Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development

The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recomme...

Full description

Saved in:
Bibliographic Details
Published inJournal of Nuclear Medicine Vol. 63; no. 4; pp. 500 - 510
Main Authors Bradshaw, Tyler J., Boellaard, Ronald, Dutta, Joyita, Jha, Abhinav K., Jacobs, Paul, Li, Quanzheng, Liu, Chi, Sitek, Arkadiusz, Saboury, Babak, Scott, Peter J.H., Slomka, Piotr J., Sunderland, John J., Wahl, Richard L., Yousefirizi, Fereshteh, Zuehlsdorff, Sven, Rahmim, Arman, Buvat, Irène
Format Journal Article
LanguageEnglish
Published United States Society of Nuclear Medicine 01.04.2022
Subjects
Algorithms
Artificial Intelligence
Best practice
Life Sciences
Molecular Imaging
Nuclear Medicine
Radionuclide Imaging
The State of The Art
research methods
computer/PACS
artificial intelligence
best practices
algorithm
statistics
Deep learning
Machine learning
Research Methods
Artificial intelligence
Statistics
Algorithm
Best practices
Computer/PACS
Online AccessGet full text
ISSN0161-5505
1535-5667
2159-662X
2159-662X
1535-5667
DOI10.2967/jnumed.121.262567

Cover

Abstract The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.
AbstractList The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.
The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations on technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations and then continuing with descriptions of how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.
The nuclear medicine field has seen a rapid expansion of academic and commercial interests in developing artificial intelligence (AI) algorithms. Users and developers can avoid some of the pitfalls of AI by recognizing and following best practices in AI algorithm development. In this article, recommendations for technical best practices for developing AI algorithms in nuclear medicine are provided, beginning with general recommendations followed by descriptions on how one might practice these principles for specific topics within nuclear medicine. This report was produced by the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging.
Author Rahmim, Arman
Buvat, Irène
Jacobs, Paul
Slomka, Piotr J.
Bradshaw, Tyler J.
Li, Quanzheng
Sitek, Arkadiusz
Scott, Peter J.H.
Dutta, Joyita
Wahl, Richard L.
Yousefirizi, Fereshteh
Liu, Chi
Boellaard, Ronald
Jha, Abhinav K.
Saboury, Babak
Zuehlsdorff, Sven
Sunderland, John J.
Author_xml – sequence: 1
  givenname: Tyler J.
  surname: Bradshaw
  fullname: Bradshaw, Tyler J.
– sequence: 2
  givenname: Ronald
  surname: Boellaard
  fullname: Boellaard, Ronald
– sequence: 3
  givenname: Joyita
  surname: Dutta
  fullname: Dutta, Joyita
– sequence: 4
  givenname: Abhinav K.
  surname: Jha
  fullname: Jha, Abhinav K.
– sequence: 5
  givenname: Paul
  surname: Jacobs
  fullname: Jacobs, Paul
– sequence: 6
  givenname: Quanzheng
  surname: Li
  fullname: Li, Quanzheng
– sequence: 7
  givenname: Chi
  surname: Liu
  fullname: Liu, Chi
– sequence: 8
  givenname: Arkadiusz
  surname: Sitek
  fullname: Sitek, Arkadiusz
– sequence: 9
  givenname: Babak
  surname: Saboury
  fullname: Saboury, Babak
– sequence: 10
  givenname: Peter J.H.
  surname: Scott
  fullname: Scott, Peter J.H.
– sequence: 11
  givenname: Piotr J.
  surname: Slomka
  fullname: Slomka, Piotr J.
– sequence: 12
  givenname: John J.
  surname: Sunderland
  fullname: Sunderland, John J.
– sequence: 13
  givenname: Richard L.
  surname: Wahl
  fullname: Wahl, Richard L.
– sequence: 14
  givenname: Fereshteh
  surname: Yousefirizi
  fullname: Yousefirizi, Fereshteh
– sequence: 15
  givenname: Sven
  surname: Zuehlsdorff
  fullname: Zuehlsdorff, Sven
– sequence: 16
  givenname: Arman
  surname: Rahmim
  fullname: Rahmim, Arman
– sequence: 17
  givenname: Irène
  surname: Buvat
  fullname: Buvat, Irène
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34740952$$D View this record in MEDLINE/PubMed
https://inserm.hal.science/inserm-03441110$$DView record in HAL
BookMark eNqFkUtv1DAUhS3Uik4LP4ANisSGBRlsx3ZiNmjog1YaHosKsbNc52bGI8ce7GRQ_31dpVCYBawsy-ccn_vdY3TggweEXhA8p1LUbzd-7KGdE0rmVFAu6idoRgmXpRD0-wGaYSJIyTnmR-g4pQ3GWDRN8xQdVaxmWHI6Q98-j8aBjsUnaK2xHgrt22IRB9vlq3bFlR_AObsCb-Bd8QHSUHyN2gzWQCq6EIuFW4Voh3VfnMEOXNj24Idn6LDTLsHzh_MEXV-cX59elssvH69OF8vSMMGHsmHAectlq5kRRGpjoCVtSzuo6xuAikElQLCm1oLXgjNpNKfQUqw7U3e6OkF0ih39Vt_-1M6pbbS9jreKYHXPSE2MVGakJkbZ9H4ybceb_GRy3agfjUFb9feLt2u1CrscKZkkBOeEN1PCes93uVgq6xPEXuGKMZLFO5Llrx8-jOHHmAmq3iaTqWoPYUyKcslyV85Elr7ak27CGH1GmNtz0jCZd5pVL_-c4HeFX2vNgnoSmBhSitApYwc92HA_kHX_hEP2nP8HegfiBMpt
CitedBy_id crossref_primary_10_1016_j_neunet_2023_08_026
crossref_primary_10_1016_j_xcrm_2024_101463
crossref_primary_10_1080_09553002_2023_2214206
crossref_primary_10_2967_jnumed_123_266110
crossref_primary_10_1038_s41571_023_00799_2
crossref_primary_10_1097_RLU_0000000000005526
crossref_primary_10_1055_a_2140_7831
crossref_primary_10_1080_08164622_2023_2197578
crossref_primary_10_3390_cancers14071674
crossref_primary_10_1002_mp_16967
crossref_primary_10_2967_jnumed_124_267924
crossref_primary_10_1080_14737159_2024_2383439
crossref_primary_10_1088_1361_6560_ac6fab
crossref_primary_10_1093_ageing_afae101
crossref_primary_10_1186_s40658_023_00598_9
crossref_primary_10_2967_jnumed_121_263703
crossref_primary_10_1007_s00259_024_06616_x
crossref_primary_10_2967_jnumed_121_263501
crossref_primary_10_3390_cancers16061090
crossref_primary_10_1007_s00259_023_06152_0
crossref_primary_10_1021_acs_molpharmaceut_2c00830
crossref_primary_10_1148_ryai_220232
crossref_primary_10_1109_ACCESS_2023_3244741
crossref_primary_10_1186_s41181_023_00218_y
crossref_primary_10_1200_JCO_24_00675
crossref_primary_10_1007_s00259_022_05891_w
crossref_primary_10_2967_jnumed_124_267570
crossref_primary_10_1007_s13246_024_01408_x
crossref_primary_10_3390_diagnostics14020181
crossref_primary_10_1136_bmj_2024_081554
crossref_primary_10_1016_j_pdpdt_2025_104528
crossref_primary_10_1097_MNM_0000000000001723
crossref_primary_10_1007_s11547_024_01770_6
crossref_primary_10_2967_jnumed_123_266080
crossref_primary_10_1053_j_semnuclmed_2022_11_003
crossref_primary_10_1111_all_15849
crossref_primary_10_1016_S1470_2045_24_00030_5
crossref_primary_10_3390_jcm13010117
crossref_primary_10_1016_j_ejmp_2023_102615
crossref_primary_10_1055_a_2157_6810
crossref_primary_10_3389_fphar_2023_1173596
crossref_primary_10_1016_j_compbiomed_2022_106165
crossref_primary_10_2967_jnumed_121_263239
crossref_primary_10_3390_diagnostics14121240
crossref_primary_10_1055_a_1909_7013
crossref_primary_10_1093_bjr_tqae235
Cites_doi 10.1002/mp.14684
10.1109/TRPMS.2018.2884320
10.2967/jnumed.120.242412
10.1016/j.ophtha.2018.01.034
10.1088/1361-6560/ab8535
10.1016/S2589-7500(20)30219-3
10.1088/1361-6560/abcd17
10.1038/s42256-021-00307-0
10.1016/j.radonc.2018.10.027
10.1038/s41570-019-0124-0
10.1117/12.2582765
10.1186/s41824-020-00086-8
10.1109/JBHI.2020.2991043
10.1016/j.jcmg.2020.07.015
10.1371/journal.pone.0238455
10.1148/ryai.2020190137
10.1016/S0140-6736(19)30037-6
10.1088/1361-6560/abb6bd
10.1148/ryai.2020200137
10.1117/12.2582350
10.1038/s41598-019-54190-2
10.1186/s40658-021-00374-7
10.1038/s41586-020-2766-y
10.1109/JPROC.2019.2936809
10.1016/j.jclinepi.2019.02.004
10.1109/TMI.2004.828354
10.1136/bmj.m441
10.1016/j.neuron.2017.12.018
10.1007/978-3-030-67194-5_1
10.1038/s41591-020-1034-x
10.1093/ajhp/zxaa218
10.2967/jnumed.118.213538
10.1007/s12021-018-9377-x
10.1073/pnas.1708274114
10.1093/jamia/ocaa088
10.1148/ryai.2020200016
10.1038/s41591-020-01192-7
10.1109/TRPMS.2020.3014786
10.2967/jnumed.121.262283
10.1088/1361-6560/ab3242
10.1186/s13550-021-00751-4
10.1038/s41591-020-1041-y
10.2967/jnumed.117.202317
10.1186/s40658-020-00346-3
10.1016/j.media.2020.101746
10.2967/jnumed.120.261586
10.1038/s41591-020-0941-1
10.1038/s41598-017-10371-5
10.1214/09-SS054
10.1021/acs.jcim.9b00325
10.1001/jama.2016.17216
10.1148/radiol.2019192515
10.1021/acs.jproteome.6b00618
10.1016/j.media.2019.03.009
10.1038/s41591-021-01229-5
10.18632/oncotarget.17856
10.1371/journal.pmed.1002683
10.1002/mp.12124
ContentType Journal Article
Copyright 2022 by the Society of Nuclear Medicine and Molecular Imaging.
Copyright Society of Nuclear Medicine Apr 1, 2022
Distributed under a Creative Commons Attribution 4.0 International License
2022 by the Society of Nuclear Medicine and Molecular Imaging. 2022
Copyright_xml – notice: 2022 by the Society of Nuclear Medicine and Molecular Imaging.
– notice: Copyright Society of Nuclear Medicine Apr 1, 2022
– notice: Distributed under a Creative Commons Attribution 4.0 International License
– notice: 2022 by the Society of Nuclear Medicine and Molecular Imaging. 2022
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
4T-
8FD
FR3
K9.
M7Z
NAPCQ
P64
7X8
1XC
5PM
ADTOC
UNPAY
DOI 10.2967/jnumed.121.262567
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Docstoc
Technology Research Database
Engineering Research Database
ProQuest Health & Medical Complete (Alumni)
Biochemistry Abstracts 1
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
Hyper Article en Ligne (HAL)
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Nursing & Allied Health Premium
Technology Research Database
Docstoc
Biochemistry Abstracts 1
ProQuest Health & Medical Complete (Alumni)
Engineering Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList Nursing & Allied Health Premium
MEDLINE - Academic

MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2159-662X
1535-5667
EndPage 510
ExternalDocumentID 10.2967/jnumed.121.262567
PMC10949110
oai:HAL:inserm-03441110v1
34740952
10_2967_jnumed_121_262567
Genre Journal Article
GrantInformation_xml – fundername: NIA NIH HHS
  grantid: R01 AG072669
– fundername: NIA NIH HHS
  grantid: R03 AG070750
GroupedDBID 123
18M
41~
5VS
96U
AAYXX
ACGFO
AEGXH
AIAGR
ALMA_UNASSIGNED_HOLDINGS
CITATION
GX1
N9A
RHI
TSM
U5U
W8F
---
-~X
.55
.GJ
29L
2WC
3O-
3V.
53G
5RE
7RV
7X7
88E
88I
8AF
8AO
8FE
8FG
8FH
8FI
8FJ
8R4
8R5
8WZ
A6W
ABEFU
ABSQV
ABUWG
ACGOD
ACIWK
ACPRK
ADDZX
ADMOG
AENEX
AFFNX
AFKRA
AFOSN
AFRAH
AHMBA
AI.
ALIPV
ARAPS
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
BKEYQ
BPHCQ
BVXVI
CCPQU
CGR
CS3
CUY
CVF
DIK
DU5
DWQXO
E3Z
EBD
EBS
ECM
EIF
EJD
EMOBN
EX3
F5P
F9R
FYUFA
GNUQQ
H13
HCIFZ
HMCUK
I-F
IL9
INIJC
J5H
KQ8
L7B
LK8
M1P
M2P
M2Q
M7P
N4W
NAPCQ
NPM
OK1
P2P
P62
PQQKQ
PROAC
PSQYO
Q2X
R0Z
RHF
RNS
RWL
S0X
SJN
SV3
TAE
TR2
TUS
UKHRP
VH1
WH7
WOQ
WOW
X7M
YHG
YQJ
ZGI
ZXP
4T-
8FD
FR3
K9.
M7Z
P64
7X8
1XC
5PM
ADTOC
UNPAY
ID FETCH-LOGICAL-c465t-84e55d59da4c619acced1dd2fe77bee34e36e6487a6576549ca52ed20afc7fa3
IEDL.DBID UNPAY
ISSN 0161-5505
1535-5667
2159-662X
IngestDate Sun Oct 26 04:09:37 EDT 2025
Thu Aug 21 18:34:49 EDT 2025
Tue Oct 14 20:45:36 EDT 2025
Fri Sep 05 09:55:09 EDT 2025
Tue Oct 07 05:13:46 EDT 2025
Wed Feb 19 02:05:11 EST 2025
Tue Jul 01 02:06:59 EDT 2025
Thu Apr 24 23:05:33 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords research methods
computer/PACS
artificial intelligence
best practices
algorithm
statistics
Deep learning
Machine learning
Research Methods
Artificial intelligence
Statistics
Algorithm
Best practices
Computer/PACS
Language English
License 2022 by the Society of Nuclear Medicine and Molecular Imaging.
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c465t-84e55d59da4c619acced1dd2fe77bee34e36e6487a6576549ca52ed20afc7fa3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Published online November 05, 2021.
ORCID 0000-0002-7306-2590
0000-0002-9651-5820
0000-0001-6932-2233
0000-0002-9980-2403
OpenAccessLink https://proxy.k.utb.cz/login?url=https://jnm.snmjournals.org/content/jnumed/63/4/500.full.pdf
PMID 34740952
PQID 2651849016
PQPubID 40808
PageCount 11
ParticipantIDs unpaywall_primary_10_2967_jnumed_121_262567
pubmedcentral_primary_oai_pubmedcentral_nih_gov_10949110
hal_primary_oai_HAL_inserm_03441110v1
proquest_miscellaneous_2594296546
proquest_journals_2651849016
pubmed_primary_34740952
crossref_citationtrail_10_2967_jnumed_121_262567
crossref_primary_10_2967_jnumed_121_262567
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2022-04-01
PublicationDateYYYYMMDD 2022-04-01
PublicationDate_xml – month: 04
  year: 2022
  text: 2022-04-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle Journal of Nuclear Medicine
PublicationTitleAlternate J Nucl Med
PublicationYear 2022
Publisher Society of Nuclear Medicine
Publisher_xml – name: Society of Nuclear Medicine
References Roberts (2022042908200985000_63.4.500.1) 2021; 3
Hatt (2022042908200985000_63.4.500.49) 2017; 44
Panayides (2022042908200985000_63.4.500.58) 2020; 24
2022042908200985000_63.4.500.9
2022042908200985000_63.4.500.8
DECIDE-AI Steering Group (2022042908200985000_63.4.500.34) 2021; 27
2022042908200985000_63.4.500.39
2022042908200985000_63.4.500.4
2022042908200985000_63.4.500.7
2022042908200985000_63.4.500.6
Weisman (2022042908200985000_63.4.500.43) 2020; 7
2022042908200985000_63.4.500.35
Müller (2022042908200985000_63.4.500.63) 2019; 3
2022042908200985000_63.4.500.3
2022042908200985000_63.4.500.33
2022042908200985000_63.4.500.2
2022042908200985000_63.4.500.54
Arabi (2022042908200985000_63.4.500.61) 2020; 4
2022042908200985000_63.4.500.51
2022042908200985000_63.4.500.52
2022042908200985000_63.4.500.50
Huff (2022042908200985000_63.4.500.26) 2021; 66
Weisman (2022042908200985000_63.4.500.45) 2020; 2
Leung (2022042908200985000_63.4.500.47) 2020; 65
Gong (2022042908200985000_63.4.500.62) 2020; 108
de Almeida (2022042908200985000_63.4.500.64) 2019; 3
Zhao (2022042908200985000_63.4.500.21) 2020; 15
Steinkamp (2022042908200985000_63.4.500.59) 2020; 2
Whiteley (2022042908200985000_63.4.500.38) 2020; 7
Lu (2022042908200985000_63.4.500.41) 2019; 64
Katsari (2022042908200985000_63.4.500.40) 2021; 8
Xue (2022042908200985000_63.4.500.5) 2018; 16
Ståhl (2022042908200985000_63.4.500.67) 2019; 59
Nelson (2022042908200985000_63.4.500.65) 2020; 77
2022042908200985000_63.4.500.48
2022042908200985000_63.4.500.44
2022042908200985000_63.4.500.20
2022042908200985000_63.4.500.60
Reader (2022042908200985000_63.4.500.37) 2021; 5
Li (2022042908200985000_63.4.500.55) 2021; 11
Dirand (2022042908200985000_63.4.500.10) 2019; 9
Cruz Rivera (2022042908200985000_63.4.500.27) 2020; 2
2022042908200985000_63.4.500.19
Weisman (2022042908200985000_63.4.500.46) 2020; 65
2022042908200985000_63.4.500.17
2022042908200985000_63.4.500.15
2022042908200985000_63.4.500.16
Bluemke (2022042908200985000_63.4.500.57) 2020; 294
2022042908200985000_63.4.500.13
2022042908200985000_63.4.500.14
2022042908200985000_63.4.500.11
2022042908200985000_63.4.500.12
2022042908200985000_63.4.500.56
2022042908200985000_63.4.500.31
2022042908200985000_63.4.500.32
2022042908200985000_63.4.500.30
Pfaehler (2022042908200985000_63.4.500.53) 2021; 48
Yu (2022042908200985000_63.4.500.42) 2020; 61
Zhu (2022042908200985000_63.4.500.18) 2020; 64
Li (2022042908200985000_63.4.500.24) 2020; 37
Yang (2022042908200985000_63.4.500.25) 2020; 3
2022042908200985000_63.4.500.28
2022042908200985000_63.4.500.29
Reuzé (2022042908200985000_63.4.500.36) 2017; 8
2022042908200985000_63.4.500.68
2022042908200985000_63.4.500.69
2022042908200985000_63.4.500.22
2022042908200985000_63.4.500.66
2022042908200985000_63.4.500.23
References_xml – volume: 48
  start-page: 1226
  year: 2021
  ident: 2022042908200985000_63.4.500.53
  article-title: Plausibility and redundancy analysis to select FDG-PET textural features in non-small cell lung cancer
  publication-title: Med Phys.
  doi: 10.1002/mp.14684
– volume: 3
  start-page: 465
  year: 2019
  ident: 2022042908200985000_63.4.500.63
  article-title: A novel DOI positioning algorithm for monolithic scintillator crystals in PET based on gradient tree boosting
  publication-title: IEEE Trans Radiat Plasma Med Sci.
  doi: 10.1109/TRPMS.2018.2884320
– ident: 2022042908200985000_63.4.500.44
  doi: 10.2967/jnumed.120.242412
– ident: 2022042908200985000_63.4.500.16
  doi: 10.1016/j.ophtha.2018.01.034
– volume: 65
  start-page: 245032
  year: 2020
  ident: 2022042908200985000_63.4.500.47
  article-title: A physics-guided modular deep-learning based automated framework for tumor segmentation in PET
  publication-title: Phys Med Biol.
  doi: 10.1088/1361-6560/ab8535
– volume: 2
  start-page: e549
  year: 2020
  ident: 2022042908200985000_63.4.500.27
  article-title: Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension
  publication-title: Lancet Digit Health.
  doi: 10.1016/S2589-7500(20)30219-3
– ident: 2022042908200985000_63.4.500.19
– volume: 66
  start-page: 04TR01
  year: 2021
  ident: 2022042908200985000_63.4.500.26
  article-title: Interpretation and visualization techniques for deep learning models in medical imaging
  publication-title: Phys Med Biol.
  doi: 10.1088/1361-6560/abcd17
– volume: 3
  start-page: 199
  year: 2021
  ident: 2022042908200985000_63.4.500.1
  article-title: Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans
  publication-title: Nat Mach Intell.
  doi: 10.1038/s42256-021-00307-0
– ident: 2022042908200985000_63.4.500.54
  doi: 10.1016/j.radonc.2018.10.027
– volume: 3
  start-page: 589
  year: 2019
  ident: 2022042908200985000_63.4.500.64
  article-title: Synthetic organic chemistry driven by artificial intelligence
  publication-title: Nat Rev Chem.
  doi: 10.1038/s41570-019-0124-0
– ident: 2022042908200985000_63.4.500.50
  doi: 10.1117/12.2582765
– volume: 4
  start-page: 17
  year: 2020
  ident: 2022042908200985000_63.4.500.61
  article-title: Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy
  publication-title: Eur J Hybrid Imaging.
  doi: 10.1186/s41824-020-00086-8
– volume: 24
  start-page: 1837
  year: 2020
  ident: 2022042908200985000_63.4.500.58
  article-title: AI in medical imaging informatics: current challenges and future directions
  publication-title: IEEE J Biomed Health Inform.
  doi: 10.1109/JBHI.2020.2991043
– ident: 2022042908200985000_63.4.500.30
  doi: 10.1016/j.jcmg.2020.07.015
– volume: 15
  start-page: e0238455
  year: 2020
  ident: 2022042908200985000_63.4.500.21
  article-title: Study of low-dose PET image recovery using supervised learning with CycleGAN
  publication-title: PLoS One.
  doi: 10.1371/journal.pone.0238455
– volume: 2
  start-page: e190137
  year: 2020
  ident: 2022042908200985000_63.4.500.59
  article-title: Evaluation of automated public de-identification tools on a corpus of radiology reports
  publication-title: Radiol Artif Intell.
  doi: 10.1148/ryai.2020190137
– volume: 37
  start-page: 50
  year: 2020
  ident: 2022042908200985000_63.4.500.24
  article-title: Federated learning: challenges, methods, and future directions
  publication-title: IEEE Signal Process Mag.
– ident: 2022042908200985000_63.4.500.33
  doi: 10.1016/S0140-6736(19)30037-6
– volume: 65
  start-page: 235019
  year: 2020
  ident: 2022042908200985000_63.4.500.46
  article-title: Comparison of 11 automated PET segmentation methods in lymphoma
  publication-title: Phys Med Biol.
  doi: 10.1088/1361-6560/abb6bd
– ident: 2022042908200985000_63.4.500.22
– volume: 3
  start-page: e200137
  year: 2020
  ident: 2022042908200985000_63.4.500.25
  article-title: CT-less direct correction of attenuation and scatter in the image space using deep learning for whole-body FDG PET: potential benefits and pitfalls
  publication-title: Radiol Artif Intell.
  doi: 10.1148/ryai.2020200137
– ident: 2022042908200985000_63.4.500.39
  doi: 10.1117/12.2582350
– volume: 9
  start-page: 17869
  year: 2019
  ident: 2022042908200985000_63.4.500.10
  article-title: A downsampling strategy to assess the predictive value of radiomic features
  publication-title: Sci Rep.
  doi: 10.1038/s41598-019-54190-2
– volume: 7
  start-page: 032503
  year: 2020
  ident: 2022042908200985000_63.4.500.38
  article-title: DirectPET: full-size neural network PET reconstruction from sinogram data
  publication-title: J Med Imaging (Bellingham).
– volume: 8
  start-page: 25
  year: 2021
  ident: 2022042908200985000_63.4.500.40
  article-title: Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment
  publication-title: EJNMMI Phys.
  doi: 10.1186/s40658-021-00374-7
– ident: 2022042908200985000_63.4.500.2
  doi: 10.1038/s41586-020-2766-y
– volume: 108
  start-page: 51
  year: 2020
  ident: 2022042908200985000_63.4.500.62
  article-title: Machine learning in PET: from photon detection to quantitative image reconstruction
  publication-title: Proc IEEE.
  doi: 10.1109/JPROC.2019.2936809
– ident: 2022042908200985000_63.4.500.20
  doi: 10.1016/j.jclinepi.2019.02.004
– ident: 2022042908200985000_63.4.500.68
– ident: 2022042908200985000_63.4.500.48
  doi: 10.1109/TMI.2004.828354
– ident: 2022042908200985000_63.4.500.11
  doi: 10.1136/bmj.m441
– ident: 2022042908200985000_63.4.500.52
– ident: 2022042908200985000_63.4.500.12
  doi: 10.1016/j.neuron.2017.12.018
– ident: 2022042908200985000_63.4.500.7
  doi: 10.1007/978-3-030-67194-5_1
– ident: 2022042908200985000_63.4.500.28
  doi: 10.1038/s41591-020-1034-x
– volume: 77
  start-page: 1556
  year: 2020
  ident: 2022042908200985000_63.4.500.65
  article-title: Demystifying artificial intelligence in pharmacy
  publication-title: Am J Health Syst Pharm.
  doi: 10.1093/ajhp/zxaa218
– ident: 2022042908200985000_63.4.500.56
  doi: 10.2967/jnumed.118.213538
– volume: 16
  start-page: 383
  year: 2018
  ident: 2022042908200985000_63.4.500.5
  article-title: Segan: adversarial network with multi-scale L1 loss for medical image segmentation
  publication-title: Neuroinformatics.
  doi: 10.1007/s12021-018-9377-x
– ident: 2022042908200985000_63.4.500.9
  doi: 10.1073/pnas.1708274114
– ident: 2022042908200985000_63.4.500.31
  doi: 10.1093/jamia/ocaa088
– volume: 2
  start-page: e200016
  year: 2020
  ident: 2022042908200985000_63.4.500.45
  article-title: Convolutional neural networks for automated PET/CT detection of diseased lymph node burden in patients with lymphoma
  publication-title: Radiol Artif Intell.
  doi: 10.1148/ryai.2020200016
– ident: 2022042908200985000_63.4.500.51
  doi: 10.1038/s41591-020-01192-7
– volume: 5
  start-page: 1
  year: 2021
  ident: 2022042908200985000_63.4.500.37
  article-title: D, Costa-Luis C, Ellis S, Schnabel JA. Deep learning for PET image reconstruction
  publication-title: IEEE Trans Radiat Plasma Med Sci.
  doi: 10.1109/TRPMS.2020.3014786
– ident: 2022042908200985000_63.4.500.60
  doi: 10.2967/jnumed.121.262283
– volume: 64
  start-page: 165019
  year: 2019
  ident: 2022042908200985000_63.4.500.41
  article-title: An investigation of quantitative accuracy for deep learning based denoising in oncological PET
  publication-title: Phys Med Biol.
  doi: 10.1088/1361-6560/ab3242
– volume: 11
  start-page: 10
  year: 2021
  ident: 2022042908200985000_63.4.500.55
  article-title: Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer
  publication-title: EJNMMI Res.
  doi: 10.1186/s13550-021-00751-4
– ident: 2022042908200985000_63.4.500.29
  doi: 10.1038/s41591-020-1041-y
– ident: 2022042908200985000_63.4.500.13
  doi: 10.2967/jnumed.117.202317
– ident: 2022042908200985000_63.4.500.69
– volume: 7
  start-page: 76
  year: 2020
  ident: 2022042908200985000_63.4.500.43
  article-title: Automated quantification of baseline imaging PET metrics on FDG PET/CT images of pediatric Hodgkin lymphoma patients
  publication-title: EJNMMI Phys.
  doi: 10.1186/s40658-020-00346-3
– volume: 64
  start-page: 101746
  year: 2020
  ident: 2022042908200985000_63.4.500.18
  article-title: Rubik’s Cube+: a self-supervised feature learning framework for 3D medical image analysis
  publication-title: Med Image Anal.
  doi: 10.1016/j.media.2020.101746
– ident: 2022042908200985000_63.4.500.4
  doi: 10.2967/jnumed.120.261586
– volume: 61
  start-page: 575
  year: 2020
  ident: 2022042908200985000_63.4.500.42
  article-title: AI-based methods for nuclear-medicine imaging: need for objective task-specific evaluation [abstract]
  publication-title: J Nucl Med.
– ident: 2022042908200985000_63.4.500.32
  doi: 10.1038/s41591-020-0941-1
– ident: 2022042908200985000_63.4.500.6
  doi: 10.1038/s41598-017-10371-5
– ident: 2022042908200985000_63.4.500.23
  doi: 10.1214/09-SS054
– volume: 59
  start-page: 3166
  year: 2019
  ident: 2022042908200985000_63.4.500.67
  article-title: Deep reinforcement learning for multiparameter optimization in de novo drug design
  publication-title: J Chem Inf Model.
  doi: 10.1021/acs.jcim.9b00325
– ident: 2022042908200985000_63.4.500.15
  doi: 10.1001/jama.2016.17216
– volume: 294
  start-page: 487
  year: 2020
  ident: 2022042908200985000_63.4.500.57
  article-title: Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers—from the Radiology editorial board
  publication-title: Radiology.
  doi: 10.1148/radiol.2019192515
– ident: 2022042908200985000_63.4.500.66
  doi: 10.1021/acs.jproteome.6b00618
– ident: 2022042908200985000_63.4.500.17
  doi: 10.1016/j.media.2019.03.009
– ident: 2022042908200985000_63.4.500.35
– volume: 27
  start-page: 186
  year: 2021
  ident: 2022042908200985000_63.4.500.34
  article-title: DECIDE-AI: new reporting guidelines to bridge the development-to-implementation gap in clinical artificial intelligence
  publication-title: Nat Med.
  doi: 10.1038/s41591-021-01229-5
– ident: 2022042908200985000_63.4.500.14
– volume: 8
  start-page: 43169
  year: 2017
  ident: 2022042908200985000_63.4.500.36
  article-title: Prediction of cervical cancer recurrence using textural features extracted from 18F-FDG PET images acquired with different scanners
  publication-title: Oncotarget.
  doi: 10.18632/oncotarget.17856
– ident: 2022042908200985000_63.4.500.3
  doi: 10.1371/journal.pmed.1002683
– ident: 2022042908200985000_63.4.500.8
– volume: 44
  start-page: e1
  year: 2017
  ident: 2022042908200985000_63.4.500.49
  article-title: Classification and evaluation strategies of auto-segmentation approaches for PET: report of AAPM task group no. 211
  publication-title: Med Phys.
  doi: 10.1002/mp.12124
SSID ssj0006888
ssj0062072
Score 2.6002262
Snippet The nuclear medicine field has seen a rapid expansion of academic and commercial interest in developing artificial intelligence (AI) algorithms. Users and...
The nuclear medicine field has seen a rapid expansion of academic and commercial interests in developing artificial intelligence (AI) algorithms. Users and...
SourceID unpaywall
pubmedcentral
hal
proquest
pubmed
crossref
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 500
SubjectTerms Algorithms
Artificial Intelligence
Best practice
Life Sciences
Molecular Imaging
Nuclear Medicine
Radionuclide Imaging
The State of The Art
Title Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development
URI https://www.ncbi.nlm.nih.gov/pubmed/34740952
https://www.proquest.com/docview/2651849016
https://www.proquest.com/docview/2594296546
https://inserm.hal.science/inserm-03441110
https://pubmed.ncbi.nlm.nih.gov/PMC10949110
https://jnm.snmjournals.org/content/jnumed/63/4/500.full.pdf
UnpaywallVersion publishedVersion
Volume 63
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 2159-662X
  dateEnd: 20250502
  omitProxy: true
  ssIdentifier: ssj0006888
  issn: 0161-5505
  databaseCode: KQ8
  dateStart: 19640101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVBFR
  databaseName: Free Medical Journals
  customDbUrl:
  eissn: 2159-662X
  dateEnd: 20241102
  omitProxy: true
  ssIdentifier: ssj0006888
  issn: 0161-5505
  databaseCode: DIK
  dateStart: 19640101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 2159-662X
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0062072
  issn: 0161-5505
  databaseCode: GX1
  dateStart: 0
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEB616QEuPMTLUCojwQVkx17vrhPEJSCqFGjUQ4vCAVn7MgkkmyhxQPDrmfWLhEogOFo7fqxnxjOfd-ZbgMdpHGsuqQliEcuA5okKZCLSQBn0LqZiKqlrTj4d8eEFfTNm4z140fTCfLbzcG3n9Ytcl2v5rmgbv8A4hu6quzzp0i6LotD9oA6XOt-HA84wE-_AwcXobPDB7SeHUTrgnIyrhUzS52l9uqNTCAlm_eXO8r9C0f7EFUJezjIvF0te2dil-P5NzGZbkej4Onxs5lAVoHwJN4UM1Y_f6B3_d5I34FqdovqDyqZuwp6xt-D9yBEfi5V_Wi_G-8LqUqaioPBPtrg9n_svcXL-Wd2BtfYxM_YHs0-L1bSYzP2tQqXbcH78-vzVMKj3ZAgU5awIetQwpllfC6oQewmljI61JrlJU2lMQk3CDUcUJDgiGQSfSjBiNIlErtJcJHegYxfW3AOfxz3ZdwRhIkdQR7Q0Ok806Uk8zlMhPYga7WSq5it322bMMsQtTqFZ9aoyVGhWKdSDp-0py4qs40_CT1DlrZyj2R4O3mVTi64_zxwTIoaB6GvswWFjFFmjMbwEQ2iMuRT34FE7jJ7plluENYsNyrA-BnvXLObB3cqG2rslNEVgzYgHvR3r2nmc3RE7nZTs3zECcoxQkQfPWkP8-2zv_5P0A7hKXJtHWaF0CJ1itTEPMfkq5BHCjpO3R7Wn_QR0LjVh
linkProvider Unpaywall
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEB616QEuPMSjbgtaJLiA7Pixu04Ql4CoAqJRDy0KB2TtyySQbKLEAcGvZ9YvEiqB4Gjt-LGeGc983plvAR6nUaS5pMaPRCR9mifKl4lIfWXQu5iKqKSuOflsxIeX9O2YjffgRdML89nOg7Wd1y9yXa7lu6Jt_ALjGLqr7vKkS7ssDAP3gzpY6nwfDjjDTLwDB5ej88EHt58cRmmf83hcLWTGfZ7Wpzs6hSDGrL_cWf5XKNqfuELIq1nm1WLJaxu7FN-_idlsKxKd3oSPzRyqApQvwaaQgfrxG73j_07yFtyoU1QyqGzqNuwZewfejxzxsViRs3oxngirS5mKgoK82eL2fE5e4uTIed2BtSaYGZPB7NNiNS0mc7JVqHQXLk5fX7wa-vWeDL6inBV-jxrGNOtrQRViL6GU0ZHWcW7SVBqTUJNwwxEFCY5IBsGnEiw2Og5FrtJcJPegYxfWHALhUU_2HUGYyBHUxVoanSc67kk8zlMhPQgb7WSq5it322bMMsQtTqFZ9aoyVGhWKdSDp-0py4qs40_CT1DlrZyj2R4O3mVTi64_zxwTIoaB8GvkwUljFFmjMbwEQ2iMuRT34FE7jJ7plluENYsNyrA-BnvXLObB_cqG2rslNEVgzWIPejvWtfM4uyN2OinZvyME5BihQg-etYb499ke_ZP0MVyPXZtHWaF0Ap1itTEPMPkq5MPax34COZ40aA
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=Nuclear+Medicine+and+Artificial+Intelligence%3A+Best+Practices+for+Algorithm+Development&rft.jtitle=The+Journal+of+nuclear+medicine+%281978%29&rft.au=Bradshaw%2C+Tyler+J&rft.au=Boellaard%2C+Ronald&rft.au=Dutta%2C+Joyita&rft.au=Jha%2C+Abhinav+K&rft.date=2022-04-01&rft.issn=1535-5667&rft.eissn=1535-5667&rft.volume=63&rft.issue=4&rft.spage=500&rft_id=info:doi/10.2967%2Fjnumed.121.262567&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0161-5505&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0161-5505&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0161-5505&client=summon