Magnetic resonance imaging bias field estimation and tissue segmentation via convolutional neural networks and multiplicative and additive intrinsic components optimization

Magnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however, intensity inhomogeneity poses a significant challenge, particularly in data-limited scenarios. This study aimed to explore an algorithm designed to robustly addr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Intelligent medicine
Hlavní autori: Liu, Jun, Peng, Yuliang, Pu, Mingshu, Tang, Ling, Shao, Lizhi, Wang, Pengxiang, Yang, Lan, Huang, Furong, Shen, Zijie, Li, Chunming
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 2025
Predmet:
ISSN:2667-1026
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Magnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however, intensity inhomogeneity poses a significant challenge, particularly in data-limited scenarios. This study aimed to explore an algorithm designed to robustly address intensity inhomogeneity for brain MRI tissue segmentation under dataset constraints. We propose a two-stage framework that leverages data-driven and knowledge-driven approaches. Initially, a data-driven model was employed for skull-stripping, where a lightweight module, named multi-view dilated convolution attention (MDCA), is integrated into skip connections. The MDCA module eliminates the effect of intensity inhomogeneity enriched in shallow features at multiple scales, thus avoiding the negative impact on deeper abstract features. Furthermore, we introduced multiplicative and additive intrinsic components optimization (MAICO) algorithm, which decomposes MRI images into their real anatomical structures, multiplicative and additive bias fields, and zero-mean Gaussian noise, thus enabling precise anatomical segmentation. Experiments on MRBrainS13 and MRBrainS18 public datasets involved the random introduction of intensity inhomogeneity to generate training, validation, and testing sets with 60%, 20%, and 20% splits, respectively. Segmentation performance was measured using Dice coefficients and compared to methods such as MICO, FSL, and UNet. An ablation study further validated the efficacy of the MDCA module. Our approach improved MRI brain tissue segmentation accuracy, achieving a mean Dice coefficient of 0.7733 across tissue types. With MDCA and MAICO, it reached 0.8163 for white matter, 0.7402 for gray matter, and 0.7634 for cerebrospinal fluid, outperforming other algorithms. Additionally, MDCA module integration in skip connections yielded a 5% average accuracy boost. This study effectively combined knowledge-driven and data-driven techniques to enhance MRI brain segmentation stability and accuracy, thereby demonstrating strong potential for clinical application in managing intensity inhomogeneity in data-constrained settings.
AbstractList AbstractObjectiveMagnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however, intensity inhomogeneity poses a significant challenge, particularly in data-limited scenarios. This study aimed to explore an algorithm designed to robustly address intensity inhomogeneity for brain MRI tissue segmentation under dataset constraints. MethodsWe propose a two-stage framework that leverages data-driven and knowledge-driven approaches. Initially, a data-driven model was employed for skull-stripping, where a lightweight module, named multi-view dilated convolution attention (MDCA), is integrated into skip connections. The MDCA module eliminates the effect of intensity inhomogeneity enriched in shallow features at multiple scales, thus avoiding the negative impact on deeper abstract features. Furthermore, we introduced multiplicative and additive intrinsic components optimization (MAICO) algorithm, which decomposes MRI images into their real anatomical structures, multiplicative and additive bias fields, and zero-mean Gaussian noise, thus enabling precise anatomical segmentation. Experiments on MRBrainS13 and MRBrainS18 public datasets involved the random introduction of intensity inhomogeneity to generate training, validation, and testing sets with 60%, 20%, and 20% splits, respectively. Segmentation performance was measured using Dice coefficients and compared to methods such as MICO, FSL, and UNet. An ablation study further validated the efficacy of the MDCA module. ResultsOur approach improved MRI brain tissue segmentation accuracy, achieving a mean Dice coefficient of 0.7733 across tissue types. With MDCA and MAICO, it reached 0.8163 for white matter, 0.7402 for gray matter, and 0.7634 for cerebrospinal fluid, outperforming other algorithms. Additionally, MDCA module integration in skip connections yielded a 5% average accuracy boost. ConclusionThis study effectively combined knowledge-driven and data-driven techniques to enhance MRI brain segmentation stability and accuracy, thereby demonstrating strong potential for clinical application in managing intensity inhomogeneity in data-constrained settings.
Magnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however, intensity inhomogeneity poses a significant challenge, particularly in data-limited scenarios. This study aimed to explore an algorithm designed to robustly address intensity inhomogeneity for brain MRI tissue segmentation under dataset constraints. We propose a two-stage framework that leverages data-driven and knowledge-driven approaches. Initially, a data-driven model was employed for skull-stripping, where a lightweight module, named multi-view dilated convolution attention (MDCA), is integrated into skip connections. The MDCA module eliminates the effect of intensity inhomogeneity enriched in shallow features at multiple scales, thus avoiding the negative impact on deeper abstract features. Furthermore, we introduced multiplicative and additive intrinsic components optimization (MAICO) algorithm, which decomposes MRI images into their real anatomical structures, multiplicative and additive bias fields, and zero-mean Gaussian noise, thus enabling precise anatomical segmentation. Experiments on MRBrainS13 and MRBrainS18 public datasets involved the random introduction of intensity inhomogeneity to generate training, validation, and testing sets with 60%, 20%, and 20% splits, respectively. Segmentation performance was measured using Dice coefficients and compared to methods such as MICO, FSL, and UNet. An ablation study further validated the efficacy of the MDCA module. Our approach improved MRI brain tissue segmentation accuracy, achieving a mean Dice coefficient of 0.7733 across tissue types. With MDCA and MAICO, it reached 0.8163 for white matter, 0.7402 for gray matter, and 0.7634 for cerebrospinal fluid, outperforming other algorithms. Additionally, MDCA module integration in skip connections yielded a 5% average accuracy boost. This study effectively combined knowledge-driven and data-driven techniques to enhance MRI brain segmentation stability and accuracy, thereby demonstrating strong potential for clinical application in managing intensity inhomogeneity in data-constrained settings.
Author Li, Chunming
Tang, Ling
Wang, Pengxiang
Peng, Yuliang
Huang, Furong
Shen, Zijie
Yang, Lan
Liu, Jun
Shao, Lizhi
Pu, Mingshu
Author_xml – sequence: 1
  givenname: Jun
  surname: Liu
  fullname: Liu, Jun
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 2
  givenname: Yuliang
  surname: Peng
  fullname: Peng, Yuliang
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 3
  givenname: Mingshu
  surname: Pu
  fullname: Pu, Mingshu
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 4
  givenname: Ling
  surname: Tang
  fullname: Tang, Ling
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 5
  givenname: Lizhi
  surname: Shao
  fullname: Shao, Lizhi
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 6
  givenname: Pengxiang
  surname: Wang
  fullname: Wang, Pengxiang
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 7
  givenname: Lan
  surname: Yang
  fullname: Yang, Lan
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 8
  givenname: Furong
  surname: Huang
  fullname: Huang, Furong
  organization: Department of Endocrinology, Nanjiang People’s Hospital, Bazhong, Sichuan 636600, China
– sequence: 9
  givenname: Zijie
  surname: Shen
  fullname: Shen, Zijie
  email: 202312012436@std.uestc.edu.cn
  organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China
– sequence: 10
  givenname: Chunming
  surname: Li
  fullname: Li, Chunming
  organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China
BookMark eNqFkc9q3DAQxn1IIGmSF-hJL7CuJMteu5RCCU1aSOkhuQtZGi-zsaVFI29JnykPWdnbU6HtaZgPvvnz-94UZz54KIq3gpeCi-bdvsQJXCm5rEsuS87lWXEpm2a7EVw2F8UN0Z5ndcs7pdRl8frN7DwktCwCBW-8BYaT2aHfsR4NsQFhdAwoZTVh8Mx4xxISzcAIdhP4dNKPaJgN_hjGeenNyDzMcS3pR4jPtDqneUx4GNFm0xFWyTiHa4M-RfSUb7FhOuS_fCIWDnkz_lx3XBfngxkJbn7Xq-Lp7vPT7ZfNw_f7r7efHja2Eq3cVH3PQcnWVGA72dRSDUr0nQM3iLYZDKheqXbgot9Wym3rTijD-25QUFetqqqrQp7G2hiIIgz6EPP38UULrhfKeq8XynqhrLnUmWc2fTiZIB92RIiaLELG6TCCTdoF_Lf94x92O6LPmMZneAHahzlmpKSFpmzQj0ukS6Kyzmm29XL0-78P-N_2X0KNuCY
Cites_doi 10.3390/ijgi10040256
10.1109/42.845174
10.1016/j.neuroimage.2011.09.015
10.1006/cviu.2001.0951
10.1109/CVPRW.2015.7301312
10.1016/j.irbm.2022.02.005
10.1109/42.585758
10.1016/j.artmed.2023.102608
10.1109/42.811268
10.1016/j.imed.2021.03.003
10.1016/j.job.2022.03.003
10.1155/2015/813696
10.1109/ACCESS.2022.3175188
10.1016/j.compmedimag.2022.102157
10.1007/978-3-319-24574-4_28
10.1109/TTS.2023.3234203
10.1016/j.mri.2018.08.024
10.5121/ijma.2013.5102
10.1109/TMI.2019.2937271
10.1007/978-3-030-01234-2_49
10.1049/iet-ipr.2018.5171
10.1109/TCYB.2018.2830977
10.1109/TMI.2016.2548501
10.1109/TMI.2006.891486
10.1016/j.patcog.2021.108420
10.1109/42.802752
10.1016/j.compbiomed.2022.106472
10.1080/03772063.2017.1409088
10.1016/j.imed.2023.10.001
10.1016/j.mri.2014.03.010
10.1016/j.mri.2019.06.010
10.1109/34.295913
10.1109/42.511747
10.1016/j.jneumeth.2021.109091
ContentType Journal Article
Copyright 2025 The Authors
The Authors
Copyright_xml – notice: 2025 The Authors
– notice: The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.imed.2025.02.002
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList


DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 10_1016_j_imed_2025_02_002
S2667102625000853
1_s2_0_S2667102625000853
GroupedDBID .1-
.FO
0R~
AAEDW
AALRI
AAXUO
AAYWO
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AFRHN
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
EBS
FDB
GROUPED_DOAJ
M41
M~E
ROL
Z5R
6I.
AAFTH
AAYXX
CITATION
ID FETCH-LOGICAL-c3182-3bb0e428a3ec926524f41b9dedf186fae4b448f01b734d75914a0b9f4e538433
ISSN 2667-1026
IngestDate Thu Nov 27 00:51:45 EST 2025
Wed Dec 10 14:24:07 EST 2025
Sat Nov 29 12:10:57 EST 2025
Wed Dec 10 14:10:12 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Brain segmentation
Attention mechanism
Intensity inhomogeneity
Magnetic resonance imaging
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c3182-3bb0e428a3ec926524f41b9dedf186fae4b448f01b734d75914a0b9f4e538433
OpenAccessLink http://dx.doi.org/10.1016/j.imed.2025.02.002
ParticipantIDs crossref_primary_10_1016_j_imed_2025_02_002
elsevier_sciencedirect_doi_10_1016_j_imed_2025_02_002
elsevier_clinicalkeyesjournals_1_s2_0_S2667102625000853
elsevier_clinicalkey_doi_10_1016_j_imed_2025_02_002
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle Intelligent medicine
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Jenkinson, Beckmann, Behrens, Woolrich, Smith (bib0035) 2012; 62
Yang, Wang, Feng (bib0019) 2019; 13
Clèrigues, Valverde, Salvi, Oliver, Lladó (bib0023) 2023; 103
Ronneberger O., Fischer P., Brox T.. U-net: Convolutional networks for biomedical image segmentation. 2015.. 1505.04597. 10.48550/arXiv.1505.04597
Styner, Brechbuhler, Szckely, Gerig (bib0014) 2000; 19
Gudise, Kande, Satya Savithri (bib0004) 2019; 65
Moeskops, Viergever, Mendrik, De Vries, Benders, Isgum (bib0027) 2016; 35
K, T (bib0010) 2013; 5
Guillemaud, Brady (bib0013) 1997; 16
Wei, Wu, Wang, Bui, Qu, Yap (bib0026) 2022; 124
Wells, Grimson, Kikinis, Jolesz (bib0012) 1996; 15
Khosravanian, Rahmanimanesh, Keshavarzi (bib0005) 2021; 352
Li, Gore, Davatzikos (bib0018) 2014; 32
Adams, Bischof (bib0009) 1994; 16
Vovk, Pernus, Likar (bib0016) 2007; 26
Beucher, Lantuéjoul (bib0008) 1979; vol. 132
Halder, Talukdar (bib0001) 2019; 62
Lee, Lee, Lee, Kim, Lim, Kim (bib0024) 2023; 153
Mendrik, Vincken, Kuijf, Breeuwer, Bouvy, De Bresser (bib0032) 2015; 2015
Yang, Ruan, Wu (bib0020) 2018; 54
Chen L.-C., Zhu Y., Papandreou G., Schroff F., Adam H.. Encoder-decoder with atrous separable convolution for semantic image segmentation. 2018.. 10.48550/ARXIV.1802.02611
Ciceri, Squarcina, Giubergia, Bertoldo, Brambilla, Peruzzo (bib0022) 2023; 143
Ahishakiye, Van Gijzen, Tumwiine, Wario, Obungoloch (bib0030) 2021; 1
Rahali, Dridi, Ben Salem, Descombes, Debreuve, De Graeve (bib0011) 2022; 43
Bai, Zhang, Liu (bib0003) 2019; 49
Ponciano, Roetner, Reiterer (bib0006) 2021; 10
Kumar, Jha, Kumar, Raju (bib0021) 2024; 4
Dhar, Dey, Borra, Sherratt (bib0029) 2023; 4
Forgy (bib0007) 1965; 21
Dayananda, Choi, Lee (bib0002) 2022; 10
Paszke A., Gross S., Chintala S., Chanan G., Yang E., DeVito Z., et al. Automatic differentiation in pytorch2017.
Pham (bib0017) 2001; 84
De Brebisson, Montana (bib0025) 2015
Pham, Prince (bib0015) Sept./1999; 18
Sun, Ma, Ding, Huang, Liang, Paisley (bib0028) 2020; 39
Van Leemput, Maes, Vandermeulen, Suetens (bib0033) 1999; 18
Tsuneki (bib0031) 2022; 64
Adams (10.1016/j.imed.2025.02.002_bib0009) 1994; 16
Styner (10.1016/j.imed.2025.02.002_bib0014) 2000; 19
Bai (10.1016/j.imed.2025.02.002_bib0003) 2019; 49
Khosravanian (10.1016/j.imed.2025.02.002_bib0005) 2021; 352
Van Leemput (10.1016/j.imed.2025.02.002_bib0033) 1999; 18
Pham (10.1016/j.imed.2025.02.002_bib0015) 1999; 18
Dayananda (10.1016/j.imed.2025.02.002_bib0002) 2022; 10
Dhar (10.1016/j.imed.2025.02.002_bib0029) 2023; 4
Sun (10.1016/j.imed.2025.02.002_bib0028) 2020; 39
Mendrik (10.1016/j.imed.2025.02.002_bib0032) 2015; 2015
Forgy (10.1016/j.imed.2025.02.002_bib0007) 1965; 21
Rahali (10.1016/j.imed.2025.02.002_bib0011) 2022; 43
Gudise (10.1016/j.imed.2025.02.002_bib0004) 2019; 65
Ciceri (10.1016/j.imed.2025.02.002_bib0022) 2023; 143
K (10.1016/j.imed.2025.02.002_bib0010) 2013; 5
Clèrigues (10.1016/j.imed.2025.02.002_bib0023) 2023; 103
Li (10.1016/j.imed.2025.02.002_bib0018) 2014; 32
De Brebisson (10.1016/j.imed.2025.02.002_bib0025) 2015
Halder (10.1016/j.imed.2025.02.002_bib0001) 2019; 62
Wei (10.1016/j.imed.2025.02.002_bib0026) 2022; 124
Jenkinson (10.1016/j.imed.2025.02.002_bib0035) 2012; 62
Ahishakiye (10.1016/j.imed.2025.02.002_bib0030) 2021; 1
Tsuneki (10.1016/j.imed.2025.02.002_bib0031) 2022; 64
Kumar (10.1016/j.imed.2025.02.002_bib0021) 2024; 4
Yang (10.1016/j.imed.2025.02.002_bib0020) 2018; 54
Wells (10.1016/j.imed.2025.02.002_bib0012) 1996; 15
Moeskops (10.1016/j.imed.2025.02.002_bib0027) 2016; 35
Yang (10.1016/j.imed.2025.02.002_bib0019) 2019; 13
Ponciano (10.1016/j.imed.2025.02.002_bib0006) 2021; 10
Guillemaud (10.1016/j.imed.2025.02.002_bib0013) 1997; 16
10.1016/j.imed.2025.02.002_bib0034
Pham (10.1016/j.imed.2025.02.002_bib0017) 2001; 84
Vovk (10.1016/j.imed.2025.02.002_bib0016) 2007; 26
10.1016/j.imed.2025.02.002_bib0036
10.1016/j.imed.2025.02.002_bib0037
Beucher (10.1016/j.imed.2025.02.002_bib0008) 1979; vol. 132
Lee (10.1016/j.imed.2025.02.002_bib0024) 2023; 153
References_xml – volume: 65
  start-page: 250
  year: 2019
  end-page: 262
  ident: bib0004
  article-title: Segmentation of MR images of the brain to detect WM, GM, and CSF tissues in the presence of noise and intensity inhomogeneity
  publication-title: IETE Journal of Research
– volume: 18
  start-page: 737
  year: Sept./1999
  end-page: 752
  ident: bib0015
  article-title: Adaptive fuzzy segmentation of magnetic resonance images
  publication-title: IEEE Trans Med Imag
– volume: 39
  start-page: 898
  year: 2020
  end-page: 909
  ident: bib0028
  article-title: A 3d spatially weighted network for segmentation of brain tissue from MRI
  publication-title: IEEE Trans Med Imag
– volume: 4
  start-page: 68
  year: 2023
  end-page: 75
  ident: bib0029
  article-title: Challenges of deep learning in medical image analysis—improving explainability and trust
  publication-title: IEEE Transactions on Technology and Society
– volume: 143
  year: 2023
  ident: bib0022
  article-title: Review on deep learning fetal brain segmentation from magnetic resonance images
  publication-title: Artif Intell Med
– reference: Paszke A., Gross S., Chintala S., Chanan G., Yang E., DeVito Z., et al. Automatic differentiation in pytorch2017.
– volume: 26
  start-page: 405
  year: 2007
  end-page: 421
  ident: bib0016
  article-title: A review of methods for correction of intensity inhomogeneity in MRI
  publication-title: IEEE Trans Med Imag
– volume: 4
  start-page: 161
  year: 2024
  end-page: 169
  ident: bib0021
  article-title: Improved neurological diagnoses and treatment strategies via automated human brain tissue segmentation from clinical magnetic resonance imaging
  publication-title: Intelligent Medicine
– volume: 43
  start-page: 640
  year: 2022
  end-page: 657
  ident: bib0011
  article-title: Biological image segmentation using region-scalable fitting energy with b-spline level set implementation and watershed
  publication-title: IRBM
– volume: 18
  start-page: 885
  year: 1999
  end-page: 896
  ident: bib0033
  article-title: Automated model-based bias field correction of MR images of the brain
  publication-title: IEEE Trans Med Imag
– volume: 16
  start-page: 238
  year: 1997
  end-page: 251
  ident: bib0013
  article-title: Estimating the bias field of MR images
  publication-title: IEEE Trans Med Imag
– volume: 352
  year: 2021
  ident: bib0005
  article-title: A level set method based on domain transformation and bias correction for MRI brain tumor segmentation
  publication-title: J Neurosci Methods
– volume: 1
  start-page: 118
  year: 2021
  end-page: 127
  ident: bib0030
  article-title: A survey on deep learning in medical image reconstruction
  publication-title: Intelligent Medicine
– volume: 153
  year: 2023
  ident: bib0024
  article-title: Fine-grained brain tissue segmentation for brain modeling of stroke patient
  publication-title: Comput Biol Med
– volume: 84
  start-page: 285
  year: 2001
  end-page: 297
  ident: bib0017
  article-title: Spatial models for fuzzy clustering
  publication-title: Comput Vision Image Understanding
– reference: Chen L.-C., Zhu Y., Papandreou G., Schroff F., Adam H.. Encoder-decoder with atrous separable convolution for semantic image segmentation. 2018.. 10.48550/ARXIV.1802.02611
– volume: 19
  start-page: 153
  year: 2000
  end-page: 165
  ident: bib0014
  article-title: Parametric estimate of intensity inhomogeneities applied to MRI
  publication-title: IEEE Trans Med Imag
– reference: Ronneberger O., Fischer P., Brox T.. U-net: Convolutional networks for biomedical image segmentation. 2015.. 1505.04597. 10.48550/arXiv.1505.04597
– volume: 2015
  start-page: 1
  year: 2015
  end-page: 16
  ident: bib0032
  article-title: Mrbrains challenge: Online evaluation framework for brain image segmentation in 3t mri scans
  publication-title: Computational Intelligence and Neuroscience
– volume: 103
  year: 2023
  ident: bib0023
  article-title: Minimizing the effect of white matter lesions on deep learning based tissue segmentation for brain volumetry
  publication-title: Comput Med Imaging Graph
– volume: 35
  start-page: 1252
  year: 2016
  end-page: 1261
  ident: bib0027
  article-title: Automatic segmentation of MR brain images with a convolutional neural network
  publication-title: IEEE Trans Med Imag
– volume: 49
  start-page: 2618
  year: 2019
  end-page: 2630
  ident: bib0003
  article-title: Similarity measure-based possibilistic FCM with label information for brain MRI segmentation
  publication-title: IEEE Trans Cybern
– volume: 21
  start-page: 768
  year: 1965
  end-page: 769
  ident: bib0007
  article-title: Cluster analysis of multivariate data : efficiency versus interpretability of classifications
  publication-title: Biometrics
– volume: 16
  start-page: 641
  year: 1994
  end-page: 647
  ident: bib0009
  article-title: Seeded region growing
  publication-title: IEEE Trans Pattern Anal Machine Intell
– volume: 124
  year: 2022
  ident: bib0026
  article-title: A cascaded nested network for 3t brain MR image segmentation guided by 7t labeling
  publication-title: Pattern Recognit
– start-page: 20
  year: 2015
  end-page: 28
  ident: bib0025
  article-title: Deep neural networks for anatomical brain segmentation
  publication-title: 2015 IEEE Conf. Comput. Vis. Pattern Recognit. Workshop CVPRW
– volume: 62
  start-page: 782
  year: 2012
  end-page: 790
  ident: bib0035
  article-title: Fsl
  publication-title: NeuroImage
– volume: 13
  start-page: 939
  year: 2019
  end-page: 945
  ident: bib0019
  article-title: New method for simultaneous moderate bias correction and image segmentation
  publication-title: IET Image Proc
– volume: 54
  start-page: 249
  year: 2018
  end-page: 264
  ident: bib0020
  article-title: Efficient segmentation and correction model for brain MR images with level set framework based on basis functions
  publication-title: Magn Reson Imaging
– volume: 15
  start-page: 429
  year: 1996
  end-page: 442
  ident: bib0012
  article-title: Adaptive segmentation of MRI data
  publication-title: IEEE Trans Med Imag
– volume: 10
  start-page: 256
  year: 2021
  ident: bib0006
  article-title: Object semantic segmentation in point clouds—comparison of a deep learning and a knowledge-based method
  publication-title: ISPRS International Journal of Geo-Information
– volume: vol. 132
  year: 1979
  ident: bib0008
  article-title: Use of watersheds in contour detection
– volume: 5
  start-page: 11
  year: 2013
  end-page: 19
  ident: bib0010
  article-title: Binarization of MRI with intensity inhomogeneity using k-means clustering for segmenting hippocampus
  publication-title: The International journal of Multimedia & Its Applications
– volume: 32
  start-page: 913
  year: 2014
  end-page: 923
  ident: bib0018
  article-title: Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation
  publication-title: Magn Reson Imaging
– volume: 64
  start-page: 312
  year: 2022
  end-page: 320
  ident: bib0031
  article-title: Deep learning models in medical image analysis
  publication-title: Journal of Oral Biosciences
– volume: 62
  start-page: 129
  year: 2019
  end-page: 151
  ident: bib0001
  article-title: Brain tissue segmentation using improved kernelized rough-fuzzy c-means with spatio-contextual information from MRI
  publication-title: Magn Reson Imaging
– volume: 10
  start-page: 52804
  year: 2022
  end-page: 52817
  ident: bib0002
  article-title: A squeeze u-segnet architecture based on residual convolution for brain MRI segmentation
  publication-title: IEEE Access
– volume: 10
  start-page: 256
  issue: 4
  year: 2021
  ident: 10.1016/j.imed.2025.02.002_bib0006
  article-title: Object semantic segmentation in point clouds—comparison of a deep learning and a knowledge-based method
  publication-title: ISPRS International Journal of Geo-Information
  doi: 10.3390/ijgi10040256
– volume: vol. 132
  year: 1979
  ident: 10.1016/j.imed.2025.02.002_bib0008
– volume: 19
  start-page: 153
  issue: 3
  year: 2000
  ident: 10.1016/j.imed.2025.02.002_bib0014
  article-title: Parametric estimate of intensity inhomogeneities applied to MRI
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/42.845174
– volume: 62
  start-page: 782
  issue: 2
  year: 2012
  ident: 10.1016/j.imed.2025.02.002_bib0035
  article-title: Fsl
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2011.09.015
– volume: 84
  start-page: 285
  issue: 2
  year: 2001
  ident: 10.1016/j.imed.2025.02.002_bib0017
  article-title: Spatial models for fuzzy clustering
  publication-title: Comput Vision Image Understanding
  doi: 10.1006/cviu.2001.0951
– start-page: 20
  year: 2015
  ident: 10.1016/j.imed.2025.02.002_bib0025
  article-title: Deep neural networks for anatomical brain segmentation
  doi: 10.1109/CVPRW.2015.7301312
– volume: 43
  start-page: 640
  issue: 6
  year: 2022
  ident: 10.1016/j.imed.2025.02.002_bib0011
  article-title: Biological image segmentation using region-scalable fitting energy with b-spline level set implementation and watershed
  publication-title: IRBM
  doi: 10.1016/j.irbm.2022.02.005
– volume: 16
  start-page: 238
  issue: 3
  year: 1997
  ident: 10.1016/j.imed.2025.02.002_bib0013
  article-title: Estimating the bias field of MR images
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/42.585758
– volume: 143
  year: 2023
  ident: 10.1016/j.imed.2025.02.002_bib0022
  article-title: Review on deep learning fetal brain segmentation from magnetic resonance images
  publication-title: Artif Intell Med
  doi: 10.1016/j.artmed.2023.102608
– volume: 18
  start-page: 885
  issue: 10
  year: 1999
  ident: 10.1016/j.imed.2025.02.002_bib0033
  article-title: Automated model-based bias field correction of MR images of the brain
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/42.811268
– volume: 1
  start-page: 118
  issue: 3
  year: 2021
  ident: 10.1016/j.imed.2025.02.002_bib0030
  article-title: A survey on deep learning in medical image reconstruction
  publication-title: Intelligent Medicine
  doi: 10.1016/j.imed.2021.03.003
– volume: 21
  start-page: 768
  year: 1965
  ident: 10.1016/j.imed.2025.02.002_bib0007
  article-title: Cluster analysis of multivariate data : efficiency versus interpretability of classifications
  publication-title: Biometrics
– volume: 64
  start-page: 312
  issue: 3
  year: 2022
  ident: 10.1016/j.imed.2025.02.002_bib0031
  article-title: Deep learning models in medical image analysis
  publication-title: Journal of Oral Biosciences
  doi: 10.1016/j.job.2022.03.003
– volume: 2015
  start-page: 1
  year: 2015
  ident: 10.1016/j.imed.2025.02.002_bib0032
  article-title: Mrbrains challenge: Online evaluation framework for brain image segmentation in 3t mri scans
  publication-title: Computational Intelligence and Neuroscience
  doi: 10.1155/2015/813696
– volume: 10
  start-page: 52804
  year: 2022
  ident: 10.1016/j.imed.2025.02.002_bib0002
  article-title: A squeeze u-segnet architecture based on residual convolution for brain MRI segmentation
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3175188
– volume: 103
  year: 2023
  ident: 10.1016/j.imed.2025.02.002_bib0023
  article-title: Minimizing the effect of white matter lesions on deep learning based tissue segmentation for brain volumetry
  publication-title: Comput Med Imaging Graph
  doi: 10.1016/j.compmedimag.2022.102157
– ident: 10.1016/j.imed.2025.02.002_bib0036
  doi: 10.1007/978-3-319-24574-4_28
– volume: 4
  start-page: 68
  issue: 1
  year: 2023
  ident: 10.1016/j.imed.2025.02.002_bib0029
  article-title: Challenges of deep learning in medical image analysis—improving explainability and trust
  publication-title: IEEE Transactions on Technology and Society
  doi: 10.1109/TTS.2023.3234203
– volume: 54
  start-page: 249
  year: 2018
  ident: 10.1016/j.imed.2025.02.002_bib0020
  article-title: Efficient segmentation and correction model for brain MR images with level set framework based on basis functions
  publication-title: Magn Reson Imaging
  doi: 10.1016/j.mri.2018.08.024
– ident: 10.1016/j.imed.2025.02.002_bib0034
– volume: 5
  start-page: 11
  issue: 1
  year: 2013
  ident: 10.1016/j.imed.2025.02.002_bib0010
  article-title: Binarization of MRI with intensity inhomogeneity using k-means clustering for segmenting hippocampus
  publication-title: The International journal of Multimedia & Its Applications
  doi: 10.5121/ijma.2013.5102
– volume: 39
  start-page: 898
  issue: 4
  year: 2020
  ident: 10.1016/j.imed.2025.02.002_bib0028
  article-title: A 3d spatially weighted network for segmentation of brain tissue from MRI
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/TMI.2019.2937271
– ident: 10.1016/j.imed.2025.02.002_bib0037
  doi: 10.1007/978-3-030-01234-2_49
– volume: 13
  start-page: 939
  issue: 6
  year: 2019
  ident: 10.1016/j.imed.2025.02.002_bib0019
  article-title: New method for simultaneous moderate bias correction and image segmentation
  publication-title: IET Image Proc
  doi: 10.1049/iet-ipr.2018.5171
– volume: 49
  start-page: 2618
  issue: 7
  year: 2019
  ident: 10.1016/j.imed.2025.02.002_bib0003
  article-title: Similarity measure-based possibilistic FCM with label information for brain MRI segmentation
  publication-title: IEEE Trans Cybern
  doi: 10.1109/TCYB.2018.2830977
– volume: 35
  start-page: 1252
  issue: 5
  year: 2016
  ident: 10.1016/j.imed.2025.02.002_bib0027
  article-title: Automatic segmentation of MR brain images with a convolutional neural network
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/TMI.2016.2548501
– volume: 26
  start-page: 405
  issue: 3
  year: 2007
  ident: 10.1016/j.imed.2025.02.002_bib0016
  article-title: A review of methods for correction of intensity inhomogeneity in MRI
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/TMI.2006.891486
– volume: 124
  year: 2022
  ident: 10.1016/j.imed.2025.02.002_bib0026
  article-title: A cascaded nested network for 3t brain MR image segmentation guided by 7t labeling
  publication-title: Pattern Recognit
  doi: 10.1016/j.patcog.2021.108420
– volume: 18
  start-page: 737
  issue: 9
  year: 1999
  ident: 10.1016/j.imed.2025.02.002_bib0015
  article-title: Adaptive fuzzy segmentation of magnetic resonance images
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/42.802752
– volume: 153
  year: 2023
  ident: 10.1016/j.imed.2025.02.002_bib0024
  article-title: Fine-grained brain tissue segmentation for brain modeling of stroke patient
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2022.106472
– volume: 65
  start-page: 250
  issue: 2
  year: 2019
  ident: 10.1016/j.imed.2025.02.002_bib0004
  article-title: Segmentation of MR images of the brain to detect WM, GM, and CSF tissues in the presence of noise and intensity inhomogeneity
  publication-title: IETE Journal of Research
  doi: 10.1080/03772063.2017.1409088
– volume: 4
  start-page: 161
  issue: 3
  year: 2024
  ident: 10.1016/j.imed.2025.02.002_bib0021
  article-title: Improved neurological diagnoses and treatment strategies via automated human brain tissue segmentation from clinical magnetic resonance imaging
  publication-title: Intelligent Medicine
  doi: 10.1016/j.imed.2023.10.001
– volume: 32
  start-page: 913
  issue: 7
  year: 2014
  ident: 10.1016/j.imed.2025.02.002_bib0018
  article-title: Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation
  publication-title: Magn Reson Imaging
  doi: 10.1016/j.mri.2014.03.010
– volume: 62
  start-page: 129
  year: 2019
  ident: 10.1016/j.imed.2025.02.002_bib0001
  article-title: Brain tissue segmentation using improved kernelized rough-fuzzy c-means with spatio-contextual information from MRI
  publication-title: Magn Reson Imaging
  doi: 10.1016/j.mri.2019.06.010
– volume: 16
  start-page: 641
  issue: 6
  year: 1994
  ident: 10.1016/j.imed.2025.02.002_bib0009
  article-title: Seeded region growing
  publication-title: IEEE Trans Pattern Anal Machine Intell
  doi: 10.1109/34.295913
– volume: 15
  start-page: 429
  issue: 4
  year: 1996
  ident: 10.1016/j.imed.2025.02.002_bib0012
  article-title: Adaptive segmentation of MRI data
  publication-title: IEEE Trans Med Imag
  doi: 10.1109/42.511747
– volume: 352
  year: 2021
  ident: 10.1016/j.imed.2025.02.002_bib0005
  article-title: A level set method based on domain transformation and bias correction for MRI brain tumor segmentation
  publication-title: J Neurosci Methods
  doi: 10.1016/j.jneumeth.2021.109091
SSID ssj0002709444
Score 2.2788515
Snippet Magnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however, intensity...
AbstractObjectiveMagnetic resonance imaging (MRI) brain tissue segmentation is essential for the diagnosis and treatment of neurological diseases; however,...
SourceID crossref
elsevier
SourceType Index Database
Publisher
SubjectTerms Attention mechanism
Brain segmentation
Deep learning
Intensity inhomogeneity
Internal Medicine
Magnetic resonance imaging
Title Magnetic resonance imaging bias field estimation and tissue segmentation via convolutional neural networks and multiplicative and additive intrinsic components optimization
URI https://www.clinicalkey.com/#!/content/1-s2.0-S2667102625000853
https://www.clinicalkey.es/playcontent/1-s2.0-S2667102625000853
https://dx.doi.org/10.1016/j.imed.2025.02.002
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  issn: 2667-1026
  databaseCode: DOA
  dateStart: 20210101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: false
  ssIdentifier: ssj0002709444
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  issn: 2667-1026
  databaseCode: M~E
  dateStart: 20210101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: false
  ssIdentifier: ssj0002709444
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nj9MwELXKwoELAgGiC6x84BZllc8mPiIEAqm7QqJCy8myE6dkRb2rpqn2xJ3_wo9k7LGTLl3xJXFJGyu2o7yXzGQyb0zICxGLooryKszL2ixhFtUhy4UIY-BGHTFVS1uJ6eO8OD0tz87Y-8nkm9fCbL8UWpdXV-zyv0INbQC2kc7-BdzDoNAA_wF02ALssP0j4E_EUiuszGzcbHPjtitci0i2ogtszlpgimugahFzKO31Dzq1XDkxkg62rbBJ6e5sAUtT_NL-2NRxrO7sMhJt6G-L3yJMjpLdafVm3Wrggc1cv9BWTXcBD6mVU3_uusbvhuKgm70v_vO2RwmJHh_l-JD61Js4zXJo7lELoJfd536MSuCxc2-mXZQDtdAYdNsT3phnI7gVBVgQFNvvWQEMSJwft3C2x2Y0LMuajDZvyET8YEYyAyW5dT_TW-R2UuTMLIZx8nUM1yUFvAfbpYGHqZ0EC7MFf57qZjdnx3VZ3Cf33DsHfYlceUAmSj8k3z1P6MAT6nhCDU-o5QkdeUIBWoo8obs8ocATeo0nFHlCPU9sz-s8sU2eJ3TgCR15Qnd58ogs3rxevHobuqU7wgqMRBKmUkYK3mxFqiqWzPIka7JYslrVTVzOGqEymWVlE8WySLMarneciUiyJlNggLM0fUwONMz2hFCwghKc_EpIBgDkTTkzyXrK6DMVAws0JYG_0PwSC7Rwn7l4zg0s3MDCo4QDLFOSeiy4lx6DseTAnF_2Km7qpTp323c85h0cyffYNCX50NO5tOiq_mbGw3_s95TcNXsYI3xGDjbrXj0nd6ot0GN9ZANOR5bYPwAKF9Jz
linkProvider ISSN International Centre
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=Magnetic+resonance+imaging+bias+field+estimation+and+tissue+segmentation+via+convolutional+neural+networks+and+multiplicative+and+additive+intrinsic+components+optimization&rft.jtitle=Intelligent+medicine&rft.au=Liu%2C+Jun&rft.au=Peng%2C+Yuliang&rft.au=Pu%2C+Mingshu&rft.au=Tang%2C+Ling&rft.date=2025&rft.pub=Elsevier+B.V&rft.issn=2667-1026&rft_id=info:doi/10.1016%2Fj.imed.2025.02.002&rft.externalDocID=S2667102625000853
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2667-1026&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2667-1026&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2667-1026&client=summon