The feasibility of K i parametric imaging in clinical dynamic 18 F‐FDG total‐body PET using a simulated‐data‐driven machine learning algorithm

Despite K parametric images providing high sensitivity and specificity in clinical diagnosis and therapeutic evaluation, their clinical application is limited by prolonged scan durations. Previous research has employed machine learning algorithms to generate reliable K images from F-FDG PET scans wi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Medical physics (Lancaster) Ročník 52; číslo 10; s. e70053
Hlavní autori: Gu, Wenjian, Liu, Weiping, Yang, Wentong, Wang, Yihan, Liu, Ze, Zhu, Zhanshi, Li, Yanxiao, Xu, Tianyi, Shi, Hongcheng, Wang, Kuanquan, Luo, Gongning, Chen, Xiaojun, Zhou, Yun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States 01.10.2025
Predmet:
ISSN:0094-2405, 2473-4209
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Despite K parametric images providing high sensitivity and specificity in clinical diagnosis and therapeutic evaluation, their clinical application is limited by prolonged scan durations. Previous research has employed machine learning algorithms to generate reliable K images from F-FDG PET scans with a duration of 10 min, but these algorithms require extensive real-world data for effective training. This study explored the feasibility of a simulated-data-driven approach for clinical K parametric imaging with reduced scan duration. A cluster analysis was conducted using K-Means on 60-minute dynamic total-body PET data from 25 subjects, followed by the construction of a noise-free simulated dataset using the Patlak equation. Subsequently, noise at varying levels was incorporated into the noise-free simulated dataset, resulting in four distinct training sets. Each dataset contains 1 200 000 simulated K values as labels, along with corresponding tissue-to-blood concentration ratios categorized by noise level (free, low, middle, and high). Based on the same simulation methodology, we also generated four corresponding test datasets at different noise levels (each with identical size to the training dataset). Ultimately, XGBoost models, each trained with data at different noise levels, were employed to predict K values from short-duration (50-60 min) PET scans. The accuracy of the K values generated from short-duration scans by our proposed method was evaluated using both simulated data (the four test datasets at varying noise levels) and real-world data (dynamic total-body PET data from 25 subjects). The K images generated by the conventional Patlak method with a t* of 20 min post-injection were chosen as the gold standard. Evaluation based on both simulated and real-world data indicates that training algorithms with a noise-inclusive simulated dataset significantly improve the average accuracy of K values. In evaluations with real-world data, K images from 50-60-minute dynamic PET scans generated using our proposed approach demonstrated superior performance compared to the conventional Patlak method, achieving a Pearson's correlation coefficient of 0.94 (vs. 0.42 for Patlak), a lower normalized mean square error of 0.11 (vs. 5.33), and a higher peak signal-to-noise ratio of 64.32 (vs. 47.87). The simulated-data-driven approach can generate reliable K images from clinical F-FDG dynamic total-body PET scans, thereby reducing the costs associated with collecting real-world data.
AbstractList Despite K parametric images providing high sensitivity and specificity in clinical diagnosis and therapeutic evaluation, their clinical application is limited by prolonged scan durations. Previous research has employed machine learning algorithms to generate reliable K images from F-FDG PET scans with a duration of 10 min, but these algorithms require extensive real-world data for effective training. This study explored the feasibility of a simulated-data-driven approach for clinical K parametric imaging with reduced scan duration. A cluster analysis was conducted using K-Means on 60-minute dynamic total-body PET data from 25 subjects, followed by the construction of a noise-free simulated dataset using the Patlak equation. Subsequently, noise at varying levels was incorporated into the noise-free simulated dataset, resulting in four distinct training sets. Each dataset contains 1 200 000 simulated K values as labels, along with corresponding tissue-to-blood concentration ratios categorized by noise level (free, low, middle, and high). Based on the same simulation methodology, we also generated four corresponding test datasets at different noise levels (each with identical size to the training dataset). Ultimately, XGBoost models, each trained with data at different noise levels, were employed to predict K values from short-duration (50-60 min) PET scans. The accuracy of the K values generated from short-duration scans by our proposed method was evaluated using both simulated data (the four test datasets at varying noise levels) and real-world data (dynamic total-body PET data from 25 subjects). The K images generated by the conventional Patlak method with a t* of 20 min post-injection were chosen as the gold standard. Evaluation based on both simulated and real-world data indicates that training algorithms with a noise-inclusive simulated dataset significantly improve the average accuracy of K values. In evaluations with real-world data, K images from 50-60-minute dynamic PET scans generated using our proposed approach demonstrated superior performance compared to the conventional Patlak method, achieving a Pearson's correlation coefficient of 0.94 (vs. 0.42 for Patlak), a lower normalized mean square error of 0.11 (vs. 5.33), and a higher peak signal-to-noise ratio of 64.32 (vs. 47.87). The simulated-data-driven approach can generate reliable K images from clinical F-FDG dynamic total-body PET scans, thereby reducing the costs associated with collecting real-world data.
Author Chen, Xiaojun
Shi, Hongcheng
Luo, Gongning
Yang, Wentong
Xu, Tianyi
Li, Yanxiao
Gu, Wenjian
Zhou, Yun
Liu, Weiping
Zhu, Zhanshi
Wang, Kuanquan
Wang, Yihan
Liu, Ze
Author_xml – sequence: 1
  givenname: Wenjian
  surname: Gu
  fullname: Gu, Wenjian
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, Faculty of Computing Harbin Institute of Technology Harbin China
– sequence: 2
  givenname: Weiping
  surname: Liu
  fullname: Liu, Weiping
  organization: Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China, United Imaging Healthcare Group Co., Ltd Shanghai China
– sequence: 3
  givenname: Wentong
  surname: Yang
  fullname: Yang, Wentong
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, ShanghaiTech University Shanghai China
– sequence: 4
  givenname: Yihan
  surname: Wang
  fullname: Wang, Yihan
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, ShanghaiTech University Shanghai China
– sequence: 5
  givenname: Ze
  surname: Liu
  fullname: Liu, Ze
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, ShanghaiTech University Shanghai China
– sequence: 6
  givenname: Zhanshi
  surname: Zhu
  fullname: Zhu, Zhanshi
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, Faculty of Computing Harbin Institute of Technology Harbin China
– sequence: 7
  givenname: Yanxiao
  surname: Li
  fullname: Li, Yanxiao
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China
– sequence: 8
  givenname: Tianyi
  surname: Xu
  fullname: Xu, Tianyi
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China
– sequence: 9
  givenname: Hongcheng
  surname: Shi
  fullname: Shi, Hongcheng
  organization: Department of Nuclear Medicine, Zhongshan Hospital Fudan University Shanghai China
– sequence: 10
  givenname: Kuanquan
  surname: Wang
  fullname: Wang, Kuanquan
  organization: Faculty of Computing Harbin Institute of Technology Harbin China
– sequence: 11
  givenname: Gongning
  surname: Luo
  fullname: Luo, Gongning
  organization: Faculty of Computing Harbin Institute of Technology Harbin China
– sequence: 12
  givenname: Xiaojun
  surname: Chen
  fullname: Chen, Xiaojun
  organization: Faculty of Computing Harbin Institute of Technology Harbin China
– sequence: 13
  givenname: Yun
  surname: Zhou
  fullname: Zhou, Yun
  organization: United Imaging Healthcare Group Co., Ltd Shanghai China, ShanghaiTech University Shanghai China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/41076590$$D View this record in MEDLINE/PubMed
BookMark eNo9kE1OwzAQRi1URH9A4gTISzYp4yR2kyUqbUFUgkX30dSZtEaxEzkpUnccgRUH5CSkLbD6RvrejDRvyHqucsTYtYCxAAjvbD2eAMjojA3CeBIFcQhpjw0A0jgIY5B9NmyaNwBQkYQL1o8FTJRMYcC-VlviBWFj1qY07Z5XBX_mhtfo0VLrjebG4sa4DTeO69I4o7Hk-d6h7TqR8Pn3x-f8YcHbqsWym9dVvuevsxXfNYct5I2xuxJbyrsyxxYP4c07OW5Rb40jXhJ6d4TLTeVNu7WX7LzAsqGr3xyx1Xy2mj4Gy5fF0_R-GWipIEBMRQ40wXWiVE4i0TGhpDQWhZBKaKE1hZjIREolcyh0ESmtpCoiIZTUFI3YzelsvVtbyrPad8_6ffbnpwNuT4D2VdN4Kv4RAdlBfWbr7Kg--gGKHnrA
Cites_doi 10.1145/1772690.1772862
10.1037/1528-3542.6.2.269
10.1016/j.tics.2007.05.005
10.1088/1361-6560/aad97f
10.1007/s00330-022-08960-8
10.1155/2007/65641
10.1088/1361-6560/ad9ce4
10.1145/2939672.2939785
10.1088/0031-9155/60/22/8643
10.1109/TMI.2021.3112783
10.1007/s00259-022-06010-5
10.1007/s00259-022-06003-4
10.1002/mp.15113
10.1006/nimg.2001.1021
10.3389/fradi.2023.1153784
10.1109/78.650093
10.1269/jrr.11089
10.1007/s00330-018-5966-1
10.1088/0031-9155/58/20/7391
10.1016/S1053-8119(03)00017-X
10.1007/s00259-023-06456-1
10.1007/s00259-022-05731-x
10.1007/s00330-022-09237-w
10.1007/s00259-018-4153-6
10.1007/s00259-022-05904-8
10.2967/jnumed.120.261651
10.1038/s41467-022-34257-x
10.1109/42.476111
10.1186/2191-219X-3-77
10.1109/TRPMS.2023.3243576
10.1007/s00259-022-05867-w
10.1007/s00259-023-06429-4
10.1007/s00259-023-06299-w
10.1162/neco.1997.9.8.1735
10.2967/jnumed.113.133892
10.1007/s11307-011-0514-2
10.1007/s00259-020-05134-w
10.1007/s00259-024-07008-x
10.1038/jcbfm.1983.1
10.1259/bjr.20170508
ContentType Journal Article
Copyright 2025 American Association of Physicists in Medicine.
Copyright_xml – notice: 2025 American Association of Physicists in Medicine.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
DOI 10.1002/mp.70053
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
DatabaseTitle CrossRef
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
Discipline Medicine
Physics
EISSN 2473-4209
ExternalDocumentID 41076590
10_1002_mp_70053
Genre Journal Article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62001144
– fundername: National Natural Science Foundation of China
  grantid: 62272135
– fundername: National Natural Science Foundation of China
  grantid: 62372135
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
53G
5GY
5RE
5VS
AAHQN
AAIPD
AAMMB
AAMNL
AANLZ
AAQQT
AASGY
AAXRX
AAYCA
AAYXX
AAZKR
ABCUV
ABDPE
ABEFU
ABJNI
ABLJU
ABQWH
ABUFD
ABXGK
ACAHQ
ACBEA
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADMLS
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AENEX
AEUYR
AEYWJ
AFBPY
AFFPM
AFWVQ
AGHNM
AGXDD
AGYGG
AHBTC
AIACR
AIAGR
AIDQK
AIDYY
AIQQE
AITYG
AIURR
ALMA_UNASSIGNED_HOLDINGS
ALVPJ
AMYDB
ASPBG
BFHJK
C45
CITATION
CS3
DCZOG
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMB
EMOBN
F5P
HDBZQ
HGLYW
I-F
KBYEO
LATKE
LEEKS
LH4
LOXES
LUTES
LYRES
MEWTI
O9-
OVD
P2P
P2W
PALCI
PHY
RJQFR
RNS
ROL
SAMSI
SUPJJ
SV3
TEORI
TN5
TWZ
USG
WOHZO
WXSBR
ZGI
ZVN
ZXP
ZY4
ZZTAW
ALUQN
CGR
CUY
CVF
ECM
EIF
NPM
XJT
ID FETCH-LOGICAL-c560-aa91d0e7ab866de18c4ea5e941f1561c1cce2a8585565d0fcf36c656f31165ce3
ISSN 0094-2405
IngestDate Mon Oct 13 01:41:30 EDT 2025
Thu Nov 20 00:55:27 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords total‐body PET
Patlak plot
machine learning
parametric image
18F‐FDG
Language English
License 2025 American Association of Physicists in Medicine.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c560-aa91d0e7ab866de18c4ea5e941f1561c1cce2a8585565d0fcf36c656f31165ce3
PMID 41076590
ParticipantIDs pubmed_primary_41076590
crossref_primary_10_1002_mp_70053
PublicationCentury 2000
PublicationDate 2025-10-00
2025-Oct
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-00
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2025
References e_1_2_8_28_1
e_1_2_8_29_1
e_1_2_8_24_1
e_1_2_8_25_1
e_1_2_8_46_1
e_1_2_8_26_1
e_1_2_8_27_1
e_1_2_8_3_1
e_1_2_8_2_1
e_1_2_8_5_1
e_1_2_8_4_1
e_1_2_8_7_1
e_1_2_8_6_1
e_1_2_8_9_1
e_1_2_8_8_1
e_1_2_8_20_1
e_1_2_8_43_1
e_1_2_8_21_1
e_1_2_8_42_1
e_1_2_8_22_1
e_1_2_8_45_1
e_1_2_8_23_1
e_1_2_8_44_1
e_1_2_8_41_1
e_1_2_8_40_1
e_1_2_8_17_1
e_1_2_8_18_1
e_1_2_8_39_1
e_1_2_8_19_1
e_1_2_8_13_1
e_1_2_8_36_1
e_1_2_8_14_1
e_1_2_8_35_1
e_1_2_8_15_1
e_1_2_8_16_1
e_1_2_8_37_1
Gu W (e_1_2_8_47_1) 2023; 64
Pedregosa F (e_1_2_8_33_1) 2011; 12
Wu Q (e_1_2_8_32_1) 2022; 63
Zhou Y (e_1_2_8_38_1) 2019; 60
e_1_2_8_10_1
e_1_2_8_31_1
e_1_2_8_11_1
e_1_2_8_34_1
e_1_2_8_12_1
e_1_2_8_30_1
References_xml – ident: e_1_2_8_34_1
  doi: 10.1145/1772690.1772862
– ident: e_1_2_8_22_1
  doi: 10.1037/1528-3542.6.2.269
– ident: e_1_2_8_23_1
  doi: 10.1016/j.tics.2007.05.005
– ident: e_1_2_8_10_1
  doi: 10.1088/1361-6560/aad97f
– ident: e_1_2_8_16_1
  doi: 10.1007/s00330-022-08960-8
– ident: e_1_2_8_45_1
  doi: 10.1155/2007/65641
– volume: 60
  start-page: 1186
  issue: 1
  year: 2019
  ident: e_1_2_8_38_1
  article-title: A machine learning‐based parametric imaging algorithm for noninvasive quantification of dynamic [68Ga] DOTATATE PET‐CT
  publication-title: J Nucl Med
– ident: e_1_2_8_40_1
  doi: 10.1088/1361-6560/ad9ce4
– ident: e_1_2_8_39_1
  doi: 10.1145/2939672.2939785
– ident: e_1_2_8_5_1
  doi: 10.1088/0031-9155/60/22/8643
– ident: e_1_2_8_37_1
  doi: 10.1109/TMI.2021.3112783
– ident: e_1_2_8_27_1
  doi: 10.1007/s00259-022-06010-5
– volume: 63
  start-page: 3184
  issue: 2
  year: 2022
  ident: e_1_2_8_32_1
  article-title: Impact of equilibration time (t*) on Patlak quantitation in dynamic total‐body imaging using the uEXPLORER PET scanner
  publication-title: J Nucl Med
– ident: e_1_2_8_19_1
  doi: 10.1007/s00259-022-06003-4
– ident: e_1_2_8_2_1
  doi: 10.1002/mp.15113
– ident: e_1_2_8_44_1
  doi: 10.1006/nimg.2001.1021
– ident: e_1_2_8_24_1
  doi: 10.3389/fradi.2023.1153784
– ident: e_1_2_8_42_1
  doi: 10.1109/78.650093
– ident: e_1_2_8_9_1
  doi: 10.1269/jrr.11089
– ident: e_1_2_8_12_1
  doi: 10.1007/s00330-018-5966-1
– ident: e_1_2_8_18_1
  doi: 10.1088/0031-9155/58/20/7391
– ident: e_1_2_8_43_1
  doi: 10.1016/S1053-8119(03)00017-X
– ident: e_1_2_8_26_1
  doi: 10.1007/s00259-023-06456-1
– ident: e_1_2_8_6_1
  doi: 10.1007/s00259-022-05731-x
– ident: e_1_2_8_15_1
  doi: 10.1007/s00330-022-09237-w
– ident: e_1_2_8_17_1
  doi: 10.1007/s00259-018-4153-6
– ident: e_1_2_8_28_1
  doi: 10.1007/s00259-022-05904-8
– ident: e_1_2_8_30_1
  doi: 10.2967/jnumed.120.261651
– ident: e_1_2_8_13_1
  doi: 10.1007/s00259-022-05904-8
– ident: e_1_2_8_25_1
  doi: 10.1038/s41467-022-34257-x
– ident: e_1_2_8_7_1
  doi: 10.1109/42.476111
– ident: e_1_2_8_36_1
  doi: 10.1186/2191-219X-3-77
– volume: 64
  start-page: 1611
  issue: 1
  year: 2023
  ident: e_1_2_8_47_1
  article-title: A machine learning‐based parametric imaging algorithm with shortened scanning duration for noninvasive quantification of total‐body dynamic [18F] FDG PET‐CT
  publication-title: J Nucl Med
– ident: e_1_2_8_21_1
  doi: 10.1109/TRPMS.2023.3243576
– ident: e_1_2_8_20_1
  doi: 10.1007/s00259-022-05867-w
– ident: e_1_2_8_14_1
  doi: 10.1007/s00259-023-06429-4
– ident: e_1_2_8_31_1
  doi: 10.1007/s00259-023-06299-w
– ident: e_1_2_8_41_1
  doi: 10.1162/neco.1997.9.8.1735
– ident: e_1_2_8_3_1
  doi: 10.2967/jnumed.113.133892
– ident: e_1_2_8_8_1
  doi: 10.1007/s11307-011-0514-2
– ident: e_1_2_8_46_1
  doi: 10.1007/s00259-020-05134-w
– volume: 12
  start-page: 2825
  year: 2011
  ident: e_1_2_8_33_1
  article-title: Scikit‐learn: machine learning in Python
  publication-title: J Mach Learn Res
– ident: e_1_2_8_35_1
  doi: 10.1007/s00259-024-07008-x
– ident: e_1_2_8_4_1
  doi: 10.1038/jcbfm.1983.1
– ident: e_1_2_8_11_1
  doi: 10.1259/bjr.20170508
– ident: e_1_2_8_29_1
  doi: 10.1007/s00259-023-06429-4
SSID ssj0006350
Score 2.4781914
Snippet Despite K parametric images providing high sensitivity and specificity in clinical diagnosis and therapeutic evaluation, their clinical application is limited...
SourceID pubmed
crossref
SourceType Index Database
StartPage e70053
SubjectTerms Algorithms
Feasibility Studies
Fluorodeoxyglucose F18
Humans
Image Processing, Computer-Assisted - methods
Machine Learning
Positron-Emission Tomography - methods
Whole Body Imaging - methods
Title The feasibility of K i parametric imaging in clinical dynamic 18 F‐FDG total‐body PET using a simulated‐data‐driven machine learning algorithm
URI https://www.ncbi.nlm.nih.gov/pubmed/41076590
Volume 52
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library - Journals
  customDbUrl:
  eissn: 2473-4209
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006350
  issn: 0094-2405
  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/eLvHCXMwtV1Lb9NAEF6FFhAXBOVVXhokbpbB7_UeEa2L1FBFKEA5Rc7uujWqnShNqnLjJ3DiL_E_-CXMPrxxKw7lwMVxJl4n8nyZnZn9doaQlzTgOM3GwqcSYxO0fqU_jVLho7qnOP3wMNPcnE9DenCQHx6y0WDwq9sLc3ZC2zY_P2fz_6pqlKGy1dbZf1C3uykK8ByVjkdUOx6vrPhKlpb2qhfQ973aUzW-G9U-i3t1Y1oTKQp6tzFSmM70Xph7hSNAFDt76Juie-4k05n45o12x95K5xhK77RuVAMwKdwlinO6frNQ1tRrNGVTdj0qcODJ0WxRL4-bvnPcLRqZbItOB6st2qVpHuIyFnsrTQyU7dcetIe1lape3EfOltlsOF6MPq4Tf7biL_WxvYPNe0SpY9A5W84StTZk1sSllkUJjf0kCljfvqdRH8fBX-cNU4e2mb-iyiqt58aOD3BpynRERlP0OZo084keeY1sRjRlaF43dz4UH4fOKUC_zuyGsj-6q4McRK-7b73gGV2IcbSvM75DbtsgBd4YcN0lA9lukZvvLQ1ji9wYGQ3dIz8RbdBDG8wq2Ica1mgDizaoW-jQBhZtEOZQ_P7-A3EGGmd4rhAGiDDQCIMSHMLwQ4Ut9aJRBRZV0KEKHKruk3GxO377zretPnyOLrdfliwUgaTlNM8yIcOcJ7JMJUvCKkQHn4dc9a1TS9gYf4ig4lWccYxEqlhVj-IyfkA22lkrHxGoUowZMWjhgtMky_g0yxgXIsvLWOK_hG2TF91TnsxNQZfJZS1uk4fm8bsrkjCgWcqCx1cY_YTcWuP1KdlYLlbyGbnOz5b16eK5BcYfJZ2dxw
linkProvider Wiley-Blackwell
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=The+feasibility+of+K+i+parametric+imaging+in+clinical+dynamic+18+F%E2%80%90FDG+total%E2%80%90body+PET+using+a+simulated%E2%80%90data%E2%80%90driven+machine+learning+algorithm&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Gu%2C+Wenjian&rft.au=Liu%2C+Weiping&rft.au=Yang%2C+Wentong&rft.au=Wang%2C+Yihan&rft.date=2025-10-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=52&rft.issue=10&rft_id=info:doi/10.1002%2Fmp.70053&rft.externalDBID=n%2Fa&rft.externalDocID=10_1002_mp_70053
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon