Capsules for biomedical image segmentation

•First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel deconvolutional capsules to create encoder-decoder architecture.•Extended the reconstruction regularization to the segmentation task.•Outperforme...

Full description

Saved in:

Bibliographic Details
Published in:	Medical image analysis Vol. 68; p. 101889
Main Authors:	LaLonde, Rodney, Xu, Ziyue, Irmakci, Ismail, Jain, Sanjay, Bagci, Ulas
Format:	Journal Article
Language:	English
Published:	Netherlands Elsevier B.V 01.02.2021 Elsevier BV
Subjects:	Ablation Capsule network Capsules Coders Computed tomography Datasets Encoders-Decoders Experiments Humans Image processing Image Processing, Computer-Assisted Image reconstruction Image segmentation Lung segmentation Lungs Magnetic Resonance Imaging Medical imaging Muscles Neural Networks, Computer Parameters Pre-clinical imaging Regularization Routing Thigh MRI segmentation Thorax Tomography Tomography, X-Ray Computed Lung segmentation Pre-clinical imaging Capsule network Thigh MRI segmentation
ISSN:	1361-8415, 1361-8423, 1361-8423
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	•First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel deconvolutional capsules to create encoder-decoder architecture.•Extended the reconstruction regularization to the segmentation task.•Outperformed existing methods across five clinical and preclinical datasets for lung segmentation from CT scans. [Display omitted] Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of “deconvolutional” capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects’ thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules’ ability to generalize to unseen handling of rotations/reflections on natural images.
AbstractList	Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of "deconvolutional" capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects' thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules' ability to generalize to unseen handling of rotations/reflections on natural images.Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of "deconvolutional" capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects' thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules' ability to generalize to unseen handling of rotations/reflections on natural images. Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of “deconvolutional” capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects’ thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules’ ability to generalize to unseen handling of rotations/reflections on natural images. •First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel deconvolutional capsules to create encoder-decoder architecture.•Extended the reconstruction regularization to the segmentation task.•Outperformed existing methods across five clinical and preclinical datasets for lung segmentation from CT scans. [Display omitted] Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of “deconvolutional” capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects’ thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules’ ability to generalize to unseen handling of rotations/reflections on natural images.
ArticleNumber	101889
Author	Irmakci, Ismail Jain, Sanjay Xu, Ziyue LaLonde, Rodney Bagci, Ulas
AuthorAffiliation	a Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL b Nvidia, Bethesda, MD c Ege University, Izmir, Turkey d Johns Hopkins University, Baltimore, MD
AuthorAffiliation_xml	– name: b Nvidia, Bethesda, MD – name: c Ege University, Izmir, Turkey – name: d Johns Hopkins University, Baltimore, MD – name: a Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL
Author_xml	– sequence: 1 givenname: Rodney surname: LaLonde fullname: LaLonde, Rodney organization: Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL – sequence: 2 givenname: Ziyue orcidid: 0000-0002-5728-6869 surname: Xu fullname: Xu, Ziyue organization: Nvidia, Bethesda, MD USA – sequence: 3 givenname: Ismail orcidid: 0000-0003-3277-2710 surname: Irmakci fullname: Irmakci, Ismail organization: Ege University, Izmir, Turkey – sequence: 4 givenname: Sanjay surname: Jain fullname: Jain, Sanjay organization: Johns Hopkins University, Baltimore, MD US State – sequence: 5 givenname: Ulas surname: Bagci fullname: Bagci, Ulas email: bagci@crcv.ucf.edu organization: Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/33246227$$D View this record in MEDLINE/PubMed
BookMark	eNqFkU1LKzEYhYMofv8CQQpu5EJrPieZhYKUe1UQ3Og6ZDJvasp0UpOZgv_e1NFydaGrhOQ5J-fNOUDbbWgBoROCJwST4mI-WUDtzYRi-n6iVLmF9gkryFhxyrY3eyL20EFKc4yx5Bzvoj3GKC8olfvoz9QsU99AGrkQR5UPa09rmpFfmBmMEswW0Ham86E9QjvONAmOP9ZD9PTv7-P0dnz_cHM3vb4fW65kN1ZQE-EwBQfcOYIrS1xhZVFyQ5jgFSPOCccqV5RWEkV5bSQ1ytQl5QJLxQ7R1eC77Kucxub3o2n0MuZI8VUH4_XXm9Y_61lYaVlyLhTOBucfBjG89JA6vfDJQtOYFkKfdJ5dcE6l4Bk9-4bOQx_bPJ6mgigpJS9Ipk7_T7SJ8vmNGWADYGNIKYLbIATrdVl6rt_L0uuy9FBWVpXfVNYPX53H8s0v2stBC7mJlYeok_XQ2gxGsJ2ug_9R_wasMK-H
CitedBy_id	crossref_primary_10_1038_s41746_023_00941_5 crossref_primary_10_1049_cvi2_12256 crossref_primary_10_1016_j_bspc_2024_107341 crossref_primary_10_1016_j_engappai_2023_106125 crossref_primary_10_1007_s11831_023_09925_w crossref_primary_10_1016_j_dsp_2025_105175 crossref_primary_10_1002_slct_202304082 crossref_primary_10_1007_s00138_023_01401_6 crossref_primary_10_3390_biomimetics10090596 crossref_primary_10_1049_ipr2_12406 crossref_primary_10_3390_electronics13061107 crossref_primary_10_1109_TPAMI_2024_3435571 crossref_primary_10_1007_s11517_021_02364_4 crossref_primary_10_1016_j_media_2025_103583 crossref_primary_10_1097_RLI_0000000000001207 crossref_primary_10_1007_s10489_022_03849_x crossref_primary_10_1002_aisy_202500154 crossref_primary_10_3390_diagnostics13040615 crossref_primary_10_1007_s10489_021_02630_w crossref_primary_10_1016_j_cmpb_2024_108054 crossref_primary_10_1111_1754_9485_13261 crossref_primary_10_1109_LGRS_2021_3124575 crossref_primary_10_1002_ima_22723 crossref_primary_10_1002_nbm_4606 crossref_primary_10_1117_1_JMI_11_1_014003 crossref_primary_10_1109_LSENS_2024_3384679 crossref_primary_10_1016_j_bspc_2025_108180 crossref_primary_10_1109_TPAMI_2022_3179526 crossref_primary_10_1007_s11042_024_19579_w crossref_primary_10_1111_coin_12600 crossref_primary_10_1007_s10586_024_04475_7 crossref_primary_10_1016_j_biocel_2023_106452 crossref_primary_10_3390_s23063144 crossref_primary_10_3390_fi14020054 crossref_primary_10_1016_j_bspc_2022_103682 crossref_primary_10_1002_mp_16975 crossref_primary_10_1007_s00500_023_08018_x crossref_primary_10_1109_JIOT_2022_3209895 crossref_primary_10_3390_s22083055 crossref_primary_10_1007_s00521_024_10144_y crossref_primary_10_1016_j_compmedimag_2024_102417 crossref_primary_10_1016_j_jvcir_2024_104187 crossref_primary_10_1016_j_yacr_2022_04_010 crossref_primary_10_1016_j_compbiomed_2022_105917 crossref_primary_10_1186_s40001_022_00634_x crossref_primary_10_1016_j_bspc_2022_104021 crossref_primary_10_3390_make6030068 crossref_primary_10_3390_app11041833 crossref_primary_10_1145_3674500 crossref_primary_10_3390_bioengineering10020181 crossref_primary_10_1002_ima_23080 crossref_primary_10_1016_j_ibmed_2025_100257
Cites_doi	10.1109/TMI.2014.2337057 10.1118/1.3528204 10.7150/thno.38065 10.1146/annurev.bioeng.2.1.315 10.1016/j.compmedimag.2011.07.003 10.1023/B:VISI.0000022288.19776.77 10.1109/TPAMI.2016.2644615 10.1093/gerona/63.12.1416 10.1109/TMI.2010.2046908 10.1109/TPAMI.2017.2699184 10.1109/TPAMI.2006.233 10.1109/TMI.2011.2180920 10.1006/gmip.1996.0021 10.1023/A:1020874308076 10.1109/TBME.2018.2866764
ContentType	Journal Article
Copyright	2020 Published by Elsevier B.V. Copyright Elsevier BV Feb 2021
Copyright_xml	– notice: 2020 – notice: Published by Elsevier B.V. – notice: Copyright Elsevier BV Feb 2021
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 8FD FR3 K9. NAPCQ P64 7X8 5PM
DOI	10.1016/j.media.2020.101889
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Biotechnology Research Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Premium Engineering Research Database Biotechnology Research Abstracts Technology Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic ProQuest Health & Medical Complete (Alumni) MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Engineering
EISSN	1361-8423
EndPage	101889
ExternalDocumentID	PMC7944580 33246227 10_1016_j_media_2020_101889 S136184152030253X
Genre	Journal Article Research Support, N.I.H., Extramural
GrantInformation_xml	– fundername: NIAID NIH HHS grantid: R01 AI153349 – fundername: NIAID NIH HHS grantid: R01 AI145435 – fundername: NCI NIH HHS grantid: R01 CA246704 – fundername: NCI NIH HHS grantid: R01 CA240639 – fundername: NIBIB NIH HHS grantid: R01 EB020539
GroupedDBID	--- --K --M .~1 0R~ 1B1 1~. 1~5 29M 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABBQC ABJNI ABLVK ABMAC ABMZM ABXDB ABYKQ ACDAQ ACGFS ACIUM ACIWK ACNNM ACPRK ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AJRQY ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV C45 CAG COF CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HX~ HZ~ IHE J1W JJJVA KOM LCYCR M41 MO0 N9A O-L O9- OAUVE OVD OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SEL SES SEW SPC SPCBC SSH SST SSV SSZ T5K TEORI UHS ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACIEU ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD AGCQF AGRNS CGR CUY CVF ECM EIF NPM 7QO 8FD FR3 K9. NAPCQ P64 7X8 5PM
ID	FETCH-LOGICAL-c487t-8ed15f02efe4ff10bc1f6c7694a1354b31ff5f3bf69c71824da72a8ad92450783
ISICitedReferencesCount	79
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000613293400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1361-8415 1361-8423
IngestDate	Tue Sep 30 16:45:41 EDT 2025 Sat Sep 27 17:18:19 EDT 2025 Tue Oct 07 07:18:06 EDT 2025 Mon Jul 21 06:01:46 EDT 2025 Sat Nov 29 07:01:33 EST 2025 Tue Nov 18 22:37:54 EST 2025 Fri Feb 23 02:48:32 EST 2024
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	Lung segmentation Pre-clinical imaging Capsule network Thigh MRI segmentation
Language	English
License	Published by Elsevier B.V.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c487t-8ed15f02efe4ff10bc1f6c7694a1354b31ff5f3bf69c71824da72a8ad92450783
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 Authors’ Contributions
ORCID	0000-0002-5728-6869 0000-0003-3277-2710
OpenAccessLink	https://www.ncbi.nlm.nih.gov/pmc/articles/7944580
PMID	33246227
PQID	2518777461
PQPubID	2045428
PageCount	1
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_7944580 proquest_miscellaneous_2465442754 proquest_journals_2518777461 pubmed_primary_33246227 crossref_primary_10_1016_j_media_2020_101889 crossref_citationtrail_10_1016_j_media_2020_101889 elsevier_sciencedirect_doi_10_1016_j_media_2020_101889
PublicationCentury	2000
PublicationDate	2021-02-01
PublicationDateYYYYMMDD	2021-02-01
PublicationDate_xml	– month: 02 year: 2021 text: 2021-02-01 day: 01
PublicationDecade	2020
PublicationPlace	Netherlands
PublicationPlace_xml	– name: Netherlands – name: Amsterdam
PublicationTitle	Medical image analysis
PublicationTitleAlternate	Med Image Anal
PublicationYear	2021
Publisher	Elsevier B.V Elsevier BV
Publisher_xml	– name: Elsevier B.V – name: Elsevier BV
References	Afshar, Mohammadi, Plataniotis (bib0002) 2018 Duarte, Rawat, Shah (bib0024) 2018 Mortazi, Karim, Rhode, Burt, Bagci (bib0048) 2017 He, Gkioxari, Dollár, Girshick (bib0030) 2017 Mobiny, Van Nguyen (bib0046) 2018 Mortazi, Burt, Bagci (bib0047) 2017; 1050 LaLonde, Kandel, Spampinato, Wallace, Bagci (bib0016) 2020 Srivastava, Valkov, Russell, Gutmann, Sutton (bib0056) 2017 Chen, Zhu, Papandreou, Schroff, Adam (bib0008) 2018 LaLonde, R., Bagci, U., 2018. Capsules for object segmentation. arXiv preprint LaLonde, Zhang, Shah (bib0041) 2018 Peng, Zhang, Yu, Luo, Sun (bib0049) 2017 Jégou, Drozdzal, Vazquez, Romero, Bengio (bib0037) 2017 Long, Shelhamer, Darrell (bib0043) 2015 Chen, Papandreou, Kokkinos, Murphy, Yuille (bib0007) 2018; 40 Lowe (bib0044) 1999; vol. 2 Alcorn (bib0003) 2019 Huang, Liu, Weinberger, van der Maaten (bib0036) 2017 Irmakci, Hussein, Savran, Kalyani, Reiter, Chia, Fishbein, Spencer, Ferrucci, Bagci (bib0014) 2018; 66 Çiçek, Abdulkadir, Lienkamp, Brox, Ronneberger (bib0010) 2016 Ferrucci, L., 2008. The baltimore longitudinal study of aging (BLSA): a 50-year-long journey and plans for the future. Zhao, Shi, Qi, Wang, Jia (bib0061) 2017 Horowitz, Pavlidis (bib0033) 1974 Mansoor (bib0045) 2014; 33 Kingma, D. P., Ba, J., 2014. Adam: a method for stochastic optimization. arXiv preprint Hsiao, Grauman (bib0034) 2018 . Qin, Y., Frosst, N., Sabour, S., Raffel, C., Cottrell, G., Hinton, G., 2019. Detecting and diagnosing adversarial images with class-conditional capsule reconstructions. arXiv preprint Ren, He, Girshick, Sun (bib0052) 2015 He, Zhang, Ren, Sun (bib0031) 2016 Hu, Shen, Sun (bib0035) 2018 Xu, Xue, Zhang (bib0021) 2019; 9 Paik, I., Kwak, T., Kim, I., 2019. Capsule networks need an improved routing algorithm. arXiv preprint Grady (bib0028) 2006; 28 Vese, Chan (bib0058) 2002; 50 Felzenszwalb, Huttenlocher (bib0026) 2004; 59 Badrinarayanan, Kendall, Cipolla (bib0005) 2017; 39 Frosst, N., Sabour, S., Hinton, G., 2018. DARCCC: Detecting adversaries by reconstruction from class conditional capsules. arXiv preprint Xie, Tu (bib0059) 2015 Armato (bib0004) 2011; 38 Tustison, Avants, Cook, Zheng, Egan, Yushkevich, Gee (bib0020) 2010; 29 Kosiorek, A. R., Sabour, S., Teh, Y. W., Hinton, G. E., 2019. Stacked capsule autoencoders. arXiv preprint Udupa, Samarasekera (bib0057) 1996; 58 Yang, Yu, Zhang, Li, Yang (bib0060) 2018 Abadi, M., et al., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from Harrison, Xu, George, Lu, Summers, Mollura (bib0029) 2017 Dalal, Triggs (bib0022) 2005; Vol. 1 Lin, Milan, Shen, Reid (bib0042) 2017 Milletari, Navab, Ahmadi (bib0018) 2016 Farag, Ahmed, El-Baz, Hassan (bib0012) 2005 Rosenfeld, Kak (bib0054) 1982 Pham, Xu, Prince (bib0050) 2000; 2 Chollet, F., et al., 2015. Keras. El-Baz, Farag, Gimel’farb, Falk, El-Ghar, Eldiasty (bib0025) 2006; vol. 3 Depeursinge, Vargas, Platon, Geissbuhler, Poletti, Müller (bib0023) 2012; 36 Karwoski, Bartholmai, Zavaletta, Holmes, Robb (bib0038) 2008; vol. 6916 Hinton, Sabour, Frosst (bib0032) 2018 Zhao, Birdal, Deng, Tombari (bib0062) 2019 Bagci, Chen, Udupa (bib0006) 2012; 31 LaLonde, Torigian, Bagci (bib0017) 2020 Sabour, Frosst, Hinton (bib0055) 2017 Elnakib, Gimel’farb, Suri, El-Baz (bib0011) 2011 Ronneberger, Fischer, Brox (bib0053) 2015 Elnakib (10.1016/j.media.2020.101889_bib0011) 2011 Lowe (10.1016/j.media.2020.101889_bib0044) 1999; vol. 2 He (10.1016/j.media.2020.101889_bib0030) 2017 Rosenfeld (10.1016/j.media.2020.101889_bib0054) 1982 10.1016/j.media.2020.101889_bib0039 Irmakci (10.1016/j.media.2020.101889_bib0014) 2018; 66 Karwoski (10.1016/j.media.2020.101889_bib0038) 2008; vol. 6916 Jégou (10.1016/j.media.2020.101889_bib0037) 2017 Peng (10.1016/j.media.2020.101889_bib0049) 2017 LaLonde (10.1016/j.media.2020.101889_bib0017) 2020 Hsiao (10.1016/j.media.2020.101889_bib0034) 2018 Farag (10.1016/j.media.2020.101889_bib0012) 2005 Udupa (10.1016/j.media.2020.101889_bib0057) 1996; 58 Depeursinge (10.1016/j.media.2020.101889_sbref0023) 2012; 36 Chen (10.1016/j.media.2020.101889_bib0008) 2018 Dalal (10.1016/j.media.2020.101889_bib0022) 2005; Vol. 1 Long (10.1016/j.media.2020.101889_bib0043) 2015 Xie (10.1016/j.media.2020.101889_bib0059) 2015 10.1016/j.media.2020.101889_bib0027 Çiçek (10.1016/j.media.2020.101889_bib0010) 2016 Zhao (10.1016/j.media.2020.101889_bib0061) 2017 Duarte (10.1016/j.media.2020.101889_bib0024) 2018 Mortazi (10.1016/j.media.2020.101889_bib0048) 2017 Grady (10.1016/j.media.2020.101889_bib0028) 2006; 28 Horowitz (10.1016/j.media.2020.101889_bib0033) 1974 Hu (10.1016/j.media.2020.101889_bib0035) 2018 Armato (10.1016/j.media.2020.101889_bib0004) 2011; 38 LaLonde (10.1016/j.media.2020.101889_bib0016) 2020 Vese (10.1016/j.media.2020.101889_bib0058) 2002; 50 Harrison (10.1016/j.media.2020.101889_bib0029) 2017 Afshar (10.1016/j.media.2020.101889_bib0002) 2018 Bagci (10.1016/j.media.2020.101889_bib0006) 2012; 31 Yang (10.1016/j.media.2020.101889_bib0060) 2018 Chen (10.1016/j.media.2020.101889_bib0007) 2018; 40 El-Baz (10.1016/j.media.2020.101889_bib0025) 2006; vol. 3 Ronneberger (10.1016/j.media.2020.101889_bib0053) 2015 10.1016/j.media.2020.101889_bib0019 Ren (10.1016/j.media.2020.101889_bib0052) 2015 Tustison (10.1016/j.media.2020.101889_bib0020) 2010; 29 10.1016/j.media.2020.101889_bib0051 LaLonde (10.1016/j.media.2020.101889_bib0041) 2018 Mortazi (10.1016/j.media.2020.101889_bib0047) 2017; 1050 Xu (10.1016/j.media.2020.101889_bib0021) 2019; 9 10.1016/j.media.2020.101889_bib0015 Sabour (10.1016/j.media.2020.101889_bib0055) 2017 Badrinarayanan (10.1016/j.media.2020.101889_bib0005) 2017; 39 10.1016/j.media.2020.101889_bib0013 He (10.1016/j.media.2020.101889_bib0031) 2016 Huang (10.1016/j.media.2020.101889_bib0036) 2017 10.1016/j.media.2020.101889_bib0009 Alcorn (10.1016/j.media.2020.101889_bib0003) 2019 Srivastava (10.1016/j.media.2020.101889_bib0056) 2017 Pham (10.1016/j.media.2020.101889_bib0050) 2000; 2 Mobiny (10.1016/j.media.2020.101889_bib0046) 2018 10.1016/j.media.2020.101889_bib0040 Mansoor (10.1016/j.media.2020.101889_bib0045) 2014; 33 Hinton (10.1016/j.media.2020.101889_bib0032) 2018 10.1016/j.media.2020.101889_bib0001 Lin (10.1016/j.media.2020.101889_bib0042) 2017 Milletari (10.1016/j.media.2020.101889_bib0018) 2016 Zhao (10.1016/j.media.2020.101889_bib0062) 2019 Felzenszwalb (10.1016/j.media.2020.101889_bib0026) 2004; 59
References_xml	– start-page: 741 year: 2018 end-page: 749 ident: bib0046 article-title: Fast capsnet for lung cancer screening publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 1175 year: 2017 end-page: 1183 ident: bib0037 article-title: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation publication-title: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on – reference: Chollet, F., et al., 2015. Keras. – start-page: 1086 year: 2020 end-page: 1090 ident: bib0016 article-title: Diagnosing colorectal polyps in the wild with capsule networks publication-title: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) – reference: Qin, Y., Frosst, N., Sabour, S., Raffel, C., Cottrell, G., Hinton, G., 2019. Detecting and diagnosing adversarial images with class-conditional capsule reconstructions. arXiv preprint: – start-page: 479 year: 2005 end-page: 533 ident: bib0012 article-title: Advanced Segmentation Techniques – volume: 29 start-page: 1310 year: 2010 end-page: 1320 ident: bib0020 article-title: N4ITK: improved n3 bias correction publication-title: IEEE Trans. Med. Imaging – start-page: 2881 year: 2017 end-page: 2890 ident: bib0061 article-title: Pyramid scene parsing network publication-title: Computer Vision and Pattern Recognition, 2017. CVPR 2017. IEEE Computer Society Conference on – volume: vol. 3 start-page: 611 year: 2006 end-page: 614 ident: bib0025 article-title: A framework for automatic segmentation of lung nodules from low dose chest CT scans publication-title: 18th International Conference on Pattern Recognition (ICPR’06) – reference: Kingma, D. P., Ba, J., 2014. Adam: a method for stochastic optimization. arXiv preprint: – start-page: 424 year: 2016 end-page: 432 ident: bib0010 article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation publication-title: International Conference on Medical Image computing and Computer-Assisted Intervention – start-page: 3859 year: 2017 end-page: 3869 ident: bib0055 article-title: Dynamic routing between capsules publication-title: Advances in Neural Information Processing Systems – start-page: 1009 year: 2019 end-page: 1018 ident: bib0062 article-title: 3D point capsule networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 66 start-page: 1069 year: 2018 end-page: 1081 ident: bib0014 article-title: A novel extension to fuzzy connectivity for body composition analysis: applications in thigh, brain, and whole body tissue segmentation publication-title: IEEE Trans. Biomed. Eng. – start-page: 621 year: 2017 end-page: 629 ident: bib0029 article-title: Progressive and multi-path holistically nested neural networks for pathological lung segmentation from CT images publication-title: Medical Image Computing and Computer Assisted Intervention MICCAI 2017 – volume: 1050 start-page: 3 year: 2017 ident: bib0047 article-title: Multi-planar deep segmentation networks for cardiac substructures from MRI and CT publication-title: Stat – start-page: 4353 year: 2017 end-page: 4361 ident: bib0049 article-title: Large kernel matters–improve semantic segmentation by global convolutional network publication-title: Computer Vision and Pattern Recognition, 2017. CVPR 2017. IEEE Computer Society Conference on – year: 2018 ident: bib0032 article-title: Matrix capsules with EM routing publication-title: 6th International Conference on Learning Representations, ICLR – volume: 58 start-page: 246 year: 1996 end-page: 261 ident: bib0057 article-title: Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation publication-title: Graph. Models Image Process. – start-page: 7132 year: 2018 end-page: 7141 ident: bib0035 article-title: Squeeze-and-excitation networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: vol. 6916 start-page: 691614 year: 2008 ident: bib0038 article-title: Processing of CT images for analysis of diffuse lung disease in the lung tissue research consortium publication-title: Medical Imaging 2008: Physiology, Function, and Structure from Medical Images – year: 2015 ident: bib0059 article-title: Holistically-nested edge detection publication-title: Proceedings of IEEE International Conference on Computer Vision – start-page: 2961 year: 2017 end-page: 2969 ident: bib0030 article-title: Mask R-CNN publication-title: Proceedings of the IEEE International Conference on Computer Vision – reference: Ferrucci, L., 2008. The baltimore longitudinal study of aging (BLSA): a 50-year-long journey and plans for the future. – start-page: 377 year: 2017 end-page: 385 ident: bib0048 article-title: CardiacNET: Segmentation of left atrium and proximal pulmonary veins from MRI using multi-view CNN publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 3308 year: 2017 end-page: 3318 ident: bib0056 article-title: VEEGAN: Reducing mode collapse in GANs using implicit variational learning publication-title: Advances in Neural Information Processing Systems – volume: 50 start-page: 271 year: 2002 end-page: 293 ident: bib0058 article-title: A multiphase level set framework for image segmentation using the Mumford and Shah model publication-title: Int. J. Comput. Vis. – volume: 40 start-page: 834 year: 2018 end-page: 848 ident: bib0007 article-title: DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – year: 2020 ident: bib0017 article-title: Encoding visual attributes in capsules for explainable medical diagnoses publication-title: Medical Image Computing and Computer Assisted Intervention MICCAI – start-page: 565 year: 2016 end-page: 571 ident: bib0018 article-title: V-Net: Fully convolutional neural networks for volumetric medical image segmentation publication-title: 2016 Fourth International Conference on 3D Vision (3DV) – year: 2018 ident: bib0041 article-title: ClusterNet: Detecting small objects in large scenes by exploiting spatio-temporal information publication-title: Computer Vision and Pattern Recognition, 2018. CVPR 2018. IEEE Computer Society Conference on – volume: 33 start-page: 2293 year: 2014 end-page: 2310 ident: bib0045 article-title: A generic approach to pathological lung segmentation publication-title: IEEE Trans. Med. Imaging – volume: 2 start-page: 315 year: 2000 end-page: 337 ident: bib0050 article-title: Current methods in medical image segmentation publication-title: Annu. Rev. Biomed. Eng. – volume: 9 start-page: 7556 year: 2019 ident: bib0021 article-title: Current status and future trends of clinical diagnoses via image-based deep learning publication-title: Theranostics – volume: vol. 2 start-page: 1150 year: 1999 end-page: 1157 ident: bib0044 article-title: Object recognition from local scale-invariant features publication-title: Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on – reference: Paik, I., Kwak, T., Kim, I., 2019. Capsule networks need an improved routing algorithm. arXiv preprint: – reference: Frosst, N., Sabour, S., Hinton, G., 2018. DARCCC: Detecting adversaries by reconstruction from class conditional capsules. arXiv preprint: – start-page: 770 year: 2016 end-page: 778 ident: bib0031 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 36 start-page: 227 year: 2012 end-page: 238 ident: bib0023 article-title: Building a reference multimedia database for interstitial lung diseases publication-title: Computerized Medical Imagingand Graphics – reference: Kosiorek, A. R., Sabour, S., Teh, Y. W., Hinton, G. E., 2019. Stacked capsule autoencoders. arXiv preprint: – volume: 59 start-page: 167 year: 2004 end-page: 181 ident: bib0026 article-title: Efficient graph-based image segmentation publication-title: Int. J. Comput. Vis. – volume: 28 start-page: 1768 year: 2006 end-page: 1783 ident: bib0028 article-title: Random walks for image segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – start-page: 424 year: 1974 end-page: 433 ident: bib0033 article-title: Picture segmentation by a direct split-and-merge procedure publication-title: Proc. of the 2nd Int. Joint Conf. on Pattern Recognition – reference: Abadi, M., et al., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from – start-page: 4845 year: 2019 end-page: 4854 ident: bib0003 article-title: Strike (with) a pose: neural networks are easily fooled by strange poses of familiar objects publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 38 start-page: 915 year: 2011 end-page: 931 ident: bib0004 article-title: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans publication-title: Med. Phys. – year: 1982 ident: bib0054 article-title: Digital Picture Processing: Volume 1 – start-page: 7610 year: 2018 end-page: 7619 ident: bib0024 article-title: VideoCapsuleNet: a simplified network for action detection publication-title: Advances in Neural Information Processing Systems – start-page: 801 year: 2018 end-page: 818 ident: bib0008 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 3431 year: 2015 end-page: 3440 ident: bib0043 article-title: Fully convolutional networks for semantic segmentation publication-title: Computer Vision and Pattern Recognition, 2015. CVPR 2015. IEEE Computer Society Conference on – volume: 39 start-page: 2481 year: 2017 end-page: 2495 ident: bib0005 article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – volume: Vol. 1 start-page: 886 year: 2005 end-page: 893 ident: bib0022 article-title: Histograms of oriented gradients for human detection publication-title: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on – year: 2017 ident: bib0042 article-title: RefineNet: Multi-path refinement networks for high-resolution semantic segmentation publication-title: Computer Vision and Pattern Recognition, 2017. CVPR 2017. IEEE Computer Society Conference on – start-page: 91 year: 2015 end-page: 99 ident: bib0052 article-title: Faster R-CNN: towards real-time object detection with region proposal networks publication-title: Advances in Neural Information Processing Systems – reference: . – start-page: 3129 year: 2018 end-page: 3133 ident: bib0002 article-title: Brain tumor type classification via capsule networks publication-title: 2018 25th IEEE International Conference on Image Processing (ICIP) – year: 2017 ident: bib0036 article-title: Densely connected convolutional networks publication-title: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on – start-page: 234 year: 2015 end-page: 241 ident: bib0053 article-title: U-Net: Convolutional networks for biomedical image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 7161 year: 2018 end-page: 7170 ident: bib0034 article-title: Creating capsule wardrobes from fashion images publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3684 year: 2018 end-page: 3692 ident: bib0060 article-title: DenseASPP for semantic segmentation in street scenes publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – reference: LaLonde, R., Bagci, U., 2018. Capsules for object segmentation. arXiv preprint: – volume: 31 start-page: 777 year: 2012 end-page: 789 ident: bib0006 article-title: Hierarchical scale-based multiobject recognition of 3-d anatomical structures publication-title: IEEE Trans. Med. Imaging – start-page: 1 year: 2011 end-page: 39 ident: bib0011 article-title: Medical Image Segmentation: A Brief Survey – volume: 33 start-page: 2293 issue: 12 year: 2014 ident: 10.1016/j.media.2020.101889_bib0045 article-title: A generic approach to pathological lung segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2014.2337057 – start-page: 2881 year: 2017 ident: 10.1016/j.media.2020.101889_bib0061 article-title: Pyramid scene parsing network – start-page: 3129 year: 2018 ident: 10.1016/j.media.2020.101889_bib0002 article-title: Brain tumor type classification via capsule networks – start-page: 7610 year: 2018 ident: 10.1016/j.media.2020.101889_bib0024 article-title: VideoCapsuleNet: a simplified network for action detection – ident: 10.1016/j.media.2020.101889_bib0039 – start-page: 741 year: 2018 ident: 10.1016/j.media.2020.101889_bib0046 article-title: Fast capsnet for lung cancer screening – start-page: 1009 year: 2019 ident: 10.1016/j.media.2020.101889_bib0062 article-title: 3D point capsule networks – volume: 38 start-page: 915 issue: 2 year: 2011 ident: 10.1016/j.media.2020.101889_bib0004 article-title: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans publication-title: Med. Phys. doi: 10.1118/1.3528204 – ident: 10.1016/j.media.2020.101889_bib0051 – start-page: 1086 year: 2020 ident: 10.1016/j.media.2020.101889_bib0016 article-title: Diagnosing colorectal polyps in the wild with capsule networks – volume: 9 start-page: 7556 issue: 25 year: 2019 ident: 10.1016/j.media.2020.101889_bib0021 article-title: Current status and future trends of clinical diagnoses via image-based deep learning publication-title: Theranostics doi: 10.7150/thno.38065 – start-page: 3308 year: 2017 ident: 10.1016/j.media.2020.101889_bib0056 article-title: VEEGAN: Reducing mode collapse in GANs using implicit variational learning – start-page: 3859 year: 2017 ident: 10.1016/j.media.2020.101889_bib0055 article-title: Dynamic routing between capsules – start-page: 1 year: 2011 ident: 10.1016/j.media.2020.101889_bib0011 – start-page: 4845 year: 2019 ident: 10.1016/j.media.2020.101889_bib0003 article-title: Strike (with) a pose: neural networks are easily fooled by strange poses of familiar objects – volume: 1050 start-page: 3 year: 2017 ident: 10.1016/j.media.2020.101889_bib0047 article-title: Multi-planar deep segmentation networks for cardiac substructures from MRI and CT publication-title: Stat – start-page: 565 year: 2016 ident: 10.1016/j.media.2020.101889_bib0018 article-title: V-Net: Fully convolutional neural networks for volumetric medical image segmentation – volume: 2 start-page: 315 issue: 1 year: 2000 ident: 10.1016/j.media.2020.101889_bib0050 article-title: Current methods in medical image segmentation publication-title: Annu. Rev. Biomed. Eng. doi: 10.1146/annurev.bioeng.2.1.315 – start-page: 234 year: 2015 ident: 10.1016/j.media.2020.101889_bib0053 article-title: U-Net: Convolutional networks for biomedical image segmentation – ident: 10.1016/j.media.2020.101889_bib0015 – ident: 10.1016/j.media.2020.101889_bib0019 – start-page: 7161 year: 2018 ident: 10.1016/j.media.2020.101889_bib0034 article-title: Creating capsule wardrobes from fashion images – volume: vol. 2 start-page: 1150 year: 1999 ident: 10.1016/j.media.2020.101889_bib0044 article-title: Object recognition from local scale-invariant features – start-page: 1175 year: 2017 ident: 10.1016/j.media.2020.101889_bib0037 article-title: The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation – year: 1982 ident: 10.1016/j.media.2020.101889_bib0054 – volume: 36 start-page: 227 issue: 3 year: 2012 ident: 10.1016/j.media.2020.101889_sbref0023 article-title: Building a reference multimedia database for interstitial lung diseases publication-title: Computerized Medical Imagingand Graphics doi: 10.1016/j.compmedimag.2011.07.003 – year: 2015 ident: 10.1016/j.media.2020.101889_bib0059 article-title: Holistically-nested edge detection – year: 2017 ident: 10.1016/j.media.2020.101889_bib0036 article-title: Densely connected convolutional networks – year: 2018 ident: 10.1016/j.media.2020.101889_bib0032 article-title: Matrix capsules with EM routing – start-page: 801 year: 2018 ident: 10.1016/j.media.2020.101889_bib0008 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation – start-page: 424 year: 2016 ident: 10.1016/j.media.2020.101889_bib0010 article-title: 3D U-Net: learning dense volumetric segmentation from sparse annotation – start-page: 770 year: 2016 ident: 10.1016/j.media.2020.101889_bib0031 article-title: Deep residual learning for image recognition – volume: 59 start-page: 167 issue: 2 year: 2004 ident: 10.1016/j.media.2020.101889_bib0026 article-title: Efficient graph-based image segmentation publication-title: Int. J. Comput. Vis. doi: 10.1023/B:VISI.0000022288.19776.77 – volume: vol. 6916 start-page: 691614 year: 2008 ident: 10.1016/j.media.2020.101889_bib0038 article-title: Processing of CT images for analysis of diffuse lung disease in the lung tissue research consortium – start-page: 377 year: 2017 ident: 10.1016/j.media.2020.101889_bib0048 article-title: CardiacNET: Segmentation of left atrium and proximal pulmonary veins from MRI using multi-view CNN – volume: 39 start-page: 2481 issue: 12 year: 2017 ident: 10.1016/j.media.2020.101889_bib0005 article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2016.2644615 – ident: 10.1016/j.media.2020.101889_bib0013 doi: 10.1093/gerona/63.12.1416 – start-page: 424 year: 1974 ident: 10.1016/j.media.2020.101889_bib0033 article-title: Picture segmentation by a direct split-and-merge procedure – start-page: 2961 year: 2017 ident: 10.1016/j.media.2020.101889_bib0030 article-title: Mask R-CNN – start-page: 7132 year: 2018 ident: 10.1016/j.media.2020.101889_bib0035 article-title: Squeeze-and-excitation networks – volume: 29 start-page: 1310 issue: 6 year: 2010 ident: 10.1016/j.media.2020.101889_bib0020 article-title: N4ITK: improved n3 bias correction publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2010.2046908 – volume: vol. 3 start-page: 611 year: 2006 ident: 10.1016/j.media.2020.101889_bib0025 article-title: A framework for automatic segmentation of lung nodules from low dose chest CT scans – volume: Vol. 1 start-page: 886 year: 2005 ident: 10.1016/j.media.2020.101889_bib0022 article-title: Histograms of oriented gradients for human detection – year: 2020 ident: 10.1016/j.media.2020.101889_bib0017 article-title: Encoding visual attributes in capsules for explainable medical diagnoses – year: 2018 ident: 10.1016/j.media.2020.101889_bib0041 article-title: ClusterNet: Detecting small objects in large scenes by exploiting spatio-temporal information – start-page: 4353 year: 2017 ident: 10.1016/j.media.2020.101889_bib0049 article-title: Large kernel matters–improve semantic segmentation by global convolutional network – volume: 40 start-page: 834 issue: 4 year: 2018 ident: 10.1016/j.media.2020.101889_bib0007 article-title: DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2017.2699184 – start-page: 3684 year: 2018 ident: 10.1016/j.media.2020.101889_bib0060 article-title: DenseASPP for semantic segmentation in street scenes – ident: 10.1016/j.media.2020.101889_bib0009 – volume: 28 start-page: 1768 issue: 11 year: 2006 ident: 10.1016/j.media.2020.101889_bib0028 article-title: Random walks for image segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2006.233 – volume: 31 start-page: 777 issue: 3 year: 2012 ident: 10.1016/j.media.2020.101889_bib0006 article-title: Hierarchical scale-based multiobject recognition of 3-d anatomical structures publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2011.2180920 – volume: 58 start-page: 246 issue: 3 year: 1996 ident: 10.1016/j.media.2020.101889_bib0057 article-title: Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation publication-title: Graph. Models Image Process. doi: 10.1006/gmip.1996.0021 – ident: 10.1016/j.media.2020.101889_bib0001 – start-page: 3431 year: 2015 ident: 10.1016/j.media.2020.101889_bib0043 article-title: Fully convolutional networks for semantic segmentation – ident: 10.1016/j.media.2020.101889_bib0040 – volume: 50 start-page: 271 issue: 3 year: 2002 ident: 10.1016/j.media.2020.101889_bib0058 article-title: A multiphase level set framework for image segmentation using the Mumford and Shah model publication-title: Int. J. Comput. Vis. doi: 10.1023/A:1020874308076 – start-page: 91 year: 2015 ident: 10.1016/j.media.2020.101889_bib0052 article-title: Faster R-CNN: towards real-time object detection with region proposal networks – ident: 10.1016/j.media.2020.101889_bib0027 – year: 2017 ident: 10.1016/j.media.2020.101889_bib0042 article-title: RefineNet: Multi-path refinement networks for high-resolution semantic segmentation – volume: 66 start-page: 1069 issue: 4 year: 2018 ident: 10.1016/j.media.2020.101889_bib0014 article-title: A novel extension to fuzzy connectivity for body composition analysis: applications in thigh, brain, and whole body tissue segmentation publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2018.2866764 – start-page: 621 year: 2017 ident: 10.1016/j.media.2020.101889_bib0029 article-title: Progressive and multi-path holistically nested neural networks for pathological lung segmentation from CT images – start-page: 479 year: 2005 ident: 10.1016/j.media.2020.101889_bib0012
SSID	ssj0007440
Score	2.5648372
Snippet	•First ever capsule network for image segmentation.•Reduced memory burden: locally-constrained routing and transformation matrix sharing.•Introduced novel... Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the...
SourceID	pubmedcentral proquest pubmed crossref elsevier
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	101889
SubjectTerms	Ablation Capsule network Capsules Coders Computed tomography Datasets Encoders-Decoders Experiments Humans Image processing Image Processing, Computer-Assisted Image reconstruction Image segmentation Lung segmentation Lungs Magnetic Resonance Imaging Medical imaging Muscles Neural Networks, Computer Parameters Pre-clinical imaging Regularization Routing Thigh MRI segmentation Thorax Tomography Tomography, X-Ray Computed
Title	Capsules for biomedical image segmentation
URI	https://dx.doi.org/10.1016/j.media.2020.101889 https://www.ncbi.nlm.nih.gov/pubmed/33246227 https://www.proquest.com/docview/2518777461 https://www.proquest.com/docview/2465442754 https://pubmed.ncbi.nlm.nih.gov/PMC7944580
Volume	68
WOSCitedRecordID	wos000613293400001&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: 1361-8423 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007440 issn: 1361-8415 databaseCode: AIEXJ dateStart: 20161201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9RAEB9sK6IPovWjp7VE8ElMSTabZPexlIpXaBFaIW9hs9m1d_bS0tyV-t87-5E018Oigi_h2OwmuZ3ZyczmN78B-CAyUelEsVDFTIZU6igUnFZhxdCTkxzfkLW0xSby42NWFPyrL3PX2nICedOwmxt--V9FjW0obJM6-xfi7i-KDfgbhY5HFDse_0jw-wID33PVOiCmza63gpjMDDynVd9nPt2oGTqmR0u9hKcq6eE6wpT9UA6KXTeq34cvFvbrxuTnoleQMZr6H9KCBMbtbADhOBSOr-BENFMP3fHbDSTuEMrdHthKHow1m0kWh4y6xMxdNWxz2cSdrXUldFbMtttBmO7abBkM2oltY6640B0-7BNzYXMvgvaJpEmxBhskTzmatI298UFx2L-IDfehS7tzD9eRTll438qtfueYrAYed_GzA4fk9Bk89ZFEsOc04Dk8UM0mPBnwS27CoyOPnHgBHzu1CFAtglu1CKzAg6FavIRvnw9O97-Evk5GKDHcnIdM1XGqI6K0olrHUSVjnck841TESUqrJNY61UmlMy7RFSG0FjkRTNQYe6fmM-4rWG8uGrUFQSUojuPo5mY1jTSuY6U4y5nkqaJURyMg3SSV0pPIm1om52WHFpyWdmZLM7Olm9kRfOoHXToOlfu7Z93sl94NdO5diepy_8DtTlalX5Btif67obykWTyC9_1ptKHmw5ho1MUC-xhSQYpKREfw2om2f9AEI46MkHwE-ZLQ-w6Gn335TDM5szzt-KqjKYve_Ov_eQuPb1fgNqzPrxbqHTyU1_NJe7UDa3nBdrzO_wIZebQT
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=Capsules+for+biomedical+image+segmentation&rft.jtitle=Medical+image+analysis&rft.au=LaLonde%2C+Rodney&rft.au=Xu%2C+Ziyue&rft.au=Irmakci%2C+Ismail&rft.au=Jain%2C+Sanjay&rft.date=2021-02-01&rft.pub=Elsevier+B.V&rft.issn=1361-8415&rft.eissn=1361-8423&rft.volume=68&rft_id=info:doi/10.1016%2Fj.media.2020.101889&rft.externalDocID=S136184152030253X
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-8415&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-8415&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-8415&client=summon