Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network
Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human in...
Saved in:
| Published in: | Journal of healthcare engineering Vol. 2018; no. 2018; pp. 1 - 14 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Cairo, Egypt
Hindawi Publishing Corporation
01.01.2018
Hindawi John Wiley & Sons, Inc |
| Subjects: | |
| ISSN: | 2040-2295, 2040-2309 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. |
|---|---|
| AbstractList | Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. |
| Audience | Academic |
| Author | Jiang, Jingfeng Mao, Lei Cui, Shaoguo Xiong, Shuyu Liu, Chang |
| AuthorAffiliation | 1 College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China 2 Medical Physics Department, University of Wisconsin, Madison, WI 53705, USA 3 Biomedical Engineering Department, Michigan Technological University, Houghton, MI 49931, USA |
| AuthorAffiliation_xml | – name: 1 College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China – name: 3 Biomedical Engineering Department, Michigan Technological University, Houghton, MI 49931, USA – name: 2 Medical Physics Department, University of Wisconsin, Madison, WI 53705, USA |
| Author_xml | – sequence: 1 fullname: Liu, Chang – sequence: 2 fullname: Jiang, Jingfeng – sequence: 3 fullname: Mao, Lei – sequence: 4 fullname: Cui, Shaoguo – sequence: 5 fullname: Xiong, Shuyu |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/29755716$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkttrFDEUxoO02Fr75rMEfBF0bS6T24uwrrYuVAW1z-FsJrONziTrZMbif2-G2dYLiHk5h-SX73zhywN0EFP0CD2i5AWlQpwxQvVZZSoiDL-HjhmpyIJxYg5ue2bEETrN-QspixteUX4fHTGjhFBUHiO_HIfUwRAc_uQ7iHOz7XwcymaKODX4VQ8h4os2FDDjpk8dfvdxjdcdbH3GVznELQb82vsdXkF2UPsav_djD20pw03qvz5Ehw202Z_u6wm6On_zefV2cfnhYr1aXi5cpeiwkF5JDozVlXRaUK2JkqKqldZOKkI9GCXZhgCrqa-VEpJ6Q2DDRG04aYDxE_Ry1t2Nm87XrryiuLC7PnTQ_7AJgv3zJIZru03frdC6YnQSeLoX6NO30efBdiE737YQfRqzZYRrRQSTpqBPZnQLrbchNqkougm3S6En49rIQj3-3dGdldsECvB8Blyfcu59c4dQYqeM7ZSx3WdccPYX7sKcVJke2n9dejZfug6xhpvwvxF7y-U_lAHwi6ZacWb4T_JZvVg |
| CitedBy_id | crossref_primary_10_1016_j_bspc_2024_106054 crossref_primary_10_1051_e3sconf_202449104002 crossref_primary_10_1049_iet_ipr_2018_6682 crossref_primary_10_3389_fncom_2020_00009 crossref_primary_10_1109_ACCESS_2020_2983075 crossref_primary_10_1038_s41598_024_51472_2 crossref_primary_10_1002_ima_22331 crossref_primary_10_1007_s11042_023_16458_8 crossref_primary_10_1016_j_bspc_2023_105886 crossref_primary_10_1016_j_cpcardiol_2023_102129 crossref_primary_10_3390_s23187816 crossref_primary_10_1007_s12553_020_00514_6 crossref_primary_10_1002_btm2_10553 crossref_primary_10_7717_peerj_cs_1878 crossref_primary_10_1049_cit2_12270 crossref_primary_10_1109_ACCESS_2020_2989819 crossref_primary_10_1007_s11042_021_11822_y crossref_primary_10_1016_j_compmedimag_2023_102313 crossref_primary_10_1063_5_0239433 crossref_primary_10_1007_s00521_022_07230_4 crossref_primary_10_1007_s12194_021_00633_3 crossref_primary_10_3171_2021_5_FOCUS21200 crossref_primary_10_1016_j_ymeth_2020_10_004 crossref_primary_10_1002_jmri_27105 crossref_primary_10_1109_ACCESS_2024_3480271 crossref_primary_10_1093_neuros_nyaa282 crossref_primary_10_1016_j_compbiomed_2024_108635 crossref_primary_10_1038_s41598_024_55864_2 crossref_primary_10_1109_ACCESS_2021_3132050 crossref_primary_10_1016_j_bspc_2023_104586 crossref_primary_10_1155_2022_8619690 crossref_primary_10_3389_fonc_2022_873268 crossref_primary_10_3390_jimaging7040066 crossref_primary_10_1016_j_compbiomed_2022_106426 crossref_primary_10_1007_s00521_021_06134_z crossref_primary_10_1016_j_compbiomed_2019_03_014 crossref_primary_10_1007_s11042_019_08048_4 crossref_primary_10_1177_0161734620902527 crossref_primary_10_1016_j_bbe_2020_07_001 crossref_primary_10_1038_s41598_019_57242_9 crossref_primary_10_1016_j_compmedimag_2020_101811 crossref_primary_10_1155_2021_6695108 crossref_primary_10_1016_j_neurad_2023_05_008 crossref_primary_10_3390_medicina61040561 crossref_primary_10_1109_JBHI_2023_3346529 crossref_primary_10_3390_healthcare10122340 crossref_primary_10_1002_mp_17260 crossref_primary_10_1007_s11761_024_00418_7 crossref_primary_10_1007_s11768_024_00231_9 crossref_primary_10_21015_vtse_v11i2_1533 crossref_primary_10_1088_1361_6560_ac7d33 crossref_primary_10_1155_2020_9258649 crossref_primary_10_1007_s11831_024_10128_0 crossref_primary_10_1016_j_inffus_2022_12_010 crossref_primary_10_1016_j_bspc_2019_101641 crossref_primary_10_1002_ima_22677 crossref_primary_10_1007_s42979_021_00784_5 crossref_primary_10_1016_j_procs_2023_01_053 crossref_primary_10_3390_jimaging7020019 crossref_primary_10_1016_j_zemedi_2018_11_002 crossref_primary_10_1007_s10143_023_02014_3 crossref_primary_10_1007_s11042_023_18017_7 crossref_primary_10_1007_s11548_021_02326_z crossref_primary_10_1002_acm2_13321 crossref_primary_10_1007_s11042_024_18996_1 crossref_primary_10_1016_j_renene_2021_06_086 crossref_primary_10_1109_TCBB_2019_2939522 crossref_primary_10_1109_ACCESS_2024_3450593 crossref_primary_10_1155_2020_2785464 crossref_primary_10_1007_s11831_023_09898_w crossref_primary_10_1016_j_ymeth_2020_09_007 crossref_primary_10_1007_s10916_019_1368_4 crossref_primary_10_1002_mp_17171 crossref_primary_10_1136_bmjopen_2020_042660 crossref_primary_10_1016_j_knosys_2023_110544 crossref_primary_10_1007_s10278_021_00516_4 crossref_primary_10_1016_j_jocn_2021_04_043 crossref_primary_10_1186_s12880_024_01283_8 crossref_primary_10_3390_diagnostics13172770 crossref_primary_10_1088_2632_2153_ad8e2c crossref_primary_10_1007_s12652_022_03773_5 crossref_primary_10_1109_ACCESS_2021_3107303 crossref_primary_10_1016_j_bspc_2022_104017 crossref_primary_10_1016_j_ejmp_2022_06_007 crossref_primary_10_3390_cancers14051349 crossref_primary_10_1109_TIP_2021_3070752 crossref_primary_10_1177_20552076221074122 crossref_primary_10_3389_fonc_2023_1325179 crossref_primary_10_1007_s11548_024_03205_z crossref_primary_10_1016_j_compbiomed_2022_105273 crossref_primary_10_3389_fonc_2019_00768 crossref_primary_10_4274_atfm_galenos_2022_97830 crossref_primary_10_13005_bpj_2576 |
| Cites_doi | 10.1109/TMI.2014.2377694 10.1007/s00401-010-0750-6 10.1109/TPAMI.2016.2572683 10.1007/s12021-014-9245-2 10.1016/j.media.2016.05.004 10.3322/caac.20069 10.1016/j.media.2016.10.004 10.1007/s10044-017-0597-8 10.1088/0031-9155/58/13/R97 10.1109/TMI.2016.2535302 10.1007/978-3-642-35289-8_26 10.1109/TMI.2016.2538465 10.1016/j.compbiomed.2013.07.001 10.1007/978-3-319-30858-6_12 10.1109/TMI.2016.2528162 10.2307/1932409 10.1007/978-3-319-60964-5_44 10.1007/978-3-642-23626-6_44 10.1007/978-3-319-19665-7_17 10.1007/s11548-015-1311-1 10.1109/TMI.2011.2181857 10.1148/radiol.09090663 10.1007/s00401-007-0243-4 10.1109/TMI.2007.912817 10.1007/978-3-642-33454-2_46 |
| ContentType | Journal Article |
| Copyright | Copyright © 2018 Shaoguo Cui et al. COPYRIGHT 2018 John Wiley & Sons, Inc. Copyright © 2018 Shaoguo Cui et al. 2018 |
| Copyright_xml | – notice: Copyright © 2018 Shaoguo Cui et al. – notice: COPYRIGHT 2018 John Wiley & Sons, Inc. – notice: Copyright © 2018 Shaoguo Cui et al. 2018 |
| DBID | ADJCN AHFXO RHU RHW RHX AAYXX CITATION NPM 7X8 5PM |
| DOI | 10.1155/2018/4940593 |
| DatabaseName | الدوريات العلمية والإحصائية - e-Marefa Academic and Statistical Periodicals معرفة - المحتوى العربي الأكاديمي المتكامل - e-Marefa Academic Complete Hindawi Publishing Complete Hindawi Publishing Subscription Journals Hindawi Publishing Open Access CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | CrossRef PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: RHX name: Hindawi Publishing Open Access url: http://www.hindawi.com/journals/ sourceTypes: Publisher – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2040-2309 |
| Editor | Chang, Weide |
| Editor_xml | – sequence: 1 givenname: Weide surname: Chang fullname: Chang, Weide |
| EndPage | 14 |
| ExternalDocumentID | PMC5884212 A587654896 29755716 10_1155_2018_4940593 1187329 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GrantInformation_xml | – fundername: Chongqing University of Technology grantid: YCX2016230 – fundername: Chongqing Municipal Education Commission grantid: KJ1709210; 16SKGH133 – fundername: Chongqing Science and Technology Commission grantid: cstc2016jcyjA0383 |
| GroupedDBID | 0R~ 24P 4.4 53G 5VS AAFWJ AAMMB ACCMX ADBBV ADJCN ADRAZ AEFGJ AENEX AGXDD AHFXO AIDQK AIDYY ALMA_UNASSIGNED_HOLDINGS AOIJS BCNDV EBD EBS EJD EMOBN H13 HYE IHR INR IPNFZ KQ8 M48 MET MV1 OK1 P2P PGMZT RIG RPM SV3 AAJEY GROUPED_DOAJ IAO IEA INH ITC RHU RHW RHX AAYXX ALUQN CITATION NPM 7X8 5PM |
| ID | FETCH-LOGICAL-c471t-6e763a22d46c8518807654d788c6701ea9762b0a2d1ed77561e90ab25d930fa23 |
| IEDL.DBID | RHX |
| ISICitedReferencesCount | 108 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000428860500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2040-2295 |
| IngestDate | Tue Nov 04 01:51:26 EST 2025 Wed Oct 01 13:30:51 EDT 2025 Tue Nov 11 10:55:36 EST 2025 Wed Feb 19 02:35:05 EST 2025 Sat Nov 29 04:52:05 EST 2025 Tue Nov 18 22:32:47 EST 2025 Sun Jun 02 18:54:28 EDT 2024 Thu Sep 25 15:12:52 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2018 |
| Language | English |
| License | This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c471t-6e763a22d46c8518807654d788c6701ea9762b0a2d1ed77561e90ab25d930fa23 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Academic Editor: Weide Chang |
| ORCID | 0000-0001-8812-6246 0000-0003-3064-0490 |
| OpenAccessLink | https://dx.doi.org/10.1155/2018/4940593 |
| PMID | 29755716 |
| PQID | 2038705269 |
| PQPubID | 23479 |
| PageCount | 14 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_5884212 proquest_miscellaneous_2038705269 gale_infotracmisc_A587654896 pubmed_primary_29755716 crossref_primary_10_1155_2018_4940593 crossref_citationtrail_10_1155_2018_4940593 hindawi_primary_10_1155_2018_4940593 emarefa_primary_1187329 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-01-01 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – month: 01 year: 2018 text: 2018-01-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Cairo, Egypt |
| PublicationPlace_xml | – name: Cairo, Egypt – name: England |
| PublicationTitle | Journal of healthcare engineering |
| PublicationTitleAlternate | J Healthc Eng |
| PublicationYear | 2018 |
| Publisher | Hindawi Publishing Corporation Hindawi John Wiley & Sons, Inc |
| Publisher_xml | – name: Hindawi Publishing Corporation – name: Hindawi – name: John Wiley & Sons, Inc |
| References | 22 (23) 2012 28 29 (31) 2014; 15 (17) 2015 10 32 11 33 34 13 36 38 18 19 (16) 2014 1 2 3 4 5 6 7 8 9 40 20 21 (25) 2009; 2 |
| References_xml | – ident: 32 doi: 10.1109/TMI.2014.2377694 – ident: 4 doi: 10.1007/s00401-010-0750-6 – ident: 22 doi: 10.1109/TPAMI.2016.2572683 – ident: 10 doi: 10.1007/s12021-014-9245-2 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 31 publication-title: Journal of Machine Learning Research – start-page: 13 volume-title: Structured prediction with convolutional neural networks for multimodal brain tumor segmentation year: 2015 ident: 17 – ident: 19 doi: 10.1016/j.media.2016.05.004 – ident: 3 doi: 10.3322/caac.20069 – ident: 21 doi: 10.1016/j.media.2016.10.004 – volume: 2 start-page: 1 year: 2009 ident: 25 publication-title: Insight Journal – ident: 9 doi: 10.1007/s10044-017-0597-8 – ident: 2 doi: 10.1088/0031-9155/58/13/R97 – ident: 29 doi: 10.1109/TMI.2016.2535302 – ident: 33 doi: 10.1007/978-3-642-35289-8_26 – ident: 18 doi: 10.1109/TMI.2016.2538465 – ident: 7 doi: 10.1016/j.compbiomed.2013.07.001 – ident: 38 doi: 10.1007/978-3-319-30858-6_12 – ident: 28 doi: 10.1109/TMI.2016.2528162 – volume-title: Brain tumor segmentation with deep neural networks year: 2014 ident: 16 – ident: 34 doi: 10.2307/1932409 – ident: 36 doi: 10.1007/978-3-319-60964-5_44 – ident: 13 doi: 10.1007/978-3-642-23626-6_44 – ident: 20 doi: 10.1007/978-3-319-19665-7_17 – volume-title: Imagenet classification with deep convolutional neural networks year: 2012 ident: 23 – ident: 8 doi: 10.1007/s11548-015-1311-1 – ident: 6 doi: 10.1109/TMI.2011.2181857 – ident: 40 doi: 10.1148/radiol.09090663 – ident: 1 doi: 10.1007/s00401-007-0243-4 – ident: 5 doi: 10.1109/TMI.2007.912817 – ident: 11 doi: 10.1007/978-3-642-33454-2_46 |
| SSID | ssj0000393413 |
| Score | 2.4948835 |
| Snippet | Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly... |
| SourceID | pubmedcentral proquest gale pubmed crossref hindawi emarefa |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1 |
| SubjectTerms | Brain tumors Gliomas Magnetic resonance imaging Medical imaging equipment Neural networks |
| Title | Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network |
| URI | https://search.emarefa.net/detail/BIM-1187329 https://dx.doi.org/10.1155/2018/4940593 https://www.ncbi.nlm.nih.gov/pubmed/29755716 https://www.proquest.com/docview/2038705269 https://pubmed.ncbi.nlm.nih.gov/PMC5884212 |
| Volume | 2018 |
| WOSCitedRecordID | wos000428860500001&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: PRVWIB databaseName: Open Access: Wiley-Blackwell Open Access Journals customDbUrl: eissn: 2040-2309 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000393413 issn: 2040-2295 databaseCode: 24P dateStart: 20100101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dT6QwEJ-4RpPzwaj3IX6lJt7ThRyUltLH9dvkbmO8j-wbKbR7buKyRnb133cGWM7VM94LgTC0wK_tzMDMbwAOAmsMagnja8OlL0Ib-VrnAz_LsigYOBfZKpH29zfV6yX9vr5sSJLKl7_wUduhex4mX4UWVHyuA51E0uC9Ou-3n1IovVRUhZA5xcdRgepZiPuzy-eUz7IbGdwx7WK8fE1u8MPwX8bm85jJJ0rodA1WG-uRdWu412HBFRuw8oRT8D247nQyrnhY2Q_suqh3_oyaHKOCjQfskOpCsLObIQUHMcowYd-vLtjFCBeXklVRBMywY-du2ZEpKYLeMmLxwK57ddj4B_h1evLz6Nxvain4OaqfiR87XEgM51bEeVKRsKlYCosOcB6rIHQGzRKeBYbb0Fml0KpyOjAZl1YjZoZHH2GxGBduE5iTOnBoiHE0FoUJrQ5FpoREWLMBNms8-DJ7yWneEI1TvYubtHI4pEwJkrSBxIPPrfRtTbDxitynBq-_YmGiIq492CH8UpqR2E-O8yNPuzKhB0x07MFBg-sb7e_PQE-pBYo9K9x4WqJUhIsaVWLHe6gHQdsS5SVLdDk9UHPDoxUg9u75M8XwumLxpgxhtBu2_u_2tuEdHdYff3ZgcXI3dbuwlN9PhuXdHnS4uMSt6id71dx4BHFJAW8 |
| linkProvider | Hindawi Publishing |
| 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=Automatic+Semantic+Segmentation+of+Brain+Gliomas+from+MRI+Images+Using+a+Deep+Cascaded+Neural+Network&rft.jtitle=Journal+of+healthcare+engineering&rft.au=Cui%2C+Shaoguo&rft.au=Mao%2C+Lei&rft.au=Jiang%2C+Jingfeng&rft.au=Liu%2C+Chang&rft.date=2018-01-01&rft.issn=2040-2295&rft.eissn=2040-2309&rft.volume=2018&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1155%2F2018%2F4940593&rft.externalDBID=n%2Fa&rft.externalDocID=10_1155_2018_4940593 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2040-2295&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2040-2295&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2040-2295&client=summon |