DEHA-Net: A Dual-Encoder-Based Hard Attention Network with an Adaptive ROI Mechanism for Lung Nodule Segmentation
Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radi...
Uložené v:
| Vydané v: | Sensors (Basel, Switzerland) Ročník 23; číslo 4; s. 1989 |
|---|---|
| Hlavní autori: | , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Switzerland
MDPI AG
10.02.2023
MDPI |
| Predmet: | |
| ISSN: | 1424-8220, 1424-8220 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks’ ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network (DEHA-Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of DEHA-Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing DEHA-Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively. |
|---|---|
| AbstractList | Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks' ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network (DEHA-Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of DEHA-Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing DEHA-Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively.Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks' ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network (DEHA-Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of DEHA-Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing DEHA-Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively. Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks’ ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network (DEHA-Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of DEHA-Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing DEHA-Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively. Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks' ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network ( -Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of -Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing -Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively. |
| Author | Usman, Muhammad Shin, Yeong-Gil |
| AuthorAffiliation | Department of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea |
| AuthorAffiliation_xml | – name: Department of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea |
| Author_xml | – sequence: 1 givenname: Muhammad orcidid: 0000-0002-7278-8488 surname: Usman fullname: Usman, Muhammad – sequence: 2 givenname: Yeong-Gil surname: Shin fullname: Shin, Yeong-Gil |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36850583$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkktv1DAQgCNURB9w4A8gS1zgEOpH4jgcKi3twq60tBKPszVxJrtesvbWTlrx73HZsmorTh7Z33ya8cxxduC8wyx7zegHIWp6GrmgBatV_Sw7YgUvcsU5PXgQH2bHMa4p5UII9SI7FFKVtFTiKLu-mM4m-SUOH8mEXIzQ51NnfIsh_wQRWzKD0JLJMKAbrHckgbc-_CK3dlgRcGTSwnawN0i-Xc3JVzQrcDZuSOcDWYxuSS59O_ZIvuNykwxw53iZPe-gj_jq_jzJfn6e_jif5YurL_PzySI3hayHvGhMx4B2FTeiwrJCzpQsqOCGScoKgI53NVRMlZ3iinKONcW6AakQGIIQJ9l85209rPU22A2E39qD1X8vfFhqCIM1PWrZJAUzBgoQBS1b6ATjrBM1lk1JG0ius51rOzYbbE3qJUD_SPr4xdmVXvobXdeSVpImwbt7QfDXI8ZBb2w02Pfg0I9R80olTlRlmdC3T9C1H4NLX5WoqpaVkrJI1JuHFe1L-TfZBLzfASb4GAN2e4RRfbc1er81iT19whq7G1Zqxvb_yfgDrCzBhw |
| CitedBy_id | crossref_primary_10_1007_s12652_023_04711_9 crossref_primary_10_3390_bioengineering10070843 crossref_primary_10_1016_j_compbiomed_2025_111059 crossref_primary_10_1007_s42600_025_00410_w crossref_primary_10_3390_electronics14153009 crossref_primary_10_1109_ACCESS_2024_3447697 crossref_primary_10_1016_j_bspc_2024_107268 crossref_primary_10_1016_j_bspc_2023_105507 crossref_primary_10_1016_j_bspc_2023_105804 crossref_primary_10_1016_j_iot_2025_101598 crossref_primary_10_1016_j_radonc_2024_110344 crossref_primary_10_1109_ACCESS_2023_3313174 crossref_primary_10_33411_ijist_202571476492 crossref_primary_10_1016_j_bspc_2024_106804 crossref_primary_10_1371_journal_pone_0311080 crossref_primary_10_54392_irjmt2416 crossref_primary_10_1007_s10278_025_01458_x crossref_primary_10_3390_diagnostics14222604 crossref_primary_10_1016_j_compbiomed_2023_107570 |
| Cites_doi | 10.1007/978-3-319-24574-4_28 10.1016/j.eswa.2022.119475 10.1593/tlo.11232 10.1118/1.3528204 10.1016/j.ijleo.2018.08.086 10.1148/radiol.2017151022 10.1109/MSMW.2016.7537995 10.1109/ISBI.2018.8363765 10.1109/JBHI.2022.3198509 10.3390/math9131457 10.21037/jmai.2019.04.01 10.1109/JSTSP.2008.2011107 10.1016/S1076-6332(03)00671-8 10.1016/j.compbiomed.2022.105781 10.1109/ICPR48806.2021.9412218 10.1016/j.media.2017.06.014 10.1016/j.compbiomed.2017.11.013 10.1016/j.acra.2007.07.021 10.1016/j.media.2017.07.005 10.1109/LGRS.2018.2802944 10.1038/s41598-020-69817-y 10.1007/s13735-017-0141-z 10.1109/TITB.2007.899504 10.1109/TMI.2007.907555 10.1016/j.ins.2022.07.044 10.1109/EMBC.2017.8037182 10.1007/978-3-319-66179-7_65 10.1016/j.asoc.2019.105934 10.1109/TBME.2011.2167621 10.1016/j.ejmp.2019.06.003 10.1016/j.cmpb.2022.106946 10.1016/j.media.2010.08.005 10.1109/TETCI.2021.3051910 10.1007/978-3-030-32040-9_30 10.1007/978-3-030-30241-2_31 |
| ContentType | Journal Article |
| Copyright | 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 by the authors. 2023 |
| Copyright_xml | – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 by the authors. 2023 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU COVID DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3390/s23041989 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Coronavirus Research Database ProQuest Central Korea Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni) ProQuest Medical Database Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition Coronavirus Research Database ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef Publicly Available Content Database MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1424-8220 |
| ExternalDocumentID | oai_doaj_org_article_6b8281cca4a3405daf3121f39e5b50ba PMC9960760 36850583 10_3390_s23041989 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: HealthHub, Seoul, South Korea |
| GroupedDBID | --- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IAO ITC KQ8 L6V M1P M48 MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RNS RPM TUS UKHRP XSB ~8M ALIPV CGR CUY CVF ECM EIF NPM 3V. 7XB 8FK AZQEC COVID DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 5PM |
| ID | FETCH-LOGICAL-c469t-4bcf1a0f72c37e57e21864032c16014aaf2f9a7185f828022e90e9ba68ea1ea33 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 16 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000942305600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1424-8220 |
| IngestDate | Mon Nov 10 04:33:02 EST 2025 Tue Nov 04 02:06:33 EST 2025 Sun Nov 09 13:43:51 EST 2025 Tue Oct 07 07:22:32 EDT 2025 Mon Jul 21 05:44:24 EDT 2025 Tue Nov 18 22:44:28 EST 2025 Sat Nov 29 07:13:50 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | dual-encoder-based CNN lung nodule segmentation 3D segmentation hard attention |
| Language | English |
| License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c469t-4bcf1a0f72c37e57e21864032c16014aaf2f9a7185f828022e90e9ba68ea1ea33 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-7278-8488 |
| OpenAccessLink | https://doaj.org/article/6b8281cca4a3405daf3121f39e5b50ba |
| PMID | 36850583 |
| PQID | 2779678664 |
| PQPubID | 2032333 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_6b8281cca4a3405daf3121f39e5b50ba pubmedcentral_primary_oai_pubmedcentral_nih_gov_9960760 proquest_miscellaneous_2780763755 proquest_journals_2779678664 pubmed_primary_36850583 crossref_primary_10_3390_s23041989 crossref_citationtrail_10_3390_s23041989 |
| PublicationCentury | 2000 |
| PublicationDate | 20230210 |
| PublicationDateYYYYMMDD | 2023-02-10 |
| PublicationDate_xml | – month: 2 year: 2023 text: 20230210 day: 10 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Sensors (Basel, Switzerland) |
| PublicationTitleAlternate | Sensors (Basel) |
| PublicationYear | 2023 |
| Publisher | MDPI AG MDPI |
| Publisher_xml | – name: MDPI AG – name: MDPI |
| References | Ullah (ref_17) 2022; 608 Liu (ref_24) 2019; 63 Zhang (ref_27) 2022; 222 Chen (ref_25) 2021; 6 Guo (ref_14) 2018; 7 Diciotti (ref_9) 2008; 12 ref_35 ref_11 ref_33 Cao (ref_37) 2020; 86 ref_32 Jung (ref_36) 2018; 92 Tong (ref_21) 2018; 174 ref_30 Meyer (ref_28) 2007; 14 ref_16 ref_38 ref_15 Wang (ref_19) 2017; 40 Moltz (ref_3) 2009; 3 Zou (ref_34) 2004; 11 Diciotti (ref_10) 2011; 58 Litjens (ref_13) 2017; 42 Tyagi (ref_18) 2022; 147 Zhou (ref_39) 2022; 26 Usman (ref_5) 2020; 10 Ullah (ref_12) 2023; 216 Zhang (ref_26) 2018; 15 ref_23 Kubota (ref_31) 2011; 15 ref_22 Armato (ref_7) 2011; 38 Devaraj (ref_2) 2017; 284 ref_20 ref_29 Dehmeshki (ref_8) 2008; 27 Mozley (ref_1) 2012; 5 ref_4 ref_6 |
| References_xml | – ident: ref_32 – ident: ref_16 doi: 10.1007/978-3-319-24574-4_28 – volume: 216 start-page: 119475 year: 2023 ident: ref_12 article-title: MTSS-AAE: Multi-task semi-supervised adversarial autoencoding for COVID-19 detection based on chest X-ray images publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2022.119475 – volume: 5 start-page: 19 year: 2012 ident: ref_1 article-title: Measurement of tumor volumes improves RECIST-based response assessments in advanced lung cancer publication-title: Transl. Oncol. doi: 10.1593/tlo.11232 – volume: 38 start-page: 915 year: 2011 ident: ref_7 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 – volume: 174 start-page: 460 year: 2018 ident: ref_21 article-title: Improved U-NET network for pulmonary nodules segmentation publication-title: Optik doi: 10.1016/j.ijleo.2018.08.086 – volume: 284 start-page: 630 year: 2017 ident: ref_2 article-title: Use of volumetry for lung nodule management: Theory and practice publication-title: Radiology doi: 10.1148/radiol.2017151022 – ident: ref_11 doi: 10.1109/MSMW.2016.7537995 – ident: ref_30 doi: 10.1109/ISBI.2018.8363765 – volume: 26 start-page: 5619 year: 2022 ident: ref_39 article-title: A cascaded multi-stage framework for automatic detection and segmentation of pulmonary nodules in developing countries publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2022.3198509 – ident: ref_35 – ident: ref_38 doi: 10.3390/math9131457 – ident: ref_6 doi: 10.21037/jmai.2019.04.01 – volume: 3 start-page: 122 year: 2009 ident: ref_3 article-title: Advanced segmentation techniques for lung nodules, liver metastases, and enlarged lymph nodes in CT scans publication-title: IEEE J. Sel. Top. Signal Process. doi: 10.1109/JSTSP.2008.2011107 – volume: 11 start-page: 178 year: 2004 ident: ref_34 article-title: Statistical validation of image segmentation quality based on a spatial overlap index1: Scientific reports publication-title: Acad. Radiol. doi: 10.1016/S1076-6332(03)00671-8 – volume: 147 start-page: 105781 year: 2022 ident: ref_18 article-title: CSE-GAN: A 3D conditional generative adversarial network with concurrent squeeze-and-excitation blocks for lung nodule segmentation publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.105781 – ident: ref_23 doi: 10.1109/ICPR48806.2021.9412218 – ident: ref_4 – volume: 40 start-page: 172 year: 2017 ident: ref_19 article-title: Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.06.014 – volume: 92 start-page: 128 year: 2018 ident: ref_36 article-title: Ground-glass nodule segmentation in chest CT images using asymmetric multi-phase deformable model and pulmonary vessel removal publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2017.11.013 – volume: 14 start-page: 1464 year: 2007 ident: ref_28 article-title: The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation publication-title: Acad. Radiol. doi: 10.1016/j.acra.2007.07.021 – volume: 42 start-page: 60 year: 2017 ident: ref_13 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.07.005 – volume: 15 start-page: 749 year: 2018 ident: ref_26 article-title: Road extraction by deep residual u-net publication-title: IEEE Geosci. Remote. Sens. Lett. doi: 10.1109/LGRS.2018.2802944 – volume: 10 start-page: 12839 year: 2020 ident: ref_5 article-title: Volumetric lung nodule segmentation using adaptive roi with multi-view residual learning publication-title: Sci. Rep. doi: 10.1038/s41598-020-69817-y – volume: 7 start-page: 87 year: 2018 ident: ref_14 article-title: A review of semantic segmentation using deep neural networks publication-title: Int. J. Multimed. Inf. Retr. doi: 10.1007/s13735-017-0141-z – volume: 12 start-page: 7 year: 2008 ident: ref_9 article-title: 3-D segmentation algorithm of small lung nodules in spiral CT images publication-title: IEEE Trans. Inf. Technol. Biomed. doi: 10.1109/TITB.2007.899504 – volume: 27 start-page: 467 year: 2008 ident: ref_8 article-title: Segmentation of pulmonary nodules in thoracic CT scans: A region growing approach publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2007.907555 – volume: 608 start-page: 1541 year: 2022 ident: ref_17 article-title: Cascade multiscale residual attention cnns with adaptive roi for automatic brain tumor segmentation publication-title: Inf. Sci. doi: 10.1016/j.ins.2022.07.044 – ident: ref_20 doi: 10.1109/EMBC.2017.8037182 – ident: ref_29 doi: 10.1007/978-3-319-66179-7_65 – volume: 86 start-page: 105934 year: 2020 ident: ref_37 article-title: Dual-branch residual network for lung nodule segmentation publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.105934 – volume: 58 start-page: 3418 year: 2011 ident: ref_10 article-title: Automated segmentation refinement of small lung nodules in CT scans by local shape analysis publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2011.2167621 – volume: 63 start-page: 112 year: 2019 ident: ref_24 article-title: A cascaded dual-pathway residual network for lung nodule segmentation in CT images publication-title: Phys. Medica doi: 10.1016/j.ejmp.2019.06.003 – volume: 222 start-page: 106946 year: 2022 ident: ref_27 article-title: Multi-Scale Segmentation Squeeze-and-Excitation UNet with Conditional Random Field for Segmenting Lung Tumor from CT Images publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2022.106946 – volume: 15 start-page: 133 year: 2011 ident: ref_31 article-title: Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models publication-title: Med. Image Anal. doi: 10.1016/j.media.2010.08.005 – ident: ref_22 – volume: 6 start-page: 1190 year: 2021 ident: ref_25 article-title: Multi-Crop Convolutional Neural Networks for Fast Lung Nodule Segmentation publication-title: IEEE Trans. Emerg. Top. Comput. Intell. doi: 10.1109/TETCI.2021.3051910 – ident: ref_33 doi: 10.1007/978-3-030-32040-9_30 – ident: ref_15 doi: 10.1007/978-3-030-30241-2_31 |
| SSID | ssj0023338 |
| Score | 2.5176322 |
| Snippet | Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 1989 |
| SubjectTerms | 3D segmentation Adipates Algorithms Computer Systems Consensus dual-encoder-based CNN hard attention Humans Lung cancer lung nodule segmentation Medical research |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7BlgMcypsGCjKIA5eoSRzHCReUpVsVqYSqPNRb5CR2WWmbbDdZfj8ziTd0UcWFa-LDSPPwfOOZbwDeGiVplKdyq0QmblgI3y2MFK6poigoqDOsLw38OJFZFp-fJ6e24NbatspNTOwDddWUVCM_CKRMMLBGUfhheeXS1ih6XbUrNG7DDjGVhRPYmc6y07MRcnFEYAOfEEdwf9BSCZS6hLZuoZ6s_6YM8-9GyWs3z9H9_5X5AezanJOlg5E8hFu6fgT3rjERPoarw9lx6ma6e89SdrhWC3dW07T7yp3iNVcxeuBnadcNzZEsG5rHGVVxmapZWqklxU129uUT-6xpmnjeXjJMiNkJRhOWNdV6odlXfXFpZ53qJ_D9aPbt47FrtzG4JULoDvVYGl95RgYll1pITdusQo8HpY-gLlTKBCZReNUJgygOUwOdeDopVBRr5WvF-VOY1E2t94AhxhP0gEfcN2HsR8qUkeAyEIhvvEIGDrzbaCcvLVU5bcxY5AhZSJH5qEgH3oxHlwM_x02HpqTi8QBRavcfmtVFbj00jwoU20eDDhXHLLZShvuBb3iiRYFSKQf2N0rOrZ-3-R8NO_B6_I0eSs8uqtbNms7EHkZxKYQDzwZ7GiUh-n9PxNwBuWVpW6Ju_6nnP3sWcKLVkZH3_N9ivYC7AboB9Zn73j5MutVav4Q75a9u3q5eWXf5DdnUHwQ priority: 102 providerName: ProQuest |
| Title | DEHA-Net: A Dual-Encoder-Based Hard Attention Network with an Adaptive ROI Mechanism for Lung Nodule Segmentation |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/36850583 https://www.proquest.com/docview/2779678664 https://www.proquest.com/docview/2780763755 https://pubmed.ncbi.nlm.nih.gov/PMC9960760 https://doaj.org/article/6b8281cca4a3405daf3121f39e5b50ba |
| Volume | 23 |
| WOSCitedRecordID | wos000942305600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwEB7BwgEOiOcSWCqDOHCJNrHjOOGWslntSttQLQ-VU-QkNlTqpkubcuS3M5OkUYtW4sLFB9tSHHvsmc-e-QbgrdWKQnkqt4pV7AaF9N3CKunaKgx5QZ5h7dXA1wuVZdFsFk93Un2RT1hHD9xN3HFYICbw8TuBFmhcVNoKn_tWxEYW0ita0witni2Y6qGWQOTV8QgJBPXHa7r6JO-gPe3TkvTfZFn-7SC5o3FOH8KD3lRkSTfER3DL1I_h_g6B4BP4eZKeJW5mmvcsYScbvXDTmoLUV-4YtVPF6F2eJU3T-TSyrPP5ZnT5ynTNkkpf03HHLj-es4mhIOD5-oqhHcsu8BBg2bLaLAz7ZL5f9SFK9VP4cpp-_nDm9kkU3BKRb4PTX1pfe1bxUigjlaEkVIEneOkjFgu0ttzGGjWUtDjRqNFN7Jm40GFktG-0EM_goF7W5jkwhGaS3t2IsiaI_FDbMpRCcYmwxCsUd-DddnLzsmcYp0QXixyRBq1DPqyDA2-GrtcdrcZNnca0QkMHYsJuK1A-8l4-8n_JhwNH2_XN--25zrlSMWrpMAwceD0048ai1xJdm-WG-kQeHr5KSgcOO3EYRkKs_Z6MhANqT1D2hrrfUs9_tOTdxIajQu_F__i3l3CPo6yTE7nvHcFBs9qYV3C3_NXM16sR3FYz1ZbRCO6M02x6OWp3CZaT3ynWTc8n029_AMdKFfY |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB5VBQl64A01FFgQSFys2muvN0ZCKCWpEjU1CFqUm1nbuyVS6qSJA-JP8RuZ8asNqrj1wDXew9j59pv9ZucB8MooSaU8mZ2FMrT9RLh2YqSwTRYEPKHMsDI08HUko6gzHoefNuB3UwtDaZUNJ5ZEnc1SipHvcilDJNYg8N_Pz2yaGkW3q80IjQoWB_rXT5Rsy3fDHv6_rznf7x99GNj1VAE7RSlYoD2pcZVjJE89qYXUNJXJdzyeuihOfKUMN6FCyhYG1Qi6OB06OkxU0NHK1YoCoEj515DHJaWQyfG5wPNQ71XdizwvdHaXFHClnKQ1n1eOBrjsPPt3WuYFP7d_-3_7QnfgVn2iZt1qC9yFDZ3fg60LfRbvw1mvP-jakS7esi7rrdTU7udUy7-w99CJZ4zSF1i3KKrUTxZVqfGMYtRM5aybqTl5Bfb545AdaqqVnixPGR732Qi5kkWzbDXV7Is-Oa0rufIHcHwl7_wQNvNZrreBoYIVdD1JnX38jhsokwbCk1ygenMSyS1406AhTutG7DQPZBqjICPgxC1wLHjZLp1X3UcuW7RHkGoXUMPw8ofZ4iSu-ScOEjTbxe3qKw_P6Jkynstd44VaJGiVsmCnAVVcs9gyPkeUBS_ax8g_dKmkcj1b0ZqOgz5KCmHBowq_rSU03MARHc8CuYbsNVPXn-ST72WPc2oaJAPn8b_Neg43BkeHo3g0jA6ewE2OW5Ay6l1nBzaLxUo_hevpj2KyXDwrNyqDb1eN-z_KOHmW |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB5VLUJw4P0wFFgQSFys2GuvN0ZCKCWJGjU1ES-Vk1nbuyVS6qSxA-Kv8euYsR3ToIpbD1y9exjb38zsNzsPgOdGSSrlyewslKHtJ8K1EyOFbbIg4AllhlWhgc9jGUXdo6NwsgW_1rUwlFa5tomVoc7mKcXIO1zKEA1rEPgd06RFTPrDN4tTmyZI0U3repxGDZED_fMH0rfi9aiP__oF58PBx7f7djNhwE6RFpYoW2pc5RjJU09qITVNaPIdj6cuEhVfKcNNqNB8C4PMBN2dDh0dJiroauVqRcFQNP87eCT3Ucd2JqPDyZeW7nnI_upeRp4XOp2Cwq-UobThAatBAeedbv9O0jzj9YbX_-fvdQOuNWdt1quV4yZs6fwWXD3TgfE2nPYH-z070uUr1mP9lZrZg5yq_Jf2Hrr3jFFiA-uVZZ0UyqI6aZ5R9JqpnPUytSB_wd6_G7FDTVXU0-KEIRFgY7SiLJpnq5lmH_TxSVPjld-BTxfyzndhO5_n-j4w5LaCLi6p54_fdQNl0kB4kgvkdU4iuQUv18iI06ZFO00KmcVI1QhEcQsiC561Wxd1X5LzNu0RvNoN1Eq8ejBfHseNZYqDBMV2UZF95eHpPVPGc7lrvFCLBKVSFuyuARY39q2I_6DLgqftMlomum5SuZ6vaE_XQe8lhbDgXo3lVhIae-CIrmeB3ED5hqibK_n0W9X9nNoJycB58G-xnsBlhHs8HkUHD-EKR22kVHvX2YXtcrnSj-BS-r2cFsvHjdYy-HrRwP8N0UKD5Q |
| 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=DEHA-Net%3A+A+Dual-Encoder-Based+Hard+Attention+Network+with+an+Adaptive+ROI+Mechanism+for+Lung+Nodule+Segmentation&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Usman%2C+Muhammad&rft.au=Shin%2C+Yeong-Gil&rft.date=2023-02-10&rft.pub=MDPI&rft.eissn=1424-8220&rft.volume=23&rft.issue=4&rft_id=info:doi/10.3390%2Fs23041989&rft.externalDocID=PMC9960760 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon |