A dense connection encoding–decoding convolutional neural network structure for semantic segmentation of thymoma

•Three-channel pseudo-color images preprocessing method is designed by concatenating different CT windows.•A dense skip connection encoding–decoding model (DSC-Net) is proposed to perform automatic segmentation of thymoma base on a deep convolutional neural network.•Dense connections are introduced...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 451; s. 1 - 11
Hlavní autori: Li, Jingyuan, Sun, Wenfang, Feng, Xiulong, Xing, Gang, von Deneen, Karen M., Wang, Wen, Zhang, Yi, Cui, Guangbin
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 03.09.2021
Predmet:
ISSN:0925-2312, 1872-8286
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •Three-channel pseudo-color images preprocessing method is designed by concatenating different CT windows.•A dense skip connection encoding–decoding model (DSC-Net) is proposed to perform automatic segmentation of thymoma base on a deep convolutional neural network.•Dense connections are introduced into the architecture of the encoding path across different level feature maps in the DSC-Net.•Different level skip connections are designed between the encoding and decoding path in the DSC-Net. Accurately positioning and segmenting thymoma from computed tomography (CT) images is of great importance for an image-driven thymoma analysis. In clinical practice, the diagnosis and segmentation of thymomas for radiologists are time-consuming and inefficient tasks. Thus, it is necessary to develop a method to accurately and efficiently realize automatic segmentation of thymoma. Here, a dense skip connection encoding–decoding model (DSC-Net), which is a deep convolutional neural network, was proposed to perform automatic segmentation of thymoma with the ability to fuse feature maps under receptive fields of different scales. An image preprocessing method was also proposed to provide much more texture information and enhance the contrast between thymoma and its surrounding tissues. A total of 310 subjects who underwent contrast-enhanced CT scanning were included in this ethically-approved retrospective study. All of the CT slices were manually labeled by four experienced radiologists, and 80% of images were included in the training set and the rest were included in the testing set. The performance of segmentation was evaluated by calculating the accuracy, intersection over union (IoU), and Boundary F1 contour matching score (BFScore) between the predicted segmentation and the manual labels. For segmentation of thymoma in the testing set, the accuracy, IoU and BFScore were 92.96%, 87.86% and 0.9087 respectively. Compared to the U-Net method, the DSC-Net model improved IoU by 3.94%. In addition, the efficacy and robustness of DSC-Net in segmentation of different patients and different types of thymoma classified by the WHO histological classification criteria were verified. The proposed preprocessing method and DSC-Net demonstrated improved performance in segmentation of thymomas, suggesting the ability to provide consistent delineation and assist radiologists in their clinical applications.
AbstractList •Three-channel pseudo-color images preprocessing method is designed by concatenating different CT windows.•A dense skip connection encoding–decoding model (DSC-Net) is proposed to perform automatic segmentation of thymoma base on a deep convolutional neural network.•Dense connections are introduced into the architecture of the encoding path across different level feature maps in the DSC-Net.•Different level skip connections are designed between the encoding and decoding path in the DSC-Net. Accurately positioning and segmenting thymoma from computed tomography (CT) images is of great importance for an image-driven thymoma analysis. In clinical practice, the diagnosis and segmentation of thymomas for radiologists are time-consuming and inefficient tasks. Thus, it is necessary to develop a method to accurately and efficiently realize automatic segmentation of thymoma. Here, a dense skip connection encoding–decoding model (DSC-Net), which is a deep convolutional neural network, was proposed to perform automatic segmentation of thymoma with the ability to fuse feature maps under receptive fields of different scales. An image preprocessing method was also proposed to provide much more texture information and enhance the contrast between thymoma and its surrounding tissues. A total of 310 subjects who underwent contrast-enhanced CT scanning were included in this ethically-approved retrospective study. All of the CT slices were manually labeled by four experienced radiologists, and 80% of images were included in the training set and the rest were included in the testing set. The performance of segmentation was evaluated by calculating the accuracy, intersection over union (IoU), and Boundary F1 contour matching score (BFScore) between the predicted segmentation and the manual labels. For segmentation of thymoma in the testing set, the accuracy, IoU and BFScore were 92.96%, 87.86% and 0.9087 respectively. Compared to the U-Net method, the DSC-Net model improved IoU by 3.94%. In addition, the efficacy and robustness of DSC-Net in segmentation of different patients and different types of thymoma classified by the WHO histological classification criteria were verified. The proposed preprocessing method and DSC-Net demonstrated improved performance in segmentation of thymomas, suggesting the ability to provide consistent delineation and assist radiologists in their clinical applications.
Author Cui, Guangbin
Li, Jingyuan
von Deneen, Karen M.
Wang, Wen
Zhang, Yi
Feng, Xiulong
Xing, Gang
Sun, Wenfang
Author_xml – sequence: 1
  givenname: Jingyuan
  surname: Li
  fullname: Li, Jingyuan
  organization: Center for Brain Imaging, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710126, China
– sequence: 2
  givenname: Wenfang
  surname: Sun
  fullname: Sun, Wenfang
  organization: School of Aerospace Science and Technology, Xidian University, Xi’an, Shaanxi 710126, China
– sequence: 3
  givenname: Xiulong
  surname: Feng
  fullname: Feng, Xiulong
  organization: Department of Radiology, Tangdu Hospital, Air Force Medical University, Xi’an, Shaanxi 710038, China
– sequence: 4
  givenname: Gang
  surname: Xing
  fullname: Xing, Gang
  organization: Center for Brain Imaging, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710126, China
– sequence: 5
  givenname: Karen M.
  surname: von Deneen
  fullname: von Deneen, Karen M.
  organization: Center for Brain Imaging, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710126, China
– sequence: 6
  givenname: Wen
  surname: Wang
  fullname: Wang, Wen
  email: wfsun@xidian.cdu.cn
  organization: Department of Radiology, Tangdu Hospital, Air Force Medical University, Xi’an, Shaanxi 710038, China
– sequence: 7
  givenname: Yi
  orcidid: 0000-0003-0859-9735
  surname: Zhang
  fullname: Zhang, Yi
  email: yizhang@xidian.edu.cn, zhangyiuf@gmail.com
  organization: Center for Brain Imaging, School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710126, China
– sequence: 8
  givenname: Guangbin
  surname: Cui
  fullname: Cui, Guangbin
  email: cuigbtd@fmmu.edu.cn
  organization: Department of Radiology, Tangdu Hospital, Air Force Medical University, Xi’an, Shaanxi 710038, China
BookMark eNqFkE1OwzAQhS0EEm3hBix8gQTbSZ2EBVJV8SdVYgNry7EnxSWxke0WdccduCEnIWlYsYDVe9LovZn5pujYOgsIXVCSUkL55Sa1sFWuSxlhNCV5Slh2hCa0LFhSspIfowmp2DxhGWWnaBrChhBaUFZNkF9gDTYAVs5aUNE4i8Eqp41df318ahjtMN65djvMZYv7df4g8d35Vxyi36q49YAb53GATtpoVG_WHdgoD6WuwfFl37lOnqGTRrYBzn90hp5vb56W98nq8e5huVglKiM8JrxiOZNK503Fy6as80yWsi7mKisp6FrPOStqTpQGqDLQhDa8AMUIcJIR0DyboauxV3kXgodGKDMeE700raBEDPTERoz0xEBPkFz09Ppw_iv85k0n_f6_2PUYg_6xnQEvgjI9T9DG93SFdubvgm-_yZM3
CitedBy_id crossref_primary_10_1016_j_neucom_2023_03_006
crossref_primary_10_1016_j_imed_2022_06_003
crossref_primary_10_1109_TGRS_2022_3202865
crossref_primary_10_1016_j_displa_2025_103091
crossref_primary_10_1016_j_jmmm_2022_169521
crossref_primary_10_1016_j_neucom_2022_01_044
crossref_primary_10_1021_acs_biomac_4c01193
crossref_primary_10_1016_j_compbiomed_2023_106635
crossref_primary_10_1016_j_engappai_2025_110045
crossref_primary_10_3390_app132111823
crossref_primary_10_3389_fnagi_2022_841297
crossref_primary_10_1007_s40747_023_01103_6
crossref_primary_10_1038_s41598_024_74025_z
Cites_doi 10.1148/rg.317115505
10.1148/radiology.210.3.r99mr07601
10.1109/CISP-BMEI.2017.8302199
10.1016/j.media.2016.05.004
10.1109/ICCEET.2012.6203833
10.1097/JTO.0b013e3181f209ca
10.1109/CVPR.2017.243
10.2352/J.ImagingSci.Technol.2004.48.1.art00007
10.1109/TMI.2011.2168234
10.1007/978-3-030-01234-2_49
10.1016/j.media.2017.06.014
10.1016/j.patrec.2012.09.015
10.1109/CVPR.2016.90
10.1097/RTI.0b013e31828609a0
10.1259/bjr.20180251
10.1109/TMI.2019.2911588
10.1007/978-3-030-00889-5_1
10.1016/j.procs.2018.01.104
10.1097/MD.0000000000020594
10.1109/TMI.2018.2845918
ContentType Journal Article
Copyright 2021 Elsevier B.V.
Copyright_xml – notice: 2021 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2021.04.023
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 11
ExternalDocumentID 10_1016_j_neucom_2021_04_023
S0925231221005506
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c306t-69242acd4f968f8b43a8ab75c381edbd5627b60cdee93ed01f67ec20e6030ed63
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000662813300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Tue Nov 18 20:38:44 EST 2025
Sat Nov 29 07:14:16 EST 2025
Fri Feb 23 02:44:20 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Thymoma
Computed tomography
Image processing
Convolutional neural network
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-69242acd4f968f8b43a8ab75c381edbd5627b60cdee93ed01f67ec20e6030ed63
ORCID 0000-0003-0859-9735
PageCount 11
ParticipantIDs crossref_citationtrail_10_1016_j_neucom_2021_04_023
crossref_primary_10_1016_j_neucom_2021_04_023
elsevier_sciencedirect_doi_10_1016_j_neucom_2021_04_023
PublicationCentury 2000
PublicationDate 2021-09-03
PublicationDateYYYYMMDD 2021-09-03
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-03
  day: 03
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References R.K. Pandey, A. Vasan, A.G. Ramakrishnan, Segmentation of Liver Lesions with Reduced Complexity Deep Models, (2018)
Yang, Y.K. M., C. Zhang, Z. Li, K. Yang, DenseASPP for semantic segmentation in street scenes, IEEE/CVF Conference on Computer Vision and Pattern Recognition.
G. Huang, L. Z, L.V.D. Maaten, K.Q. Weinberger, Densely connected convolutional networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 10.1109/CVPR.2017.243.
S. Angelina, L.P. Suresh, S.H.K. Veni, Image segmentation based on genetic algorithm for region growth and region merging, International Conference on Computing, Electronics and Electrical Technologies IEEE, (IEEE, 2012), pp. 970–974. 10.1109/ICCEET.2012.6203833
Marom (b0005) 2013; 28
Li, Chen, Qi, Dou, Fu, Heng (b0090) 2018; 37
Zhou, Siddiquee, Tajbakhsh, Liang (b0095) 2018; 11045
Li, Gu, Fan, Li, Xiao, Liu (b0110) 2018; 91
Barbu, Suehling, Xu, Liu, Zhou, Comaniciu (b0025) 2012; 31
Liu, Xiao, Liang, Guan (b0060) 2012
Kaur, Soni, Gosain (b0055) 2013; 34
Jiang (b0040) 2006
K. He, Z. X, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, (2016). 10.1109/CVPR.2016.90
X. Gao, Y. Cai, C. Qiu, Y. Cui, Retinal blood vessel segmentation based on the Gaussian matched filter and U-net, 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2017, 1. 10.1109/CISP-BMEI.2017.8302199
Wu, Gil, Deligdisch (b0045) 2004
L. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, (2018).
Uchida, Matsubara, Onuki, Matsuoka, Ichihara, Nakajima (b0105) 2020; 99
Man, Huang, Feng, Li, Wu (b0080) 2019; 38
H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/CVPR.2017.660.
S. Wang, Z. M, Z. Liu, Z. Liu, D. Gu, Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation, Med. Image Anal. (2017) 172–183
B. Ait Skourt, A. El Hassani, A. Majda, Lung CT image segmentation using deep neural networks, Procedia Comput. Sci. 127 (2018) 109–113. 10.1016/j.procs.2018.01.104.
Kong (b0150) 2015; 17
Ibtehaz, Rahman (b0100) 2019
Benveniste, Rosado-de-Christenson, Sabloff, Moran, Swisher, Marom (b0015) 2011; 31
Tang (b0035) 2008
Mayo-Smith, Gupta, Ridlen, Brody, Clements, Cronan (b0115) 1999; 210
Marom (b0010) 2010; 5
Havaei, Davy, Warde-Farley, Biard, Courville, Bengio, Pal, Jodoin, Larochelle (b0020) 2017; 35
Ronneberger, Fischer, Brox (b0065) 2015
L. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking Atrous Convolution for Semantic Image Segmentation, (2017)
Ronneberger (10.1016/j.neucom.2021.04.023_b0065) 2015
10.1016/j.neucom.2021.04.023_b0125
Jiang (10.1016/j.neucom.2021.04.023_b0040) 2006
Havaei (10.1016/j.neucom.2021.04.023_b0020) 2017; 35
10.1016/j.neucom.2021.04.023_b0145
10.1016/j.neucom.2021.04.023_b0085
10.1016/j.neucom.2021.04.023_b0140
Marom (10.1016/j.neucom.2021.04.023_b0010) 2010; 5
10.1016/j.neucom.2021.04.023_b0120
Uchida (10.1016/j.neucom.2021.04.023_b0105) 2020; 99
Mayo-Smith (10.1016/j.neucom.2021.04.023_b0115) 1999; 210
Barbu (10.1016/j.neucom.2021.04.023_b0025) 2012; 31
Zhou (10.1016/j.neucom.2021.04.023_b0095) 2018; 11045
Tang (10.1016/j.neucom.2021.04.023_b0035) 2008
Li (10.1016/j.neucom.2021.04.023_b0090) 2018; 37
Wu (10.1016/j.neucom.2021.04.023_b0045) 2004
Li (10.1016/j.neucom.2021.04.023_b0110) 2018; 91
Man (10.1016/j.neucom.2021.04.023_b0080) 2019; 38
Benveniste (10.1016/j.neucom.2021.04.023_b0015) 2011; 31
10.1016/j.neucom.2021.04.023_b0135
Kong (10.1016/j.neucom.2021.04.023_b0150) 2015; 17
Marom (10.1016/j.neucom.2021.04.023_b0005) 2013; 28
10.1016/j.neucom.2021.04.023_b0030
Liu (10.1016/j.neucom.2021.04.023_b0060) 2012
10.1016/j.neucom.2021.04.023_b0075
10.1016/j.neucom.2021.04.023_b0130
10.1016/j.neucom.2021.04.023_b0070
Ibtehaz (10.1016/j.neucom.2021.04.023_b0100) 2019
10.1016/j.neucom.2021.04.023_b0050
Kaur (10.1016/j.neucom.2021.04.023_b0055) 2013; 34
References_xml – reference: S. Wang, Z. M, Z. Liu, Z. Liu, D. Gu, Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation, Med. Image Anal. (2017) 172–183
– volume: 37
  start-page: 2663
  year: 2018
  end-page: 2674
  ident: b0090
  article-title: H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes
  publication-title: IEEE Trans. Med. Imag.
– reference: X. Gao, Y. Cai, C. Qiu, Y. Cui, Retinal blood vessel segmentation based on the Gaussian matched filter and U-net, 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2017, 1. 10.1109/CISP-BMEI.2017.8302199
– volume: 5
  start-page: S296
  year: 2010
  end-page: S303
  ident: b0010
  article-title: Imaging thymoma
  publication-title: J. Thorac. Oncol.
– volume: 35
  start-page: 18
  year: 2017
  end-page: 31
  ident: b0020
  article-title: Brain tumor segmentation with deep neural networks
  publication-title: Med. Image Anal.
– volume: 28
  start-page: 69
  year: 2013
  ident: b0005
  article-title: Advances in thymoma imaging
  publication-title: J. Thorac. Imag.
– volume: 17
  start-page: 19
  year: 2015
  end-page: 21
  ident: b0150
  article-title: Multi-slice spiral CT in benign and malignant thymoma imaging diagnosis and differential diagnosis
  publication-title: J. Shenyang Med. College
– reference: S. Angelina, L.P. Suresh, S.H.K. Veni, Image segmentation based on genetic algorithm for region growth and region merging, International Conference on Computing, Electronics and Electrical Technologies IEEE, (IEEE, 2012), pp. 970–974. 10.1109/ICCEET.2012.6203833
– volume: 31
  start-page: 1847
  year: 2011
  end-page: 1861
  ident: b0015
  article-title: Role of imaging in the diagnosis, staging, and treatment of thymoma
  publication-title: Radiographics
– reference: R.K. Pandey, A. Vasan, A.G. Ramakrishnan, Segmentation of Liver Lesions with Reduced Complexity Deep Models, (2018)
– year: 2008
  ident: b0035
  article-title: Fast image segmentation method based on threshold
  publication-title: Control Decis. Conf.
– reference: B. Ait Skourt, A. El Hassani, A. Majda, Lung CT image segmentation using deep neural networks, Procedia Comput. Sci. 127 (2018) 109–113. 10.1016/j.procs.2018.01.104.
– reference: K. He, Z. X, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, (2016). 10.1109/CVPR.2016.90
– volume: 31
  start-page: 240
  year: 2012
  end-page: 250
  ident: b0025
  article-title: Automatic detection and segmentation of lymph nodes from CT data
  publication-title: IEEE Trans. Med. Imag.
– volume: 11045
  start-page: 3
  year: 2018
  end-page: 11
  ident: b0095
  article-title: UNet++: a nested U-Net architecture for medical image segmentation
  publication-title: Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support
– reference: H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/CVPR.2017.660.
– reference: Yang, Y.K. M., C. Zhang, Z. Li, K. Yang, DenseASPP for semantic segmentation in street scenes, IEEE/CVF Conference on Computer Vision and Pattern Recognition.
– start-page: 22
  year: 2004
  end-page: 27
  ident: b0045
  article-title: Region growing segmentation of chromatin clumps of ovarian cells using adaptive gradients
  publication-title: J. Imag. Sci. Technol.
– start-page: 74
  year: 2019
  end-page: 87
  ident: b0100
  article-title: MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation
  publication-title: Neural Networks
– reference: G. Huang, L. Z, L.V.D. Maaten, K.Q. Weinberger, Densely connected convolutional networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 10.1109/CVPR.2017.243.
– volume: 34
  start-page: 163
  year: 2013
  end-page: 175
  ident: b0055
  article-title: RETRACTED: A robust kernelized intuitionistic fuzzy c-means clustering algorithm in segmentation of noisy medical images
  publication-title: Pattern Recogn. Lett.
– reference: L. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, (2018).
– start-page: 398
  year: 2006
  end-page: 401
  ident: b0040
  article-title: Medical image segmentation based on improved ostu algorithm and regional growth algorithm
  publication-title: J. Northeastern Univ.
– volume: 210
  start-page: 601
  year: 1999
  end-page: 604
  ident: b0115
  article-title: Detecting hepatic lesions: the added utility of CT liver window settings
  publication-title: Radiology
– start-page: 234
  year: 2015
  end-page: 241
  ident: b0065
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Med. Image Comput. Comput. Assist. Intervent. (MICCAI)
– volume: 99
  year: 2020
  ident: b0105
  article-title: Efficacy of measuring the invasive diameter of lung adenocarcinoma using mediastinal window settings
  publication-title: Medicine
– volume: 91
  start-page: 20180251
  year: 2018
  ident: b0110
  article-title: Effect of CT window settings on size measurements of the solid component in subsolid nodules: evaluation of prediction efficacy of the degree of pathological malignancy in lung adenocarcinoma
  publication-title: Br. J. Radiol.
– volume: 38
  start-page: 1971
  year: 2019
  end-page: 1980
  ident: b0080
  article-title: Deep Q learning driven CT pancreas segmentation with geometry-aware U-Net
  publication-title: IEEE Trans. Med. Imag.
– reference: L. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking Atrous Convolution for Semantic Image Segmentation, (2017)
– start-page: 221
  year: 2012
  end-page: 230
  ident: b0060
  publication-title: Fuzzy C-means Clustering with Bilateral Filtering for Medical Image Segmentation
– volume: 31
  start-page: 1847
  year: 2011
  ident: 10.1016/j.neucom.2021.04.023_b0015
  article-title: Role of imaging in the diagnosis, staging, and treatment of thymoma
  publication-title: Radiographics
  doi: 10.1148/rg.317115505
– year: 2008
  ident: 10.1016/j.neucom.2021.04.023_b0035
  article-title: Fast image segmentation method based on threshold
  publication-title: Control Decis. Conf.
– volume: 210
  start-page: 601
  year: 1999
  ident: 10.1016/j.neucom.2021.04.023_b0115
  article-title: Detecting hepatic lesions: the added utility of CT liver window settings
  publication-title: Radiology
  doi: 10.1148/radiology.210.3.r99mr07601
– ident: 10.1016/j.neucom.2021.04.023_b0145
– ident: 10.1016/j.neucom.2021.04.023_b0070
  doi: 10.1109/CISP-BMEI.2017.8302199
– volume: 35
  start-page: 18
  year: 2017
  ident: 10.1016/j.neucom.2021.04.023_b0020
  article-title: Brain tumor segmentation with deep neural networks
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2016.05.004
– ident: 10.1016/j.neucom.2021.04.023_b0140
– ident: 10.1016/j.neucom.2021.04.023_b0050
  doi: 10.1109/ICCEET.2012.6203833
– volume: 5
  start-page: S296
  year: 2010
  ident: 10.1016/j.neucom.2021.04.023_b0010
  article-title: Imaging thymoma
  publication-title: J. Thorac. Oncol.
  doi: 10.1097/JTO.0b013e3181f209ca
– ident: 10.1016/j.neucom.2021.04.023_b0085
– ident: 10.1016/j.neucom.2021.04.023_b0125
  doi: 10.1109/CVPR.2017.243
– start-page: 22
  year: 2004
  ident: 10.1016/j.neucom.2021.04.023_b0045
  article-title: Region growing segmentation of chromatin clumps of ovarian cells using adaptive gradients
  publication-title: J. Imag. Sci. Technol.
  doi: 10.2352/J.ImagingSci.Technol.2004.48.1.art00007
– start-page: 74
  year: 2019
  ident: 10.1016/j.neucom.2021.04.023_b0100
  article-title: MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation
  publication-title: Neural Networks
– volume: 31
  start-page: 240
  year: 2012
  ident: 10.1016/j.neucom.2021.04.023_b0025
  article-title: Automatic detection and segmentation of lymph nodes from CT data
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2011.2168234
– start-page: 398
  year: 2006
  ident: 10.1016/j.neucom.2021.04.023_b0040
  article-title: Medical image segmentation based on improved ostu algorithm and regional growth algorithm
  publication-title: J. Northeastern Univ.
– ident: 10.1016/j.neucom.2021.04.023_b0130
  doi: 10.1007/978-3-030-01234-2_49
– ident: 10.1016/j.neucom.2021.04.023_b0135
  doi: 10.1007/978-3-030-01234-2_49
– ident: 10.1016/j.neucom.2021.04.023_b0030
  doi: 10.1016/j.media.2017.06.014
– volume: 34
  start-page: 163
  year: 2013
  ident: 10.1016/j.neucom.2021.04.023_b0055
  article-title: RETRACTED: A robust kernelized intuitionistic fuzzy c-means clustering algorithm in segmentation of noisy medical images
  publication-title: Pattern Recogn. Lett.
  doi: 10.1016/j.patrec.2012.09.015
– ident: 10.1016/j.neucom.2021.04.023_b0120
  doi: 10.1109/CVPR.2016.90
– start-page: 234
  year: 2015
  ident: 10.1016/j.neucom.2021.04.023_b0065
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Med. Image Comput. Comput. Assist. Intervent. (MICCAI)
– volume: 28
  start-page: 69
  year: 2013
  ident: 10.1016/j.neucom.2021.04.023_b0005
  article-title: Advances in thymoma imaging
  publication-title: J. Thorac. Imag.
  doi: 10.1097/RTI.0b013e31828609a0
– volume: 91
  start-page: 20180251
  year: 2018
  ident: 10.1016/j.neucom.2021.04.023_b0110
  article-title: Effect of CT window settings on size measurements of the solid component in subsolid nodules: evaluation of prediction efficacy of the degree of pathological malignancy in lung adenocarcinoma
  publication-title: Br. J. Radiol.
  doi: 10.1259/bjr.20180251
– volume: 38
  start-page: 1971
  year: 2019
  ident: 10.1016/j.neucom.2021.04.023_b0080
  article-title: Deep Q learning driven CT pancreas segmentation with geometry-aware U-Net
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2019.2911588
– start-page: 221
  year: 2012
  ident: 10.1016/j.neucom.2021.04.023_b0060
– volume: 11045
  start-page: 3
  year: 2018
  ident: 10.1016/j.neucom.2021.04.023_b0095
  article-title: UNet++: a nested U-Net architecture for medical image segmentation
  publication-title: Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support
  doi: 10.1007/978-3-030-00889-5_1
– ident: 10.1016/j.neucom.2021.04.023_b0075
  doi: 10.1016/j.procs.2018.01.104
– volume: 99
  year: 2020
  ident: 10.1016/j.neucom.2021.04.023_b0105
  article-title: Efficacy of measuring the invasive diameter of lung adenocarcinoma using mediastinal window settings
  publication-title: Medicine
  doi: 10.1097/MD.0000000000020594
– volume: 37
  start-page: 2663
  year: 2018
  ident: 10.1016/j.neucom.2021.04.023_b0090
  article-title: H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes
  publication-title: IEEE Trans. Med. Imag.
  doi: 10.1109/TMI.2018.2845918
– volume: 17
  start-page: 19
  year: 2015
  ident: 10.1016/j.neucom.2021.04.023_b0150
  article-title: Multi-slice spiral CT in benign and malignant thymoma imaging diagnosis and differential diagnosis
  publication-title: J. Shenyang Med. College
SSID ssj0017129
Score 2.4093864
Snippet •Three-channel pseudo-color images preprocessing method is designed by concatenating different CT windows.•A dense skip connection encoding–decoding model...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Computed tomography
Convolutional neural network
Image processing
Thymoma
Title A dense connection encoding–decoding convolutional neural network structure for semantic segmentation of thymoma
URI https://dx.doi.org/10.1016/j.neucom.2021.04.023
Volume 451
WOSCitedRecordID wos000662813300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbtswECXcpIdeuhdNN_DQW8BCK0kdhSJdgiAo0LTVTRDFUWHDloMkDpJb_yFfkF_rl3S4yXZTpM2hF1kgJGqZ55kh9fiGkNdCapVkHWc80jnLMONmTS45ayREXOdK5bbG0tc9sb8vq6r4NBpdhrUwp1PR9_LsrDj8r6bGNjS2WTp7A3MPnWID7qPRcYtmx-0_Gb7cRlfiSOg9uELgRqzSxKjAbEg1uAZLOvd3g7Yy4pb2x1LDt522rPnCYLiIxzBDK4xb3Pk-8yuWekcxOJ_NvXufBDGoBQZGWzDCT0WUM6PIoA38hqmHPcsk2MUjzhdLkH5eWEf4Dfqu8WHVpqrOKVXjxXS-bK58SZb34VA_gZHElqGVrs5EJjnDNHPNKWdehta51XglPjvffMXzu0mIyRt8U4YGZC5kNWzdauZ1oe3fAuBASwyMt0nteqlNL3WU1djLLbKZiLxAx7lZftypdodPVSJOnKCjf4qwPtOSCK_ezZ_zn5Wc5uA-uesHI7R0IHpARtA_JPdCoQ_q_f4jclRSiym6xBQNmPr54yKgia6hiTo0UY8mOqCJIppoQBNdRROdd9Sj6TH58m7n4O0H5ot1sBZHnSeM40A-aVqddQWXnVRZ2shGibzFlBC00phnC8WjVgMUKego7riANomAY5gBzdMnZKOf9_CUUC21jCDOQSjIRJcp2aaY-GrMTZURYNwiaXiFdeuV7E1BlWl9nQG3CBvOOnRKLn85XgTr1D4bdVlmjZC79sxnN7zSc3Jn-b94QTbQHPCS3G5PT8bHR6883n4B2mK0OA
linkProvider Elsevier
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=A+dense+connection+encoding%E2%80%93decoding+convolutional+neural+network+structure+for+semantic+segmentation+of+thymoma&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Li%2C+Jingyuan&rft.au=Sun%2C+Wenfang&rft.au=Feng%2C+Xiulong&rft.au=Xing%2C+Gang&rft.date=2021-09-03&rft.issn=0925-2312&rft.volume=451&rft.spage=1&rft.epage=11&rft_id=info:doi/10.1016%2Fj.neucom.2021.04.023&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2021_04_023
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon