FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics

Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that requi...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in computer science (Lausanne) Vol. 3
Main Authors: Quan, Tran Minh, Hildebrand, David Grant Colburn, Jeong, Won-Ki
Format: Journal Article
Language:English
Published: Frontiers Media S.A 13.05.2021
Subjects:
ISSN:2624-9898, 2624-9898
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that require minimal user intervention. Deep learning has provided exceptional performance in image classification tasks in computer vision, leading to a recent explosion in popularity. Similarly, its application to connectomic analyses holds great promise. Here, we introduce a deep neural network architecture, FusionNet, with a focus on its application to accomplish automatic segmentation of neuronal structures in connectomics data. FusionNet combines recent advances in machine learning, such as semantic segmentation and residual neural networks, with summation-based skip connections. This results in a much deeper network architecture and improves segmentation accuracy. We demonstrate the performance of the proposed method by comparing it with several other popular electron microscopy segmentation methods. We further illustrate its flexibility through segmentation results for two different tasks: cell membrane segmentation and cell nucleus segmentation.
AbstractList Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in connectomics research is developing scalable image analysis algorithms that require minimal user intervention. Deep learning has provided exceptional performance in image classification tasks in computer vision, leading to a recent explosion in popularity. Similarly, its application to connectomic analyses holds great promise. Here, we introduce a deep neural network architecture, FusionNet, with a focus on its application to accomplish automatic segmentation of neuronal structures in connectomics data. FusionNet combines recent advances in machine learning, such as semantic segmentation and residual neural networks, with summation-based skip connections. This results in a much deeper network architecture and improves segmentation accuracy. We demonstrate the performance of the proposed method by comparing it with several other popular electron microscopy segmentation methods. We further illustrate its flexibility through segmentation results for two different tasks: cell membrane segmentation and cell nucleus segmentation.
Author Jeong, Won-Ki
Quan, Tran Minh
Hildebrand, David Grant Colburn
Author_xml – sequence: 1
  givenname: Tran Minh
  surname: Quan
  fullname: Quan, Tran Minh
– sequence: 2
  givenname: David Grant Colburn
  surname: Hildebrand
  fullname: Hildebrand, David Grant Colburn
– sequence: 3
  givenname: Won-Ki
  surname: Jeong
  fullname: Jeong, Won-Ki
BookMark eNp1kF1LwzAUhoNMcM79AO_yBzaTtGkT78Z0OhgT_LgOaZqMzLYZSars39uuCiJ4dT44z3vOeS_BqHGNBuAao3mSMH5jlKsPc4IInmc44QyfgTHJSDrjjLPRr_wCTEPYI4QIxZiyfAzKVRusa7Y63sIFvNP6AFdtVR3hsw62bGUFl675cFUbu6mu2urWn0L8dP4dGufhupY7DV_0rtZNlP0ctE2PNVpFV1sVrsC5kVXQ0-84AW-r-9fl42zz9LBeLjYzlRIUZ4xihDKaJoVMiixVhiqJqDQM0xxrwhnNSEkKYigvjDEZxiSlElOT5IjLjpuA9aBbOrkXB29r6Y_CSStODed3QvpoVaWFpAaxkhptCpVSWvCi347z0iiUd5s6rXzQUt6F4LURyg7fRS9tJTASvffi5L3ovReD9x2J_5A_l_zPfAFXBIqw
CitedBy_id crossref_primary_10_1016_j_eswa_2024_124783
crossref_primary_10_3390_geomatics5010009
crossref_primary_10_1109_JSTARS_2024_3518460
crossref_primary_10_1016_j_patcog_2023_109788
crossref_primary_10_3390_rs16224201
crossref_primary_10_1109_TUFFC_2022_3219401
crossref_primary_10_1016_j_cag_2025_104239
crossref_primary_10_3390_su16010117
crossref_primary_10_1111_cgf_14574
crossref_primary_10_1117_1_JMI_11_2_024009
crossref_primary_10_1007_s11042_024_19976_1
crossref_primary_10_1007_s11042_023_16991_6
crossref_primary_10_1016_j_jncc_2024_12_006
crossref_primary_10_1016_j_optlastec_2025_113097
crossref_primary_10_1002_aisy_202300745
crossref_primary_10_53941_aim_2025_100004
crossref_primary_10_1109_JBHI_2022_3207874
crossref_primary_10_1109_ACCESS_2025_3585064
crossref_primary_10_1016_j_cag_2025_104391
crossref_primary_10_1109_TAI_2024_3418378
crossref_primary_10_1016_j_inffus_2024_102369
crossref_primary_10_3389_fped_2024_1338131
crossref_primary_10_1007_s11042_024_20145_7
crossref_primary_10_1016_j_neucom_2024_127737
crossref_primary_10_3389_fphys_2022_918381
crossref_primary_10_1016_j_compag_2024_109560
crossref_primary_10_1134_S0361768822030057
crossref_primary_10_3390_ai4010009
crossref_primary_10_1145_3632956
crossref_primary_10_3390_en18174523
crossref_primary_10_1007_s40766_025_00073_4
crossref_primary_10_3390_app11157046
crossref_primary_10_1007_s00371_024_03499_9
crossref_primary_10_3389_fncom_2024_1423051
crossref_primary_10_1016_j_procs_2025_04_467
crossref_primary_10_1093_bjr_tqae076
crossref_primary_10_1007_s00138_023_01418_x
crossref_primary_10_3390_su16114409
crossref_primary_10_1109_TMI_2024_3474028
crossref_primary_10_3390_app131910798
crossref_primary_10_3390_s22020523
crossref_primary_10_1038_s41598_024_79305_2
crossref_primary_10_7717_peerj_cs_2180
crossref_primary_10_3389_fphar_2022_1080273
crossref_primary_10_3390_rs15071821
crossref_primary_10_1109_TGRS_2023_3281490
crossref_primary_10_1109_ACCESS_2023_3305270
crossref_primary_10_1109_TGRS_2023_3314586
crossref_primary_10_1007_s10278_024_01299_0
crossref_primary_10_1109_TITS_2023_3266776
crossref_primary_10_4103_ATMR_ATMR_27_25
crossref_primary_10_1080_15481603_2023_2270806
crossref_primary_10_1093_jmicro_dfab043
crossref_primary_10_1109_ACCESS_2021_3084066
crossref_primary_10_1016_j_csbj_2022_08_024
crossref_primary_10_1016_j_cag_2024_104105
crossref_primary_10_1155_2024_9422083
crossref_primary_10_1115_1_4068665
crossref_primary_10_3390_ijms26094346
crossref_primary_10_1007_s11042_023_16627_9
crossref_primary_10_1007_s11704_022_2015_7
crossref_primary_10_1109_ACCESS_2024_3508748
crossref_primary_10_3389_fimmu_2023_1111172
crossref_primary_10_1007_s11242_022_01833_0
crossref_primary_10_3233_JIFS_236286
crossref_primary_10_1016_j_eswa_2024_126370
crossref_primary_10_3389_fonc_2023_1064548
Cites_doi 10.3389/fnana.2018.00112
10.1038/nature14539
10.1038/nmeth.2476
10.1109/TPAMI.2020.2980827
10.1016/j.media.2015.02.001
10.1007/s11263-015-0816-y
10.3389/fnana.2015.00142
10.1109/tmi.2016.2613019
10.1038/nature09818
10.1109/tmi.2018.2820120
10.1016/j.procs.2016.09.407
10.1109/MCG.2010.56
10.1038/nmeth.4151
10.1371/journal.pbio.1000502
10.1126/science.1209168
10.1038/nature22356
10.1016/j.conb.2011.10.022
10.1038/nmeth.2019
10.1093/bioinformatics/btw165
10.3389/fncir.2014.00068
10.3389/fcomp.2019.00006
10.1007/978-0-387-49765-5
10.1162/neco.2009.10-08-881
10.1016/j.cell.2018.06.019
10.1038/nature09802
10.1371/journal.pone.0038011
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.3389/fcomp.2021.613981
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals - NZ
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2624-9898
ExternalDocumentID oai_doaj_org_article_a5f08d5fefbc455b9b851017dfc07985
10_3389_fcomp_2021_613981
GroupedDBID 9T4
AAFWJ
AAYXX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
M~E
OK1
ID FETCH-LOGICAL-c420t-851006543ba3b64cf5ca05af81571e298562d2b2f59bfff611245a15f3709a543
IEDL.DBID DOA
ISICitedReferencesCount 77
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000657669900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2624-9898
IngestDate Fri Oct 03 12:21:28 EDT 2025
Tue Nov 18 22:37:04 EST 2025
Sat Nov 29 02:11:55 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c420t-851006543ba3b64cf5ca05af81571e298562d2b2f59bfff611245a15f3709a543
OpenAccessLink https://doaj.org/article/a5f08d5fefbc455b9b851017dfc07985
ParticipantIDs doaj_primary_oai_doaj_org_article_a5f08d5fefbc455b9b851017dfc07985
crossref_citationtrail_10_3389_fcomp_2021_613981
crossref_primary_10_3389_fcomp_2021_613981
PublicationCentury 2000
PublicationDate 2021-05-13
PublicationDateYYYYMMDD 2021-05-13
PublicationDate_xml – month: 05
  year: 2021
  text: 2021-05-13
  day: 13
PublicationDecade 2020
PublicationTitle Frontiers in computer science (Lausanne)
PublicationYear 2021
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References B21
Bock (B4) 2011; 471
Ciresan (B13) 2012
Wu (B55) 2015
LeCun (B32) 2015; 521
Pape (B37) 2019; 1
Zeiler (B57) 2014
Ensafi (B16) 2014
Shapira (B43) 2008
Chen (B10) 2016
Quan (B40) 2018; 37
Wetzel (B52) 2016
Fakhry (B18) 2017; 36
He (B23) 2016
Drozdzal (B14) 2016
Arganda-Carreras (B1) 2015; 910
Long (B36) 2015
Sommer (B47) 2011
Zhu (B60) 2019
Beier (B3) 2017; 14
Fakhry (B17) 2016; 32
Hayworth (B22) 2014; 8
Hildebrand (B25) 2015
Chen (B9) 2016
Hildebrand (B26) 2017; 545
Briggman (B6) 2011; 471
Weiler (B51) 2017
Cicek (B12) 2016
Parag (B38) 2015
Helmstaedter (B24) 2013; 10
Isin (B28) 2016; 102
Hirsch (B27) 2020
Lichtman (B34) 2011; 334
Cardona (B8) 2012; 7
Wolf (B54) 2019
Wiehman (B53) 2016
Schindelin (B44) 2012; 9
Ronneberger (B41) 2015
Cardona (B7) 2010; 8
Gatys (B20) 2016
Quan (B39) 2016
Turaga (B50) 2010; 22
B11
Stollenga (B48) 2015
Krizhevsky (B31) 2012
Zheng (B59) 2018; 174
Szegedy (B49) 2015
Shen (B45) 2017
Simonyan (B46) 2014
Eberle (B15) 2018; 12
Lee (B33) 2018
Lin (B35) 2014
Zheng (B58) 2015
Beier (B2) 2016
Briggman (B5) 2012; 22
Jeong (B29) 2010; 30
Russakovsky (B42) 2015; 115
Xiao (B56) 2018
Kaynig (B30) 2015; 22
References_xml – year: 2014
  ident: B35
  article-title: Network in Network
– start-page: 1
  year: 2016
  ident: B52
  article-title: Registering Large Volume Serial-Section Electron Microscopy Image Sets for Neural Circuit Reconstruction Using FFT Signal Whitening
– volume: 12
  start-page: 112
  year: 2018
  ident: B15
  article-title: Multi-Beam Scanning Electron Microscopy for High-Throughput Imaging in Connectomics Research
  publication-title: Front. Neuroanat.
  doi: 10.3389/fnana.2018.00112
– volume: 521
  start-page: 436
  year: 2015
  ident: B32
  article-title: Deep Learning
  publication-title: Nature
  doi: 10.1038/nature14539
– start-page: 2391
  year: 2017
  ident: B45
  article-title: Multi-stage Multi-Recursive-Input Fully Convolutional Networks for Neuronal Boundary Detection
– start-page: 565
  year: 2015
  ident: B58
  article-title: 3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data
– volume: 10
  start-page: 501
  year: 2013
  ident: B24
  article-title: Cellular-Resolution Connectomics: Challenges of Dense Neural Circuit Reconstruction
  publication-title: Nat. Methods
  doi: 10.1038/nmeth.2476
– year: 2014
  ident: B46
  article-title: Very Deep Convolutional Networks for Large-Scale Image Recognition
– year: 2019
  ident: B54
  article-title: The Mutex Watershed and its Objective: Efficient, Parameter-Free Image Partitioning
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.2980827
– volume: 22
  start-page: 77
  year: 2015
  ident: B30
  article-title: Large-scale Automatic Reconstruction of Neuronal Processes From Electron Microscopy Images
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2015.02.001
– ident: B21
– volume: 115
  start-page: 211
  year: 2015
  ident: B42
  article-title: ImageNet Large Scale Visual Recognition Challenge
  publication-title: Int. J. Comput. Vision
  doi: 10.1007/s11263-015-0816-y
– start-page: 2843
  year: 2012
  ident: B13
  article-title: Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images
– volume: 910
  start-page: 142
  year: 2015
  ident: B1
  article-title: Crowdsourcing the Creation of Image Segmentation Algorithms for Connectomics
  publication-title: Front. Neuroanat.
  doi: 10.3389/fnana.2015.00142
– start-page: 624
  year: 2016
  ident: B53
  article-title: Semantic Segmentation of Bioimages Using Convolutional Neural Networks
– volume: 36
  start-page: 447
  year: 2017
  ident: B18
  article-title: Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/tmi.2016.2613019
– volume: 471
  start-page: 183
  year: 2011
  ident: B6
  article-title: Wiring Specificity in the Direction-Selectivity Circuit of the Retina
  publication-title: Nature
  doi: 10.1038/nature09818
– start-page: 770
  year: 2016
  ident: B23
  article-title: Deep Residual Learning for Image Recognition
– start-page: 3036
  year: 2016
  ident: B10
  article-title: Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
– volume: 37
  start-page: 1488
  year: 2018
  ident: B40
  article-title: Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/tmi.2018.2820120
– volume: 102
  start-page: 317
  year: 2016
  ident: B28
  article-title: Review of MRI-Based Brain Tumor Image Segmentation Using Deep Learning Methods
  publication-title: Procedia Comput. Sci.
  doi: 10.1016/j.procs.2016.09.407
– volume: 30
  start-page: 58
  year: 2010
  ident: B29
  article-title: Secrett and NeuroTrace: Interactive Visualization and Analysis Tools for Large-Scale Neuroscience Data Sets
  publication-title: IEEE Comput. Graphics Appl.
  doi: 10.1109/MCG.2010.56
– volume: 14
  start-page: 101
  year: 2017
  ident: B3
  article-title: Multicut Brings Automated Neurite Segmentation Closer to Human Performance
  publication-title: Nat. Methods
  doi: 10.1038/nmeth.4151
– start-page: 6732
  year: 2014
  ident: B16
  article-title: 3D Reconstruction of Neurons in Electron Microscopy Images
– volume: 8
  start-page: e1000502
  year: 2010
  ident: B7
  article-title: An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy
  publication-title: PLoS Biol.
  doi: 10.1371/journal.pbio.1000502
– volume: 334
  start-page: 618
  year: 2011
  ident: B34
  article-title: The Big and the Small: Challenges of Imaging the Brain’s Circuits
  publication-title: Science
  doi: 10.1126/science.1209168
– year: 2015
  ident: B25
  article-title: Whole-Brain Functional and Structural Examination in Larval Zebrafish
– year: 2016
  ident: B39
  article-title: FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics
– start-page: 818
  year: 2014
  ident: B57
  article-title: Visualizing and Understanding Convolutional Networks
– start-page: 179
  year: 2016
  ident: B14
  article-title: The Importance of Skip Connections in Biomedical Image Segmentation
– start-page: 288
  year: 2020
  ident: B27
  article-title: Patchperpix for Instance Segmentation
– start-page: 715
  year: 2016
  ident: B2
  article-title: An Efficient Fusion Move Algorithm for the Minimum Cost Lifted Multicut Problem
– volume: 545
  start-page: 345
  year: 2017
  ident: B26
  article-title: Whole-Brain Serial-Section Electron Microscopy in Larval Zebrafish
  publication-title: Nature
  doi: 10.1038/nature22356
– volume: 22
  start-page: 154
  year: 2012
  ident: B5
  article-title: Volume Electron Microscopy for Neuronal Circuit Reconstruction
  publication-title: Curr. Opin. Neurobiol.
  doi: 10.1016/j.conb.2011.10.022
– start-page: 849
  year: 2017
  ident: B51
  article-title: Learning Steerable Filters for Rotation Equivariant cnns
– volume: 9
  start-page: 676
  year: 2012
  ident: B44
  article-title: Fiji: an Open-Source Platform for Biological-Image Analysis
  publication-title: Nat. Methods
  doi: 10.1038/nmeth.2019
– volume: 32
  start-page: 2352
  year: 2016
  ident: B17
  article-title: Deep Models for Brain EM Image Segmentation: Novel Insights and Improved Performance
  publication-title: Bioinformatics
  doi: 10.1093/bioinformatics/btw165
– start-page: 424
  year: 2016
  ident: B12
  article-title: 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
– start-page: 378
  year: 2018
  ident: B56
  article-title: Deep Contextual Residual Network for Electron Microscopy Image Segmentation in Connectomics
– start-page: 2998
  year: 2015
  ident: B48
  article-title: Parallel Multi-Dimensional LSTM, with Application to Fast Biomedical Volumetric Image Segmentation
– start-page: 230
  year: 2011
  ident: B47
  article-title: Ilastik: Interactive Learning and Segmentation Toolkit
– volume: 8
  start-page: 68
  year: 2014
  ident: B22
  article-title: Imaging ATUM Ultrathin Section Libraries With WaferMapper: A Multi-Scale Approach to EM Reconstruction of Neural Circuits
  publication-title: Front. Neural Circuits
  doi: 10.3389/fncir.2014.00068
– start-page: 1
  year: 2015
  ident: B49
  article-title: Going Deeper with Convolutions
– start-page: 712
  year: 2019
  ident: B60
  article-title: Ace-net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
– volume: 1
  start-page: 657
  year: 2019
  ident: B37
  article-title: Leveraging Domain Knowledge to Improve Microscopy Image Segmentation with Lifted Multicuts
  publication-title: Front. Comput. Sci.
  doi: 10.3389/fcomp.2019.00006
– volume-title: Matrix-Based Multigrid
  year: 2008
  ident: B43
  doi: 10.1007/978-0-387-49765-5
– year: 2015
  ident: B55
  article-title: An Iterative Convolutional Neural Network Algorithm Improves Electron Microscopy Image Segmentation
– start-page: 234
  year: 2015
  ident: B41
  article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation
– start-page: 1097
  year: 2012
  ident: B31
  article-title: ImageNet Classification With Deep Convolutional Neural Networks
– start-page: 3431
  year: 2015
  ident: B36
  article-title: Fully Convolutional Networks for Semantic Segmentation
– ident: B11
– start-page: 657
  year: 2015
  ident: B38
  article-title: Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation
– volume: 22
  start-page: 511
  year: 2010
  ident: B50
  article-title: Convolutional Networks can Learn to Generate Affinity Graphs for Image Segmentation
  publication-title: Neural Comput.
  doi: 10.1162/neco.2009.10-08-881
– volume: 174
  start-page: 730
  year: 2018
  ident: B59
  article-title: A Complete Electron Microscopy Volume of the Brain of Adult drosophila Melanogaster
  publication-title: Cell
  doi: 10.1016/j.cell.2018.06.019
– start-page: 2414
  year: 2016
  ident: B20
  article-title: Image Style Transfer Using Convolutional Neural Networks
– start-page: 1167
  year: 2016
  ident: B9
  article-title: Deep Contextual Networks for Neuronal Structure Segmentation
– start-page: 335
  year: 2018
  ident: B33
  article-title: DeepHCS: Bright-Field to Fluorescence Microscopy Image Conversion Using Deep Learning for Label-Free High-Content Screening
– volume: 471
  start-page: 177
  year: 2011
  ident: B4
  article-title: Network Anatomy and In Vivo Physiology of Visual Cortical Neurons
  publication-title: Nature
  doi: 10.1038/nature09802
– volume: 7
  start-page: e38011
  year: 2012
  ident: B8
  article-title: TrakEM2 Software for Neural Circuit Reconstruction
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0038011
SSID ssj0002511587
Score 2.4442847
Snippet Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput,...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
SubjectTerms connectomic analysis
deep learning
image segementation
refinement
skip connection
Title FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics
URI https://doaj.org/article/a5f08d5fefbc455b9b851017dfc07985
Volume 3
WOSCitedRecordID wos000657669900001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals - NZ
  customDbUrl:
  eissn: 2624-9898
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511587
  issn: 2624-9898
  databaseCode: DOA
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2624-9898
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511587
  issn: 2624-9898
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQxcDCG1Fe8sCEFOrEcWKzFWgFElSIl7pFsWujSjStaEBi4bdz56RVWWBhSZzIsazvLvZdcvcdIceKO56kHCy30PEgBgcjkLmIAwVN45gW1ldreL5Jez3Z76u7hVJfGBNW0QNXwLVy4ZgcCGedNrEQWmnp1WjgDEuV9Oyl0FhwpnANRsNZyLT6jQlemGo5DNEGfzAKT2EHUzL8sREt8PX7jaW7TlZri5C2q5lskCVbbJK1WbUFWr98W2TQfccvWz1bntE2vbR2QtF__KT3duozqujFuPioNQmukHbDn3ycNwXjlF6PYPWgD_ZlVGccFXRYUB_rYkpMT55uk6du5_HiKqhrJAQmjlgZIBg-P1TnXCexccLkTOROhiINbQQAJdEg0pETSjvnEjCvYpGHwvGUKRAK3yGNYlzYXUK1BLGBTDnTEikLFeM8BouB29QlhidNwmaAZaYmEMc6Fq8ZOBKIceYxzhDjrMK4SU7mj0wq9ozfOp-jFOYdkfja3wB1yGp1yP5Sh73_GGSfrOC8MEgg5AekUb6920OybD7K4fTtyGsaHG-_Ot-yrti0
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=FusionNet%3A+A+Deep+Fully+Residual+Convolutional+Neural+Network+for+Image+Segmentation+in+Connectomics&rft.jtitle=Frontiers+in+computer+science+%28Lausanne%29&rft.au=Tran+Minh+Quan&rft.au=David+Grant+Colburn+Hildebrand&rft.au=Won-Ki+Jeong&rft.date=2021-05-13&rft.pub=Frontiers+Media+S.A&rft.eissn=2624-9898&rft.volume=3&rft_id=info:doi/10.3389%2Ffcomp.2021.613981&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_a5f08d5fefbc455b9b851017dfc07985
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2624-9898&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2624-9898&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2624-9898&client=summon