Multi-phase features interaction transformer network for liver tumor segmentation and microvascular invasion assessment in contrast-enhanced CT

Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation mo...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Mathematical biosciences and engineering : MBE Ročník 21; číslo 4; s. 5735 - 5761
Hlavní autori: Zhang, Wencong, Tao, Yuxi, Huang, Zhanyao, Li, Yue, Chen, Yingjia, Song, Tengfei, Ma, Xiangyuan, Zhang, Yaqin
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States AIMS Press 24.04.2024
Predmet:
Algorithms
Contrast Media
contrast-enhanced ct
Female
Humans
Image Processing, Computer-Assisted - methods
Liver - blood supply
Liver - diagnostic imaging
Liver - pathology
Liver Neoplasms - blood supply
Liver Neoplasms - diagnostic imaging
Liver Neoplasms - pathology
liver tumor segmentation
Male
Microvessels - diagnostic imaging
Microvessels - pathology
multi-phase
Neoplasm Invasiveness
Radiographic Image Interpretation, Computer-Assisted - methods
Tomography, X-Ray Computed
transformer
liver tumor segmentation
transformer
contrast-enhanced CT
multi-phase
ISSN:1551-0018, 1551-0018
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.
AbstractList Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.
Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.
Author Zhang, Wencong
Huang, Zhanyao
Ma, Xiangyuan
Song, Tengfei
Li, Yue
Chen, Yingjia
Zhang, Yaqin
Tao, Yuxi
Author_xml – sequence: 1
  givenname: Wencong
  surname: Zhang
  fullname: Zhang, Wencong
  organization: Department of Biomedical Engineering, College of Engineering, Shantou University, Shantou, China, Department of Biomedical Engineering, College of Design and Engineering, National University of Singapore, Singapore
– sequence: 2
  givenname: Yuxi
  surname: Tao
  fullname: Tao, Yuxi
  organization: Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
– sequence: 3
  givenname: Zhanyao
  surname: Huang
  fullname: Huang, Zhanyao
  organization: Department of Biomedical Engineering, College of Engineering, Shantou University, Shantou, China
– sequence: 4
  givenname: Yue
  surname: Li
  fullname: Li, Yue
  organization: School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
– sequence: 5
  givenname: Yingjia
  surname: Chen
  fullname: Chen, Yingjia
  organization: Department of Biomedical Engineering, College of Engineering, Shantou University, Shantou, China
– sequence: 6
  givenname: Tengfei
  surname: Song
  fullname: Song, Tengfei
  organization: Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
– sequence: 7
  givenname: Xiangyuan
  surname: Ma
  fullname: Ma, Xiangyuan
  organization: Department of Biomedical Engineering, College of Engineering, Shantou University, Shantou, China
– sequence: 8
  givenname: Yaqin
  surname: Zhang
  fullname: Zhang, Yaqin
  organization: Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38872556$$D View this record in MEDLINE/PubMed
BookMark eNpNkUtv1TAQhS1URB-wYo-8RKpS_Lw3WaIrCpWK2JS1NXHGbUpiXzxOEb-Cv4zvg4rVHI8_nxn5nLOTmCIy9laKK91p82Hu8UoJZZTVL9iZtFY2Qsj25D99ys6JHoXQRmvzip3qtl0ra1dn7M_XZSpjs30AQh4QypKR-BgLZvBlTJGXDJFCyjNmHrH8SvkHr0c-jU-1U5a5asL7GWOB_QOIA59Hn9MTkF8myNWuyv0VERLt0NrjPsVqTqXB-ADR48A3d6_ZywAT4ZtjvWDfrz_dbb40t98-32w-3jagulY3AYQclDVBdKgHqYIGDKaHofOggjUadY9owqpd215plAakX0GAWqEDqS_YzcF3SPDotnmcIf92CUa3b6R87yCX0U_oWoRegLcGem3W2LYGMVghsW4iTOer1_uD1zannwtScfNIHqcJIqaFnBa7NTqjTEXfHdGln3F4HvwvkApcHoD6f0QZwzMihdvF7Wrc7hi3_gu9WKFL
Cites_doi 10.1053/j.gastro.2004.09.011
10.1109/IEMBS.2009.5333760
10.1016/j.simpat.2023.102769
10.1016/j.compbiomed.2017.01.009
10.1007/s00371-021-02328-7
10.1109/ICIP.2019.8802942
10.54294/1uhwld
10.3109/10929080109145999
10.1109/ICCV48922.2021.00468
10.54294/25etax
10.1016/j.compmedimag.2020.101811
10.4236/jcc.2015.311023
10.1002/mp.14922
10.1002/mp.13438
10.1016/j.imed.2022.07.002
10.1109/TMI.2019.2948320
10.1038/s41571-021-00560-7
10.1007/s00261-020-02485-8
10.1038/s41572-020-00240-3
10.1016/j.inffus.2022.10.022
10.1148/radiol.2513081740
10.1016/j.bspc.2023.104791
10.1109/TMI.2018.2878669
10.3390/cancers14122956
10.1109/TIP.2019.2905537
10.1016/j.compmedimag.2021.101885
10.3389/fnins.2022.1009581
10.1158/0008-5472.CAN-17-0339
10.1155/2016/8763205
10.1016/j.compbiomed.2022.105620
10.1007/s00261-022-03496-3
10.1016/j.artmed.2017.03.008
10.1038/s41598-018-33860-7
10.1007/s00268-005-0718-1
10.3389/fonc.2021.588010
10.1007/s00432-020-03366-9
10.1016/j.compeleceng.2013.02.008
10.1109/ACCESS.2021.3107473
10.1016/j.compmedimag.2021.102021
10.3322/caac.21660
10.21037/qims-22-1011
10.1016/j.cmpb.2017.04.008
10.1109/JBHI.2022.3220788
10.3748/wjg.v28.i26.3092
10.1007/s11548-019-01989-z
10.1148/radiol.2273011768
ContentType Journal Article
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOA
DOI 10.3934/mbe.2024253
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic

CrossRef
MEDLINE
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– 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 Biology
EISSN 1551-0018
EndPage 5761
ExternalDocumentID oai_doaj_org_article_8eab0ac54ab347e884eef501e298049c
38872556
10_3934_mbe_2024253
Genre Journal Article
GroupedDBID ---
53G
5GY
AAYXX
AENEX
ALMA_UNASSIGNED_HOLDINGS
AMVHM
CITATION
EBD
EBS
EJD
EMOBN
F5P
GROUPED_DOAJ
IAO
ITC
J9A
ML0
OK1
P2P
RAN
SV3
TUS
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-a2983-fa01d254f09e3d12f3aef4bad9ca2f543e3bee4f6875b23e14a1c6afa4a1a9a13
IEDL.DBID DOA
ISSN 1551-0018
IngestDate Fri Oct 03 12:48:20 EDT 2025
Fri Jul 11 12:29:12 EDT 2025
Mon Jul 21 05:58:51 EDT 2025
Sat Nov 29 04:14:56 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords liver tumor segmentation
transformer
contrast-enhanced CT
multi-phase
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a2983-fa01d254f09e3d12f3aef4bad9ca2f543e3bee4f6875b23e14a1c6afa4a1a9a13
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://doaj.org/article/8eab0ac54ab347e884eef501e298049c
PMID 38872556
PQID 3068759424
PQPubID 23479
PageCount 27
ParticipantIDs doaj_primary_oai_doaj_org_article_8eab0ac54ab347e884eef501e298049c
proquest_miscellaneous_3068759424
pubmed_primary_38872556
crossref_primary_10_3934_mbe_2024253
PublicationCentury 2000
PublicationDate 2024-Apr-24
PublicationDateYYYYMMDD 2024-04-24
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-Apr-24
  day: 24
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Mathematical biosciences and engineering : MBE
PublicationTitleAlternate Math Biosci Eng
PublicationYear 2024
Publisher AIMS Press
Publisher_xml – name: AIMS Press
References key-10.3934/mbe.2024253-38
key-10.3934/mbe.2024253-37
key-10.3934/mbe.2024253-36
key-10.3934/mbe.2024253-35
key-10.3934/mbe.2024253-34
key-10.3934/mbe.2024253-33
key-10.3934/mbe.2024253-32
key-10.3934/mbe.2024253-31
key-10.3934/mbe.2024253-39
key-10.3934/mbe.2024253-41
key-10.3934/mbe.2024253-40
key-10.3934/mbe.2024253-27
key-10.3934/mbe.2024253-26
key-10.3934/mbe.2024253-25
key-10.3934/mbe.2024253-24
key-10.3934/mbe.2024253-23
key-10.3934/mbe.2024253-22
key-10.3934/mbe.2024253-21
key-10.3934/mbe.2024253-20
key-10.3934/mbe.2024253-64
key-10.3934/mbe.2024253-29
key-10.3934/mbe.2024253-28
key-10.3934/mbe.2024253-30
key-10.3934/mbe.2024253-16
key-10.3934/mbe.2024253-15
key-10.3934/mbe.2024253-59
key-10.3934/mbe.2024253-14
key-10.3934/mbe.2024253-58
key-10.3934/mbe.2024253-13
key-10.3934/mbe.2024253-57
key-10.3934/mbe.2024253-12
key-10.3934/mbe.2024253-56
key-10.3934/mbe.2024253-11
key-10.3934/mbe.2024253-55
key-10.3934/mbe.2024253-10
key-10.3934/mbe.2024253-54
key-10.3934/mbe.2024253-53
key-10.3934/mbe.2024253-19
key-10.3934/mbe.2024253-18
key-10.3934/mbe.2024253-17
key-10.3934/mbe.2024253-63
key-10.3934/mbe.2024253-62
key-10.3934/mbe.2024253-61
key-10.3934/mbe.2024253-60
key-10.3934/mbe.2024253-5
key-10.3934/mbe.2024253-49
key-10.3934/mbe.2024253-4
key-10.3934/mbe.2024253-48
key-10.3934/mbe.2024253-3
key-10.3934/mbe.2024253-47
key-10.3934/mbe.2024253-2
key-10.3934/mbe.2024253-46
key-10.3934/mbe.2024253-9
key-10.3934/mbe.2024253-45
key-10.3934/mbe.2024253-8
key-10.3934/mbe.2024253-44
key-10.3934/mbe.2024253-7
key-10.3934/mbe.2024253-43
key-10.3934/mbe.2024253-6
key-10.3934/mbe.2024253-42
key-10.3934/mbe.2024253-52
key-10.3934/mbe.2024253-51
key-10.3934/mbe.2024253-50
key-10.3934/mbe.2024253-1
References_xml – ident: key-10.3934/mbe.2024253-3
  doi: 10.1053/j.gastro.2004.09.011
– ident: key-10.3934/mbe.2024253-18
  doi: 10.1109/IEMBS.2009.5333760
– ident: key-10.3934/mbe.2024253-41
– ident: key-10.3934/mbe.2024253-47
  doi: 10.1016/j.simpat.2023.102769
– ident: key-10.3934/mbe.2024253-16
  doi: 10.1016/j.compbiomed.2017.01.009
– ident: key-10.3934/mbe.2024253-50
  doi: 10.1007/s00371-021-02328-7
– ident: key-10.3934/mbe.2024253-38
  doi: 10.1109/ICIP.2019.8802942
– ident: key-10.3934/mbe.2024253-15
  doi: 10.54294/1uhwld
– ident: key-10.3934/mbe.2024253-55
– ident: key-10.3934/mbe.2024253-14
  doi: 10.3109/10929080109145999
– ident: key-10.3934/mbe.2024253-56
  doi: 10.1109/ICCV48922.2021.00468
– ident: key-10.3934/mbe.2024253-51
– ident: key-10.3934/mbe.2024253-17
  doi: 10.54294/25etax
– ident: key-10.3934/mbe.2024253-21
  doi: 10.1016/j.compmedimag.2020.101811
– ident: key-10.3934/mbe.2024253-59
– ident: key-10.3934/mbe.2024253-7
  doi: 10.4236/jcc.2015.311023
– ident: key-10.3934/mbe.2024253-34
  doi: 10.1002/mp.14922
– ident: key-10.3934/mbe.2024253-24
  doi: 10.1002/mp.13438
– ident: key-10.3934/mbe.2024253-45
  doi: 10.1016/j.imed.2022.07.002
– ident: key-10.3934/mbe.2024253-30
  doi: 10.1109/TMI.2019.2948320
– ident: key-10.3934/mbe.2024253-62
  doi: 10.1038/s41571-021-00560-7
– ident: key-10.3934/mbe.2024253-33
  doi: 10.1007/s00261-020-02485-8
– ident: key-10.3934/mbe.2024253-40
– ident: key-10.3934/mbe.2024253-27
– ident: key-10.3934/mbe.2024253-48
– ident: key-10.3934/mbe.2024253-2
  doi: 10.1038/s41572-020-00240-3
– ident: key-10.3934/mbe.2024253-58
– ident: key-10.3934/mbe.2024253-49
  doi: 10.1016/j.inffus.2022.10.022
– ident: key-10.3934/mbe.2024253-12
  doi: 10.1148/radiol.2513081740
– ident: key-10.3934/mbe.2024253-44
  doi: 10.1016/j.bspc.2023.104791
– ident: key-10.3934/mbe.2024253-20
– ident: key-10.3934/mbe.2024253-22
  doi: 10.1109/TMI.2018.2878669
– ident: key-10.3934/mbe.2024253-9
  doi: 10.3390/cancers14122956
– ident: key-10.3934/mbe.2024253-23
  doi: 10.1109/TIP.2019.2905537
– ident: key-10.3934/mbe.2024253-31
  doi: 10.1016/j.compmedimag.2021.101885
– ident: key-10.3934/mbe.2024253-46
  doi: 10.3389/fnins.2022.1009581
– ident: key-10.3934/mbe.2024253-43
– ident: key-10.3934/mbe.2024253-64
  doi: 10.1158/0008-5472.CAN-17-0339
– ident: key-10.3934/mbe.2024253-4
  doi: 10.1155/2016/8763205
– ident: key-10.3934/mbe.2024253-13
  doi: 10.1016/j.compbiomed.2022.105620
– ident: key-10.3934/mbe.2024253-61
  doi: 10.1007/s00261-022-03496-3
– ident: key-10.3934/mbe.2024253-37
  doi: 10.1016/j.artmed.2017.03.008
– ident: key-10.3934/mbe.2024253-26
  doi: 10.1038/s41598-018-33860-7
– ident: key-10.3934/mbe.2024253-57
– ident: key-10.3934/mbe.2024253-28
– ident: key-10.3934/mbe.2024253-53
– ident: key-10.3934/mbe.2024253-11
  doi: 10.1007/s00268-005-0718-1
– ident: key-10.3934/mbe.2024253-60
  doi: 10.3389/fonc.2021.588010
– ident: key-10.3934/mbe.2024253-10
  doi: 10.1007/s00432-020-03366-9
– ident: key-10.3934/mbe.2024253-19
  doi: 10.1016/j.compeleceng.2013.02.008
– ident: key-10.3934/mbe.2024253-8
  doi: 10.1109/ACCESS.2021.3107473
– ident: key-10.3934/mbe.2024253-54
  doi: 10.1016/j.compmedimag.2021.102021
– ident: key-10.3934/mbe.2024253-1
  doi: 10.3322/caac.21660
– ident: key-10.3934/mbe.2024253-63
  doi: 10.21037/qims-22-1011
– ident: key-10.3934/mbe.2024253-6
  doi: 10.1016/j.cmpb.2017.04.008
– ident: key-10.3934/mbe.2024253-42
– ident: key-10.3934/mbe.2024253-32
  doi: 10.1109/JBHI.2022.3220788
– ident: key-10.3934/mbe.2024253-25
– ident: key-10.3934/mbe.2024253-5
  doi: 10.3748/wjg.v28.i26.3092
– ident: key-10.3934/mbe.2024253-29
– ident: key-10.3934/mbe.2024253-36
  doi: 10.1007/s11548-019-01989-z
– ident: key-10.3934/mbe.2024253-52
– ident: key-10.3934/mbe.2024253-39
– ident: key-10.3934/mbe.2024253-35
  doi: 10.1148/radiol.2273011768
SSID ssj0034334
Score 2.3326128
Snippet Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging...
SourceID doaj
proquest
pubmed
crossref
SourceType Open Website
Aggregation Database
Index Database
StartPage 5735
SubjectTerms Algorithms
Contrast Media
contrast-enhanced ct
Female
Humans
Image Processing, Computer-Assisted - methods
Liver - blood supply
Liver - diagnostic imaging
Liver - pathology
Liver Neoplasms - blood supply
Liver Neoplasms - diagnostic imaging
Liver Neoplasms - pathology
liver tumor segmentation
Male
Microvessels - diagnostic imaging
Microvessels - pathology
multi-phase
Neoplasm Invasiveness
Radiographic Image Interpretation, Computer-Assisted - methods
Tomography, X-Ray Computed
transformer
Title Multi-phase features interaction transformer network for liver tumor segmentation and microvascular invasion assessment in contrast-enhanced CT
URI https://www.ncbi.nlm.nih.gov/pubmed/38872556
https://www.proquest.com/docview/3068759424
https://doaj.org/article/8eab0ac54ab347e884eef501e298049c
Volume 21
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1551-0018
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0034334
  issn: 1551-0018
  databaseCode: DOA
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagAokL4t3lURmpV6tJZrKJj1BRcao4FGlv0cQeUyQ2rTZZJH4Ff5mxnazggLhwiuNYie2Z2N_IM98odVoEWpc9eFOI9hqsAY0NDMYLvHAWA_ompGQTzeVlu9nYT7-l-oo-YZkeOE_cWcvUF-RqpB6w4bZF5lAXJVe2FXTr4upbNHYxpvIaDAiAORoPLODZto-MmBFdwx_7T6Lp_zu2THvMxSP1cAaH-l3u1GN1h4cn6n5OF_njqfqZomXN7bXsPDpwouQcdSR82OXwBD0tMJR3esgO3lpu9bfofaGn_VbKI3_ZzgFHg6bB6230yVs8UuV1UkyPDpydUqeTSzuNk-HhOjkN6POrZ-rzxYer849mTqhgSGYLTKCi9GIRhsIy-LIKQBywJ28dVaFGYOiZMazFiOkr4BKpdGsKJFeyVMJzdTTcDHystAC1Hlzp2lAxShPrmtpTW3PFIXiyK3W6THN3m3kzOrE3ojQ6kUY3S2Ol3kcRHJpEsutUISrQzSrQ_UsFVurtIsBOfo544kED3-zHTuwhGYrFClfqRZbs4VMgy2vkX3v5P7rwSj2II4rHTBW-VkfTbs9v1D33ffo67k7U3WbTniQN_QX6mfCO
linkProvider Directory of Open Access Journals
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=Multi-phase+features+interaction+transformer+network+for+liver+tumor+segmentation+and+microvascular+invasion+assessment+in+contrast-enhanced+CT&rft.jtitle=Mathematical+biosciences+and+engineering+%3A+MBE&rft.au=Zhang%2C+Wencong&rft.au=Tao%2C+Yuxi&rft.au=Huang%2C+Zhanyao&rft.au=Li%2C+Yue&rft.date=2024-04-24&rft.eissn=1551-0018&rft.volume=21&rft.issue=4&rft.spage=5735&rft_id=info:doi/10.3934%2Fmbe.2024253&rft_id=info%3Apmid%2F38872556&rft.externalDocID=38872556
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1551-0018&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1551-0018&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1551-0018&client=summon