDate Tue Nov 04 02:00:53 EST 2025
Thu Oct 02 07:00:04 EDT 2025
Sat Nov 29 14:52:36 EST 2025
Mon Jul 21 05:59:05 EDT 2025
Sat Nov 29 06:09:48 EST 2025
Tue Nov 18 21:43:04 EST 2025
Wed Jan 22 16:26:11 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Pick's disease
random forest classifier
corticobasal degeneration
object detection
machine learning
Alzheimer's disease
progressive supranuclear palsy
Language English
License Attribution
2021 The Authors. Neuropathology and Applied Neurobiology published by John Wiley & Sons Ltd on behalf of British Neuropathological Society.
This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c5099-15069e4ec39af6b7c37c41e26c6627543d99c943f237b7e71e35e7ae3f0506ee3
Notes Funding information
Jaye F. and Betty F. Dyer Foundation; Rainwater Charitable Trust; CurePSP Foundation; National Institutes of Health, Grant/Award Numbers: UG3 NS104095, R01 AG062348, U54 NS100693; Mayo Clinic Foundation for Medical Research
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Correction added on 23 September 2021, after first online publication: Peer review history statement has been added.
Funding information Jaye F. and Betty F. Dyer Foundation; Rainwater Charitable Trust; CurePSP Foundation; National Institutes of Health, Grant/Award Numbers: UG3 NS104095, R01 AG062348, U54 NS100693; Mayo Clinic Foundation for Medical Research
ORCID 0000-0002-6158-130X
0000-0001-7189-7917
0000-0001-8868-9700
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fnan.12759
PMID 34402107
PQID 2620014017
PQPubID 1096364
PageCount 12
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_9293025
proquest_miscellaneous_2562235725
proquest_journals_2620014017
pubmed_primary_34402107
crossref_citationtrail_10_1111_nan_12759
crossref_primary_10_1111_nan_12759
wiley_primary_10_1111_nan_12759_NAN12759
PublicationCentury 2000
PublicationDate February 2022
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: February 2022
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: Oxford
– name: Hoboken
PublicationTitle Neuropathology and applied neurobiology
PublicationTitleAlternate Neuropathol Appl Neurobiol
PublicationYear 2022
Publisher Wiley Subscription Services, Inc
John Wiley and Sons Inc
Publisher_xml – name: Wiley Subscription Services, Inc
– name: John Wiley and Sons Inc
References 2018; 141
2002; 58
2019; 9
2019; 6
2020; 140
2019; 2
2019; 99
2019; 10
2013; 126
2019; 15
2019; 14
1994; 44
1991; 82
2011; 12
2011; 7
2019; 189
1996; 55
2020; 8
2016; 7
2020; 4
2013; 10
2002; 61
2021
2019; 24
2015; 41
2017; 32
2007; 130
1997; 56
2018; 136
2019
2020; 139
2018
2016; 84
2017; 140
2011; 45
2015
2020; 43
2017; 124
2001; 58
2014; 6
2018; 16
2021; 80
e_1_2_11_10_1
e_1_2_11_32_1
e_1_2_11_31_1
e_1_2_11_36_1
e_1_2_11_14_1
e_1_2_11_13_1
e_1_2_11_35_1
e_1_2_11_12_1
e_1_2_11_34_1
e_1_2_11_11_1
e_1_2_11_33_1
e_1_2_11_7_1
e_1_2_11_29_1
e_1_2_11_28_1
e_1_2_11_5_1
e_1_2_11_27_1
e_1_2_11_4_1
e_1_2_11_26_1
e_1_2_11_3_1
e_1_2_11_2_1
e_1_2_11_21_1
e_1_2_11_44_1
e_1_2_11_20_1
e_1_2_11_45_1
e_1_2_11_25_1
e_1_2_11_40_1
e_1_2_11_24_1
e_1_2_11_41_1
e_1_2_11_9_1
e_1_2_11_23_1
e_1_2_11_42_1
e_1_2_11_8_1
e_1_2_11_22_1
e_1_2_11_43_1
e_1_2_11_18_1
e_1_2_11_17_1
Pedregosa F (e_1_2_11_30_1) 2011; 12
e_1_2_11_16_1
e_1_2_11_15_1
e_1_2_11_37_1
e_1_2_11_38_1
Ono M (e_1_2_11_6_1) 2017; 140
e_1_2_11_39_1
e_1_2_11_19_1
34475569 - Nat Rev Neurol. 2021 Oct;17(10):595
References_xml – volume: 99
  start-page: 1019
  issue: 7
  year: 2019
  end-page: 1029
  article-title: Artificial intelligence in neuropathology: deep learning‐based assessment of tauopathy
  publication-title: Lab Invest
– volume: 140
  start-page: 764
  issue: 3
  year: 2017
  end-page: 780
  article-title: Distinct binding of PET ligands PBB3 and AV‐1451 to tau fibril strains in neurodegenerative tauopathies
  publication-title: Brain
– volume: 130
  start-page: 1566
  issue: 6
  year: 2007
  end-page: 1576
  article-title: Pathological tau burden and distribution distinguishes progressive supranuclear palsy‐parkinsonism from Richardson's syndrome
  publication-title: Brain
– volume: 6
  start-page: 185
  year: 2019
  article-title: Translational AI and deep learning in diagnostic pathology
  publication-title: Front Med (Lausanne)
– volume: 24
  start-page: 1112
  issue: 8
  year: 2019
  end-page: 1134
  article-title: Tau PET imaging in neurodegenerative tauopathies‐still a challenge
  publication-title: Mol Psychiatry
– volume: 12
  start-page: 2825
  year: 2011
  end-page: 2830
  article-title: Scikit‐learn: machine learning in Python
  publication-title: J Mach Learn Res
– volume: 80
  start-page: 306
  issue: 4
  year: 2021
  end-page: 312
  article-title: Deep learning‐based image classification in differentiating tufted astrocytes, astrocytic plaques, and neuritic plaques
  publication-title: J Neuropathol Exp Neurol
– volume: 140
  start-page: 99
  issue: 2
  year: 2020
  end-page: 119
  article-title: Distribution patterns of tau pathology in progressive supranuclear palsy
  publication-title: Acta Neuropathol
– volume: 136
  start-page: 389
  issue: 3
  year: 2018
  end-page: 404
  article-title: Corticobasal degeneration with TDP‐43 pathology presenting with progressive supranuclear palsy syndrome: a distinct clinicopathologic subtype
  publication-title: Acta Neuropathol
– volume: 7
  start-page: 486
  issue: 4
  year: 2011
  end-page: 489
  article-title: How golden is the gold standard of neuropathology in dementia?
  publication-title: Alzheimers Dement
– volume: 189
  start-page: 1686
  issue: 9
  year: 2019
  end-page: 1698
  article-title: Pathology image analysis using segmentation deep learning algorithms
  publication-title: Am J Pathol
– volume: 2
  issue: 5
  year: 2019
  article-title: Trends in the US and Canadian Pathologist Workforces From 2007 to 2017
  publication-title: JAMA Netw Open
– year: 2021
  article-title: Machine learning‐based decision tree classifier for the diagnosis of progressive supranuclear palsy and corticobasal degeneration
  publication-title: Neuropathol Appl Neurobiol
– volume: 10
  start-page: 569
  issue: 6
  year: 2013
  end-page: 577
  article-title: Neuropathological correlates of cerebral multimorbidity
  publication-title: Curr Alzheimer Res
– volume: 8
  start-page: 59
  issue: 1
  year: 2020
  article-title: Validation of machine learning models to detect amyloid pathologies across institutions
  publication-title: Acta Neuropathol Commun
– volume: 4
  start-page: 787
  issue: 8
  year: 2020
  end-page: 800
  article-title: Defining and predicting transdiagnostic categories of neurodegenerative disease
  publication-title: Nat Biomed Eng
– volume: 58
  start-page: 1803
  issue: 11
  year: 2001
  end-page: 1809
  article-title: Clinical and pathological diagnosis of frontotemporal dementia: report of the Work Group on Frontotemporal Dementia and Pick's Disease
  publication-title: Arch Neurol
– volume: 14
  issue: 6
  year: 2019
  article-title: Deep learning approach to peripheral leukocyte recognition
  publication-title: PLoS One
– volume: 55
  start-page: 97
  issue: 1
  year: 1996
  end-page: 105
  article-title: Validity and reliability of the preliminary NINDS neuropathologic criteria for progressive supranuclear palsy and related disorders
  publication-title: J Neuropathol Exp Neurol
– year: 2018
– volume: 16
  start-page: 34
  year: 2018
  end-page: 42
  article-title: Machine learning methods for histopathological image analysis
  publication-title: Comput Struct Biotechnol J
– volume: 32
  start-page: 246
  issue: 2
  year: 2017
  end-page: 255
  article-title: Distribution and characteristics of transactive response DNA binding protein 43 kDa pathology in progressive supranuclear palsy
  publication-title: Mov Disord
– volume: 8
  start-page: 162
  issue: 1
  year: 2020
  article-title: Associations of mitochondrial genomic variation with corticobasal degeneration, progressive supranuclear palsy, and neuropathological tau measures
  publication-title: Acta Neuropathol Commun
– volume: 9
  start-page: 72
  year: 2019
  article-title: Skin lesion segmentation in dermoscopic images with combination of YOLO and GrabCut Algorithm
  publication-title: Diagnostics (Basel)
– volume: 32
  start-page: 1772
  issue: 12
  year: 2017
  end-page: 1779
  article-title: Cognitive impairment in progressive supranuclear palsy is associated with tau burden
  publication-title: Mov Disord
– volume: 41
  start-page: 3
  issue: 1
  year: 2015
  end-page: 23
  article-title: Invited review: neuropathology of tauopathies: principles and practice
  publication-title: Neuropathol Appl Neurobiol
– volume: 84
  start-page: 427
  issue: 4
  year: 2016
  end-page: 434
  article-title: Epitope mapping and structural basis for the recognition of phosphorylated tau by the anti‐tau antibody AT8
  publication-title: Proteins
– volume: 139
  start-page: 63
  issue: 1
  year: 2020
  end-page: 77
  article-title: 4‐Repeat tau seeds and templating subtypes as brain and CSF biomarkers of frontotemporal lobar degeneration
  publication-title: Acta Neuropathol
– volume: 56
  start-page: 1095
  issue: 10
  year: 1997
  end-page: 1097
  article-title: Consensus recommendations for the postmortem diagnosis of Alzheimer disease from the National Institute on Aging and the Reagan Institute Working Group on diagnostic criteria for the neuropathological assessment of Alzheimer disease
  publication-title: J Neuropathol Exp Neurol
– volume: 45
  start-page: 384
  issue: 3
  year: 2011
  end-page: 389
  article-title: Neuropathology of frontotemporal lobar degeneration‐tau (FTLD‐tau)
  publication-title: J Mol Neurosci
– volume: 6
  start-page: 85
  issue: 9
  year: 2014
  article-title: Quantitative neuropathological assessment to investigate cerebral multi‐morbidity
  publication-title: Alzheimers Res Ther
– volume: 58
  start-page: 1791
  issue: 12
  year: 2002
  end-page: 1800
  article-title: Phases of A beta‐deposition in the human brain and its relevance for the development of AD
  publication-title: Neurology
– volume: 61
  start-page: 935
  issue: 11
  year: 2002
  end-page: 946
  article-title: Office of rare diseases neuropathologic criteria for corticobasal degeneration
  publication-title: J Neuropathol Exp Neurol
– volume: 7
  start-page: 29
  issue: 1
  year: 2016
  article-title: Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases
  publication-title: J Pathol Inform
– volume: 10
  start-page: 2173
  issue: 1
  year: 2019
  article-title: Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline
  publication-title: Nat Commun
– volume: 82
  start-page: 239
  issue: 4
  year: 1991
  end-page: 259
  article-title: Neuropathological stageing of Alzheimer‐related changes
  publication-title: Acta Neuropathol
– volume: 15
  start-page: 17
  issue: 1
  year: 2019
  end-page: 24
  article-title: Racial and ethnic estimates of Alzheimer's disease and related dementias in the United States (2015‐2060) in adults aged >/=65 years
  publication-title: Alzheimers Dement
– volume: 43
  start-page: 1135
  issue: 3
  year: 2020
  end-page: 1136
  article-title: Hands‐on machine learning with Scikit‐Learn, Keras, and Tensorflow, 2nd edition
  publication-title: Phys Eng Sci Med
– year: 2019
– volume: 126
  start-page: 537
  issue: 4
  year: 2013
  end-page: 544
  article-title: Globular glial tauopathies (GGT): consensus recommendations
  publication-title: Acta Neuropathol
– volume: 141
  start-page: 521
  issue: 2
  year: 2018
  end-page: 534
  article-title: Retiring the term FTDP‐17 as MAPT mutations are genetic forms of sporadic frontotemporal tauopathies
  publication-title: Brain
– year: 2015
– volume: 124
  start-page: 671
  issue: 6
  year: 2017
  end-page: 683
  article-title: Quantitative neuropathology: an update on automated methodologies and implications for large scale cohorts
  publication-title: J Neural Transm (Vienna)
– volume: 44
  start-page: 2015
  issue: 11
  year: 1994
  end-page: 2019
  article-title: Preliminary NINDS neuropathologic criteria for Steele‐Richardson‐Olszewski syndrome (progressive supranuclear palsy)
  publication-title: Neurology
– ident: e_1_2_11_7_1
  doi: 10.1093/jnen/61.11.935
– ident: e_1_2_11_9_1
  doi: 10.1097/00005072-199710000-00002
– ident: e_1_2_11_35_1
  doi: 10.1186/s13195-014-0085-y
– ident: e_1_2_11_4_1
  doi: 10.1038/s41380-018-0342-8
– ident: e_1_2_11_22_1
  doi: 10.1212/WNL.58.12.1791
– ident: e_1_2_11_33_1
  doi: 10.1002/prot.24988
– ident: e_1_2_11_37_1
  doi: 10.1093/brain/awm104
– ident: e_1_2_11_8_1
  doi: 10.1212/WNL.44.11.2015
– ident: e_1_2_11_43_1
  doi: 10.1002/mds.26809
– volume: 12
  start-page: 2825
  year: 2011
  ident: e_1_2_11_30_1
  article-title: Scikit‐learn: machine learning in Python
  publication-title: J Mach Learn Res
– ident: e_1_2_11_40_1
  doi: 10.1002/mds.27198
– ident: e_1_2_11_42_1
  doi: 10.3389/fmed.2019.00185
– ident: e_1_2_11_34_1
  doi: 10.2174/15672050113109990002
– ident: e_1_2_11_10_1
  doi: 10.1007/s12031-011-9589-0
– ident: e_1_2_11_5_1
  doi: 10.1007/s00401-019-02080-2
– ident: e_1_2_11_28_1
  doi: 10.1371/journal.pone.0218808
– ident: e_1_2_11_19_1
  doi: 10.1093/jnen/nlab005
– ident: e_1_2_11_17_1
  doi: 10.1038/s41374-019-0202-4
– ident: e_1_2_11_12_1
  doi: 10.1186/s40478-020-00927-4
– ident: e_1_2_11_15_1
  doi: 10.1001/jamanetworkopen.2019.4337
– ident: e_1_2_11_27_1
  doi: 10.3390/diagnostics9030072
– volume: 140
  start-page: 764
  issue: 3
  year: 2017
  ident: e_1_2_11_6_1
  article-title: Distinct binding of PET ligands PBB3 and AV‐1451 to tau fibril strains in neurodegenerative tauopathies
  publication-title: Brain
– ident: e_1_2_11_13_1
  doi: 10.1016/j.jalz.2011.04.011
– ident: e_1_2_11_16_1
  doi: 10.1016/j.csbj.2018.01.001
– ident: e_1_2_11_18_1
  doi: 10.1038/s41467-019-10212-1
– ident: e_1_2_11_23_1
  doi: 10.1007/s00401-013-1171-0
– ident: e_1_2_11_20_1
  doi: 10.1111/nan.12710
– ident: e_1_2_11_24_1
  doi: 10.1001/archneur.58.11.1803
– ident: e_1_2_11_39_1
  doi: 10.1186/s40478-020-01035-z
– ident: e_1_2_11_32_1
  doi: 10.1007/s13246-020-00913-z
– ident: e_1_2_11_14_1
  doi: 10.1097/00005072-199601000-00010
– ident: e_1_2_11_29_1
  doi: 10.1016/j.ajpath.2019.05.007
– ident: e_1_2_11_31_1
– ident: e_1_2_11_21_1
  doi: 10.1007/BF00308809
– ident: e_1_2_11_2_1
  doi: 10.1111/nan.12208
– ident: e_1_2_11_3_1
  doi: 10.1016/j.jalz.2018.06.3063
– ident: e_1_2_11_38_1
  doi: 10.1007/s00401-020-02158-2
– ident: e_1_2_11_25_1
– ident: e_1_2_11_41_1
  doi: 10.1007/s00702-017-1702-2
– ident: e_1_2_11_44_1
  doi: 10.1007/s00401-018-1878-z
– ident: e_1_2_11_45_1
  doi: 10.1093/brain/awx328
– ident: e_1_2_11_36_1
  doi: 10.1038/s41551-020-0593-y
– ident: e_1_2_11_26_1
  doi: 10.1109/CVPR.2016.91
– ident: e_1_2_11_11_1
  doi: 10.4103/2153-3539.186902
– reference: 34475569 - Nat Rev Neurol. 2021 Oct;17(10):595
SSID ssj0005769
Score 2.5401819
Snippet Aims This study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear...
This study aimed to develop a deep learning-based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy...
AimsThis study aimed to develop a deep learning‐based model for differentiating tauopathies, including Alzheimer's disease (AD), progressive supranuclear palsy...
We developed a deep learning‐based tool for diagnosing Alzheimer’s disease (AD), progressive supranuclear palsy (PSP), corticobasal degeneration (CBD) and...
SourceID pubmedcentral
proquest
pubmed
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage e12759
SubjectTerms Alzheimer Disease - diagnosis
Alzheimer Disease - pathology
Alzheimer's disease
Astrocytes
Caudate nucleus
Cortex (motor)
corticobasal degeneration
Decision making
Deep Learning
Degeneration
Frontal gyrus
Humans
machine learning
Neurodegenerative diseases
Niemann-Pick disease
object detection
Original
Paralysis
Pick Disease of the Brain - pathology
Pick's disease
Progressive supranuclear palsy
random forest classifier
Senile plaques
Supranuclear Palsy, Progressive - pathology
Tau protein
tau Proteins
Tauopathies - diagnosis
Tauopathies - pathology
Title Deep learning‐based model for diagnosing Alzheimer's disease and tauopathies
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fnan.12759
https://www.ncbi.nlm.nih.gov/pubmed/34402107
https://www.proquest.com/docview/2620014017
https://www.proquest.com/docview/2562235725
https://pubmed.ncbi.nlm.nih.gov/PMC9293025
Volume 48
WOSCitedRecordID wos000693183200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1365-2990
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0005769
  issn: 0305-1846
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTtwwEB7xJ8QFWmjLAkUuQoJLqiR21htxWgGrHiBCCKS9RY4zhpVoFm12OXDiEfqMfRI8TjawAqRKvUSJPE4se8aeicffB7Af-cK0M869jooyT-g88DpGC88IFeTKJ8Ju48gmZJJ0-v34Yg6OpmdhKnyI5ocbWYabr8nAVVa-MvJCFT8JnTyeh8Ug4JJUOhQXL_kd0vHZkUJ7Noxp17BClMbTVJ1djN54mG8TJV87sG4F6q39V9s_wWrteLJupSmfYQ6LdVg-r7fWNyA5QbxnNYnEzd-nP7S-5cwx5TDr2bK8Ssqzhax793iLg984OihZvcPDVJGzsZoMHcUxll_gund6dfzLq8kWPB0RSichDcYoUPNY2dGTmkstAgzb2kHEC57HsY4FNyGXmUQZII9QKuTGtzUR-VdYKIYFbgLLfBMaK0FzhVBh2z7zKDC-DrXRJhItOJz2eqprJHIixLhLpxGJ7Z_U9U8L9hrR-wp-4z2hnenQpbUFlikB7bvoUbbgR1NsbYc2RFSBw4mVsc4fwf2EUQu-VSPdfIULQeGwrS1ndKARIFzu2ZJicOvwua3HyX1656HTgY8bnibdxN1s_bvoNqyEdALDJY7vwMJ4NMHvsKQfxoNytOtMwF5lv7MLiyeXveuzZ36QDMk
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTtwwEB7BUlEuFAqFpfy4FVK5pEpiZ72RelmVrqi6RFUFErfI64zLSpBF-9NDT32EPiNPgsfxpqygEhK3RB4nlj1jz9jj7wM4TEJhWn3Og7ZK-oHQRRS0jRaBESoqVEiE3caRTcgsa19cpN8X4NPsLkyFD1FvuJFluPmaDJw2pO9ZeanKjwRPni7CkrBqlDRg6fhH97z3L8VDOko70unARjItjyxEmTx15fn16IGT-TBX8r4P6xah7qvnNX8NVr3zyTqVtqzDApavYfnUH69vQHaMeMM8kcTP2z9_aY0rmGPLYda7ZUWVmGcLWefq9yUOrnH0Ycz8KQ9TZcEmajp0NMc43oTz7pezzyeBJ1wIdEJInYQ2mKJAzVNlR1BqLrWIMG5pBxMveJGmOhXcxFz2JcoIeYJSITehrYnI30CjHJa4DawfmthYCZovhIpb9p0nkQl1rI02iWjC0azbc-3RyIkU4yqfRSW2f3LXP014X4veVBAcjwntzsYu91Y4zgls30WQsgnv6mJrP3QookocTq2MdQAJ8idOmrBVDXX9Fy4EhcS2tpxTglqAsLnnS8rBpcPotl4nD-mbR04J_t_wPOtk7mHn6aIH8PLk7LSX975m397CSkw3Mlwi-S40JqMp7sEL_WsyGI_2vUXcAYaLD74
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1fT9swED91DCFexoAxCgwMmgQvQUns1I3ES7WuAgFRH0DiLXKdM1RiadU_e-CJj7DPuE-Cz0kDFUNC2lsinxPLvrPv7PPvB_A98oVp9Dj3mirqeUJngdc0WnhGqCBTPhF2G0c2IZOkeXMTd2twMrsLU-BDVBtuZBluviYDx2FmXlh5rvJjgiePP8BHEdk5lnCdRfc5wUM6QjvSaM_GMY0SV4jyeKqq86vRKxfzdabkSw_WLUGdlf9r_Gf4VLqerFXoyirUMF-DpcvycH0dkjbikJU0Erd_H__QCpcxx5XDrG_LsiItzxay1v3DHfZ_4ehwzMozHqbyjE3UdOBIjnH8Ba47P69-nHol3YKnI8LpJKzBGAVqHis7flJzqUWAYUM7kHjBszjWseAm5LInUQbII5QKufFtTUS-AQv5IMdNYD3fhMZK0GwhVNiw7zwKjK9DbbSJRB2OZt2e6hKLnCgx7tNZTGL7J3X9U4eDSnRYAHD8S2hnNnZpaYPjlKD2Xfwo67BfFVvroSMRleNgamWs-0eAP2FUh6_FUFd_4UJQQGxryzklqAQImXu-JO_fOYRu63Nyn7555JTg7YanSStxD1vvF92DpW67k16cJefbsBzSdQyXRb4DC5PRFL_Bov496Y9Hu84cngAwXQ2n
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=Deep+learning-based+model+for+diagnosing+Alzheimer%27s+disease+and+tauopathies&rft.jtitle=Neuropathology+and+applied+neurobiology&rft.au=Koga%2C+Shunsuke&rft.au=Ikeda%2C+Akihiro&rft.au=Dickson%2C+Dennis+W&rft.date=2022-02-01&rft.eissn=1365-2990&rft.volume=48&rft.issue=1&rft.spage=e12759&rft_id=info:doi/10.1111%2Fnan.12759&rft_id=info%3Apmid%2F34402107&rft.externalDocID=34402107
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0305-1846&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0305-1846&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0305-1846&client=summon