Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network
A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning. In this paper,...
Gespeichert in:
| Veröffentlicht in: | British journal of radiology Jg. 94; H. 1126; S. 20210038 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
England
The British Institute of Radiology
01.10.2021
|
| Schlagworte: | |
| ISSN: | 0007-1285, 1748-880X, 1748-880X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning.
In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder-decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored.
The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (
< 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable.
The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images.
The hybrid CNN has valuable prospect with the ability to segment lung tumor. |
|---|---|
| AbstractList | A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning.OBJECTIVEA stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning.In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder-decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored.METHODSIn this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder-decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored.The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (p < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable.RESULTSThe newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (p < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable.The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images.CONCLUSIONSThe implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images.The hybrid CNN has valuable prospect with the ability to segment lung tumor.ADVANCES IN KNOWLEDGEThe hybrid CNN has valuable prospect with the ability to segment lung tumor. A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning. In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder-decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored. The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics ( < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable. The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images. The hybrid CNN has valuable prospect with the ability to segment lung tumor. |
| Author | Shao, Yan Duan, Yanhua Ying, Yanchen Xu, Zhiyong Gan, Wutian Quan, Hong Chen, Hua Huang, Ying Feng, Aihui Gu, Hengle Wang, Hao Fu, Xiaolong |
| Author_xml | – sequence: 1 givenname: Wutian surname: Gan fullname: Gan, Wutian – sequence: 2 givenname: Hao surname: Wang fullname: Wang, Hao – sequence: 3 givenname: Hengle surname: Gu fullname: Gu, Hengle – sequence: 4 givenname: Yanhua surname: Duan fullname: Duan, Yanhua – sequence: 5 givenname: Yan surname: Shao fullname: Shao, Yan – sequence: 6 givenname: Hua surname: Chen fullname: Chen, Hua – sequence: 7 givenname: Aihui surname: Feng fullname: Feng, Aihui – sequence: 8 givenname: Ying surname: Huang fullname: Huang, Ying – sequence: 9 givenname: Xiaolong surname: Fu fullname: Fu, Xiaolong – sequence: 10 givenname: Yanchen surname: Ying fullname: Ying, Yanchen – sequence: 11 givenname: Hong surname: Quan fullname: Quan, Hong – sequence: 12 givenname: Zhiyong surname: Xu fullname: Xu, Zhiyong |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34347535$$D View this record in MEDLINE/PubMed |
| BookMark | eNptUbtOwzAUtVARLY-NGXlCDKQ4fjTOglSVp1SJpQOb5ThOMSR2sRMQf49DWwSI6T587jnX9-yDgXVWA3CconGKWX5RPPsxRjhFiPAdMEozyhPO0eMAjBBCWZJizoZgP4TnvmQ52gNDQgnNGGEjYKZd6xrZGgWDXjbatjF3FroK1p1dwrZrnA8wdmYLaBq51AEWMuiyb0mIr-ApJFfw6aPwpoTK2TdXdz2DrKHVnf8K7bvzL4dgt5J10EebeAAWN9eL2V0yf7i9n03niSKctonkGOcVqVSqiMSFZJoTkuWYIs1YVfGyxFxmmk4mOclLhiSROY1ITQuUVpQcgMs17aorGl2q-KO4hFj5uLz_EE4a8fvFmiexdG8iJ5ijSU9wtiHw7rXToRWNCUrXtbTadUFgxjhlZEJxhJ781PoW2Z43AvAaoLwLwetKKLM-cJQ2tUiR6D0U0UOx9TAOnf8Z2vL-C_8EF5-eOQ |
| CitedBy_id | crossref_primary_10_1109_JBHI_2024_3400599 crossref_primary_10_1002_mp_17463 crossref_primary_10_3390_diagnostics12122971 crossref_primary_10_1038_s41598_025_95757_6 crossref_primary_10_3390_cancers15092573 crossref_primary_10_1016_j_radonc_2024_110344 crossref_primary_10_1109_JBHI_2022_3186275 crossref_primary_10_26599_BDMA_2024_9020088 crossref_primary_10_3390_biology10111084 crossref_primary_10_1148_radiol_233029 crossref_primary_10_1007_s00066_024_02262_2 crossref_primary_10_1177_15593258241263687 crossref_primary_10_1016_j_compmedimag_2024_102383 crossref_primary_10_1097_MCP_0000000000001179 crossref_primary_10_1186_s12885_024_11962_y crossref_primary_10_3390_jcm11247334 crossref_primary_10_1007_s10044_025_01425_w crossref_primary_10_1371_journal_pone_0266147 crossref_primary_10_4103_digm_digm_25_22 crossref_primary_10_1016_j_phro_2024_100637 crossref_primary_10_3390_cancers14225569 crossref_primary_10_1016_j_clon_2023_01_016 crossref_primary_10_3390_diagnostics15070846 crossref_primary_10_7717_peerj_cs_1802 crossref_primary_10_1371_journal_pone_0282107 crossref_primary_10_1002_mp_15904 crossref_primary_10_1007_s10278_025_01458_x |
| Cites_doi | 10.7150/ijms.3635 10.1109/TMI.2018.2845918 10.1002/cncr.32802 10.1109/TMI.2019.2923601 10.1016/j.neunet.2020.03.007 10.1007/s00066-015-0812-8 10.1109/TMI.2018.2821244 10.1016/j.cmpb.2020.105395 10.1002/mp.13331 10.1016/j.neucom.2018.10.099 10.1109/ACCESS.2019.2921434 10.1007/s00066-003-0976-5 10.1007/s00259-020-04781-3 10.1088/1361-6560/aaf44b 10.1109/TMI.2019.2928056 10.1007/s11548-016-1467-3 10.1093/jrr/rrz086 |
| ContentType | Journal Article |
| Copyright | 2021 The Authors. Published by the British Institute of Radiology 2021 The Authors |
| Copyright_xml | – notice: 2021 The Authors. Published by the British Institute of Radiology 2021 The Authors |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM |
| DOI | 10.1259/bjr.20210038 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic 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 Physics |
| DocumentTitleAlternate | Hybrid CNN for lung tumor segmentation on CT images |
| EISSN | 1748-880X |
| ExternalDocumentID | PMC9328064 34347535 10_1259_bjr_20210038 |
| Genre | Journal Article Comparative Study |
| GroupedDBID | --- .55 0R~ 169 18M 1OC 23N 2WC 33P 36B 4.4 53G 5GY 5RE 5WD 6J9 AANLZ AAUAY AAWTL AAXRX AAYXX ABCUV ABDFA ABEJV ABGNP ABJNI ABNHQ ABQNK ABSZQ ABXGK ABXVV ACAHQ ACCZN ACGFO ACGOF ACXBN ADBBV ADBTR ADIPN ADMGS ADNBA ADOZA ADVOB ADXAS AEGXH AENEX AEUYR AHMMS AIACR AIAGR AIURR AJAOE AJNCP ALMA_UNASSIGNED_HOLDINGS AMYDB AOIJS BAWUL BCRHZ BFHJK C45 CITATION CS3 DCZOG DIK DRFUL DRMAN DRSTM DU5 E3Z EBD EBS EMB EMOBN F5P GX1 H13 HYE IH2 KBYEO KOP L7B LATKE LEEKS LYRES MXFUL MXMAN MXSTM NU- OCZFY OJZSN OK1 OVD OWPYF P0W P2P ROX SJN SUPJJ SV3 TEORI TR2 TUS TWZ TXR W8F WIN WOQ X7M ZZTAW AGORE ALUQN CGR CUY CVF ECM EIF NPM 7X8 5PM |
| ID | FETCH-LOGICAL-c384t-a8229f3fc1c3a2ba5e83379240e55ff8dd28a7e466939d50a3a943a2e4b01f43 |
| ISICitedReferencesCount | 27 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000698627000008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0007-1285 1748-880X |
| IngestDate | Tue Nov 04 02:06:56 EST 2025 Thu Oct 02 07:03:21 EDT 2025 Mon Jul 21 06:00:34 EDT 2025 Sat Nov 29 06:21:55 EST 2025 Tue Nov 18 21:40:19 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1126 |
| Language | English |
| License | https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c384t-a8229f3fc1c3a2ba5e83379240e55ff8dd28a7e466939d50a3a943a2e4b01f43 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| OpenAccessLink | https://doi.org/10.1259/bjr.20210038 |
| PMID | 34347535 |
| PQID | 2558453642 |
| PQPubID | 23479 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_9328064 proquest_miscellaneous_2558453642 pubmed_primary_34347535 crossref_citationtrail_10_1259_bjr_20210038 crossref_primary_10_1259_bjr_20210038 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-10-01 |
| PublicationDateYYYYMMDD | 2021-10-01 |
| PublicationDate_xml | – month: 10 year: 2021 text: 2021-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | British journal of radiology |
| PublicationTitleAlternate | Br J Radiol |
| PublicationYear | 2021 |
| Publisher | The British Institute of Radiology |
| Publisher_xml | – name: The British Institute of Radiology |
| References | Baldeon Calisto (2024050215405672700_b15) 2020; 126 Kumar (2024050215405672700_b26) 2019; 39 Baskar (2024050215405672700_b2) 2012; 9 Huang (2024050215405672700_b22) 2017 Pang (2024050215405672700_b7) 2020; 47 Zhong (2024050215405672700_b27) 2019; 46 Liu (2024050215405672700_b10) 2018 Weiss (2024050215405672700_b3) 2003; 179 Jue (2024050215405672700_b28) 2019; 11769 Hossain (2024050215405672700_b18) 2019 Long (2024050215405672700_b13) 2015 Zheng (2024050215405672700_b16) 2019; 33 Nemoto (2024050215405672700_b14) 2020; 61 Henley (2024050215405672700_b1) 2020; 126 Chen (2024050215405672700_b9) 2016 Ronneberger (2024050215405672700_b8) 2015 Zhao (2024050215405672700_b25) 2018; 64 Pang (2024050215405672700_b6) 2019 Kamal (2024050215405672700_b5) 2020 Li (2024050215405672700_b21) 2020; 392 Schimek-Jasch (2024050215405672700_b4) 2015; 191 Jia (2024050215405672700_b11) 2020; 39 Li (2024050215405672700_b17) 2018; 37 Chen (2024050215405672700_b19) 2019; 7 Milletari (2024050215405672700_b20) 2016 Zhang (2024050215405672700_b23) 2020; 192 Zhang (2024050215405672700_b12) 2018; 37 Lu (2024050215405672700_b24) 2017; 12 |
| References_xml | – volume: 9 start-page: 193 year: 2012 ident: 2024050215405672700_b2 article-title: Cancer and radiation therapy: current advances and future directions publication-title: Int J Med Sci doi: 10.7150/ijms.3635 – volume: 37 start-page: 2663 year: 2018 ident: 2024050215405672700_b17 article-title: H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2018.2845918 – volume: 126 start-page: 2225 year: 2020 ident: 2024050215405672700_b1 article-title: Annual report to the nation on the status of cancer, part I: National cancer statistics publication-title: Cancer doi: 10.1002/cncr.32802 – start-page: 36 year: 2020 ident: 2024050215405672700_b5 article-title: Lung cancer tumor region segmentation using recurrent 3D-DenseUNet publication-title: MICCAI 2020 Thoracic Image Analysis (TIA) Workshop – volume: 39 start-page: 204 year: 2019 ident: 2024050215405672700_b26 article-title: Co-Learning feature fusion maps from PET-CT images of lung cancer publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2019.2923601 – volume: 126 start-page: 76 year: 2020 ident: 2024050215405672700_b15 article-title: AdaEn-Net: an ensemble of adaptive 2D-3D fully Convolutional networks for medical image segmentation publication-title: Neural Netw doi: 10.1016/j.neunet.2020.03.007 – volume: 191 start-page: 525 year: 2015 ident: 2024050215405672700_b4 article-title: A teaching intervention in a contouring dummy run improved target volume delineation in locally advanced non-small cell lung cancer: reducing the interobserver variability in multicentre clinical studies publication-title: Strahlenther Onkol doi: 10.1007/s00066-015-0812-8 – volume: 37 start-page: 2149 year: 2018 ident: 2024050215405672700_b12 article-title: Automatic segmentation of acute ischemic stroke from DWI using 3-D fully Convolutional DenseNets publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2018.2821244 – start-page: 1348 year: 2019 ident: 2024050215405672700_b18 article-title: A Pipeline for Lung Tumor Detection and Segmentation from CT Scans Using Dilated Convolutional Neural Networks – volume: 192 year: 2020 ident: 2024050215405672700_b23 article-title: DENSE-INception U-net for medical image segmentation publication-title: Comput Methods Programs Biomed doi: 10.1016/j.cmpb.2020.105395 – volume: 46 start-page: 619 year: 2019 ident: 2024050215405672700_b27 article-title: Simultaneous cosegmentation of tumors in PET-CT images using deep fully convolutional networks publication-title: Med Phys doi: 10.1002/mp.13331 – volume: 11769 start-page: 221 year: 2019 ident: 2024050215405672700_b28 article-title: Integrating cross-modality hallucinated MRI with CT to aid mediastinal lung tumor segmentation publication-title: Med Image Comput Comput Assist Interv – volume: 392 start-page: 277 year: 2020 ident: 2024050215405672700_b21 article-title: Deep learning for variational multimodality tumor segmentation in PET/CT publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.10.099 – volume: 7 start-page: 75591 year: 2019 ident: 2024050215405672700_b19 article-title: Hsn: hybrid segmentation network for small cell lung cancer segmentation publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2921434 – start-page: 234 year: 2015 ident: 2024050215405672700_b8 article-title: Brox T. U-net: Convolutional networks for biomedical image segmentation publication-title: Med Image Comput Comput Assist Interv – start-page: 589 year: 2019 ident: 2024050215405672700_b6 article-title: Communications in Computer and Information Science – start-page: 4700 year: 2017 ident: 2024050215405672700_b22 article-title: Densely connected convolutional networks – start-page: 3036 year: 2016 ident: 2024050215405672700_b9 article-title: Combining fully convolutional and recurrent neural networks for 3D biomedical image segmentation – start-page: 565 year: 2016 ident: 2024050215405672700_b20 article-title: V-Net: fully Convolutional neural networks for volumetric medical image segmentation – start-page: 851 year: 2018 ident: 2024050215405672700_b10 article-title: 3D anisotropic hybrid network: transferring Convolutional features from 2D images to 3D anisotropic volumes publication-title: Med Image Comput Comput Assist Interv – volume: 179 start-page: 21 year: 2003 ident: 2024050215405672700_b3 article-title: The impact of gross tumor volume (GTV) and clinical target volume (CTV) definition on the total accuracy in radiotherapy theoretical aspects and practical experiences publication-title: Strahlenther Onkol doi: 10.1007/s00066-003-0976-5 – volume: 47 start-page: 2248 year: 2020 ident: 2024050215405672700_b7 article-title: CTumorGAN: a unified framework for automatic computed tomography tumor segmentation publication-title: Eur J Nucl Med Mol Imaging doi: 10.1007/s00259-020-04781-3 – volume: 64 start-page: 015011 year: 2018 ident: 2024050215405672700_b25 article-title: Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network publication-title: Phys Med Biol doi: 10.1088/1361-6560/aaf44b – volume: 39 start-page: 447 year: 2020 ident: 2024050215405672700_b11 article-title: 3D APA-Net: 3D Adversarial pyramid anisotropic Convolutional network for prostate segmentation in Mr images publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2019.2928056 – start-page: 3431 year: 2015 ident: 2024050215405672700_b13 article-title: Fully Convolutional Networks for Semantic Segmentation – volume: 12 start-page: 171 year: 2017 ident: 2024050215405672700_b24 article-title: Automatic 3D liver location and segmentation via convolutional neural network and graph cut publication-title: Int J Comput Assist Radiol Surg doi: 10.1007/s11548-016-1467-3 – volume: 61 start-page: 257 year: 2020 ident: 2024050215405672700_b14 article-title: Efficacy evaluation of 2D, 3D U-Net semantic segmentation and atlas-based segmentation of normal lungs excluding the trachea and main bronchi publication-title: J Radiat Res doi: 10.1093/jrr/rrz086 – volume: 33 start-page: 5909 year: 2019 ident: 2024050215405672700_b16 article-title: A new ensemble learning framework for 3D biomedical image segmentation publication-title: Proc Conf AAAI Artif Intell |
| SSID | ssj0007590 |
| Score | 2.4914126 |
| Snippet | A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The... |
| SourceID | pubmedcentral proquest pubmed crossref |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 20210038 |
| SubjectTerms | Humans Imaging, Three-Dimensional Lung Neoplasms - diagnostic imaging Neural Networks, Computer Radiographic Image Interpretation, Computer-Assisted - methods Tomography, X-Ray Computed |
| Title | Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/34347535 https://www.proquest.com/docview/2558453642 https://pubmed.ncbi.nlm.nih.gov/PMC9328064 |
| Volume | 94 |
| WOSCitedRecordID | wos000698627000008&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: Wiley Online Library Free Content customDbUrl: eissn: 1748-880X dateEnd: 20231231 omitProxy: false ssIdentifier: ssj0007590 issn: 0007-1285 databaseCode: WIN dateStart: 20090101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1748-880X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007590 issn: 0007-1285 databaseCode: DRFUL dateStart: 20090101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELe6DhAvCMZX-ZiMBLxUEUnsNPbj1DD2MCaEglaeIsdx1qI2mdpmGv8Afzfn2MmSDaTxwEsaXe3U6u-XO599d0boLUvBLCnBndQFBlOSSQc8WwZ3khMquUdFnSh8HJ6csNmMfxkMfjW5MBfLsCjY5SU__69QgwzA1qmz_wB3-1AQwD2ADleAHa63Av6g2pamDutGna1salE9KVxWOjWqWunzdUAyjceLldA1HrQpy7RIjP2oJgOJxvOfOpmrDku34wU0dfnL-qMOHu_tCNvqSJ1SFGuRLXqr9p_Mautpte2Q8tSuWB-Jsm1XGYtYnC1b3kWV6fxdFPNKdBcrfK8Ne7tSwKEDJtFsZCujc0PKHFAjs65SNicfN-TzTFb9DXUPvhvAkf7QhV3Bd3VNoZh-Ve1r1q6NQdTeD_RPoHfS9N5Bu34YcDZEu9HXw2_HrU0HoUlmssO3KRTQ_0P31_uTmxsey_XA285MJn6IHlgXBB8Y6jxCA1XsoXufbZDFHrpbRwXLzWO0aLmEu1zCZY41l7DhEgbJNMaGS7jmkhYJ7Ef4PSYRNkzCPSZhwyRsmfQExYcf4-mRY8_mcCRhdOsIfVBATnLpSSL8VASKERKCM--qIMhzlmU-E6GikwknPAtcQQSn0FLR1PVySp6iYVEW6jnCTKUTxvJcUCZoSgTLJBUBT3nOuQyZHKFx858m0tat18enLJM_IThC79rW56Zey1_avWngSUCh6l0yUaiy2iTgYzMaEPDLR-iZgat9EqGEgn8fjFDYA7JtoIu1978pFvO6aDv4SQym_y9uOb6X6P7V-_MKDbfrSr1Gd-QFvMrrfbQTzti-JelvyLq1Pg |
| linkProvider | Wiley-Blackwell |
| 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+segmentation+of+lung+tumors+on+CT+images+based+on+a+2D+%26+3D+hybrid+convolutional+neural+network&rft.jtitle=British+journal+of+radiology&rft.au=Gan%2C+Wutian&rft.au=Wang%2C+Hao&rft.au=Gu%2C+Hengle&rft.au=Duan%2C+Yanhua&rft.date=2021-10-01&rft.issn=0007-1285&rft.eissn=1748-880X&rft.volume=94&rft.issue=1126&rft_id=info:doi/10.1259%2Fbjr.20210038&rft.externalDBID=n%2Fa&rft.externalDocID=10_1259_bjr_20210038 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0007-1285&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0007-1285&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0007-1285&client=summon |