Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks
•Two approaches to detect retinal layers in rat OCT images are presented.•One approach is based on classical image processing and the other on deep learning.•Both methods significantly outperform a commercial image segmentation software.•Deep-learning-based method obtains promising results on unseen...
Gespeichert in:
| Veröffentlicht in: | Computer methods and programs in biomedicine Jg. 198; S. 105788 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Ireland
Elsevier B.V
01.01.2021
|
| Schlagworte: | |
| ISSN: | 0169-2607, 1872-7565, 1872-7565 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | •Two approaches to detect retinal layers in rat OCT images are presented.•One approach is based on classical image processing and the other on deep learning.•Both methods significantly outperform a commercial image segmentation software.•Deep-learning-based method obtains promising results on unseen databases.•A new rat OCT database with expert-reviewed segmentations is publicly available.
Background and Objective: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented. Methods: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture. Results: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons. Conclusions: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images. |
|---|---|
| AbstractList | •Two approaches to detect retinal layers in rat OCT images are presented.•One approach is based on classical image processing and the other on deep learning.•Both methods significantly outperform a commercial image segmentation software.•Deep-learning-based method obtains promising results on unseen databases.•A new rat OCT database with expert-reviewed segmentations is publicly available.
Background and Objective: Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented. Methods: One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture. Results: After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons. Conclusions: Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images. Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented. One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture. After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons. Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images. Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.BACKGROUND AND OBJECTIVEOptical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of great relevance to study possible toxic effect of drugs and other treatments before human trials. In this paper, two different approaches to detect the most significant retinal layers in a rat OCT image are presented.One approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.METHODSOne approach is based on a combination of local horizontal intensity profiles along with a new proposed variant of watershed transformation and the other is built upon an encoder-decoder convolutional network architecture.After a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.RESULTSAfter a wide validation, an averaged absolute distance error of 3.77 ± 2.59 and 1.90 ± 0.91 µm is achieved by both approaches, respectively, on a batch of the rat OCT database. After a second test of the deep-learning-based method using an unseen batch of the database, an averaged absolute distance error of 2.67 ± 1.25 µm is obtained. The rat OCT database used in this paper is made publicly available to facilitate further comparisons.Based on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images.CONCLUSIONSBased on the obtained results, it was demonstrated the competitiveness of the first approach since outperforms the commercial Insight image segmentation software (Phoenix Research Labs) as well as its utility to generate labelled images for validation purposes speeding significantly up the ground truth generation process. Regarding the second approach, the deep-learning-based method improves the results achieved by the more conventional method and also by other state-of-the-art techniques. In addition, it was verified that the results of the proposed network can be generalized to new rat OCT images. |
| ArticleNumber | 105788 |
| Author | Klemp, Kristian Larsen, Michael Colomer, Adrián Mossi, José M. Naranjo, Valery Morales, Sandra del Amor, Rocío Woldbye, David |
| Author_xml | – sequence: 1 givenname: Sandra surname: Morales fullname: Morales, Sandra email: sanmomar@i3b.upv.es organization: Instituto de Investigación e Innovación en Bioingeniería, I3B, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain – sequence: 2 givenname: Adrián surname: Colomer fullname: Colomer, Adrián organization: Instituto de Investigación e Innovación en Bioingeniería, I3B, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain – sequence: 3 givenname: José M. surname: Mossi fullname: Mossi, José M. organization: ITEAM Research Institute, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain – sequence: 4 givenname: Rocío surname: del Amor fullname: del Amor, Rocío organization: Instituto de Investigación e Innovación en Bioingeniería, I3B, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain – sequence: 5 givenname: David surname: Woldbye fullname: Woldbye, David organization: Laboratory of Neural Plasticity, Department of Neuroscience, University of Copenhagen, Denmark – sequence: 6 givenname: Kristian surname: Klemp fullname: Klemp, Kristian organization: Dept. of Ophthalmology, Rigshospitalet-Glostrup, Glostrup, Copenhagen, Denmark – sequence: 7 givenname: Michael surname: Larsen fullname: Larsen, Michael organization: Dept. of Ophthalmology, Rigshospitalet-Glostrup, Glostrup, Copenhagen, Denmark – sequence: 8 givenname: Valery surname: Naranjo fullname: Naranjo, Valery organization: Instituto de Investigación e Innovación en Bioingeniería, I3B, Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33130492$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkc1u3CAURlGVqpmkfYEuKlZVN55ibDBE3VSj_kkjRarSNbLxJWLCwBRwKr99cZ12kUW6ugKdcwXfd4HOfPCA0OuabGtS8_eHrT6ehi0ldLlgnRDP0KYWHa06xtkZ2hRIVpST7hxdpHQghFDG-At03jR1Q1pJNyh8h2x977DrZ4g4we0RfO6zDR5bj2MYyxFf726wPfa3kK7wPuiCW5_BJ5tnfIrBWAcJv8Vmcm7GOvj74KZlRQE9TPHPyL9CvEsv0XPTuwSvHuYl-vH5083ua7W__vJt93Ff6ZbVuQIgoxklwGia0bRUCtKDltA1RhohGZOccw285XRoejADDLoTICQwOQgOzSV6t-4tz_s5QcrqaJMG53oPYUqKtowLJoQkBX3zgE7DEUZ1iuWrcVZ_QyoAXQEdQ0oRzD-kJmppQh3U0oRamlBrE0USjyRt11xz7K17Wv2wqlACurcQVdIWvIbRRtBZjcE-rV890rWz3pbW7mD-n_wbgKS5wA |
| CitedBy_id | crossref_primary_10_3390_sym15020287 crossref_primary_10_3390_s23104737 crossref_primary_10_3390_s21238027 crossref_primary_10_3390_bioengineering10040407 crossref_primary_10_1016_j_cmpb_2024_108229 crossref_primary_10_1016_j_bspc_2021_102946 crossref_primary_10_1038_s41597_024_04259_z crossref_primary_10_3103_S1060992X24700589 crossref_primary_10_1080_02713683_2025_2537284 |
| Cites_doi | 10.1364/BOE.4.001133 10.1371/journal.pone.0181059 10.1364/BOE.8.002732 10.1109/TMI.2012.2225152 10.1364/OE.17.023719 10.1109/TMI.2010.2087390 10.1109/TBME.2010.2055057 10.1109/TMI.2009.2016958 10.1109/TPAMI.2016.2644615 10.1109/TPAMI.2016.2572683 10.1364/BOE.10.003987 10.1364/BOE.5.000348 10.1364/BOE.4.002712 10.1002/jbio.201500239 10.1364/BOE.8.003627 10.1364/OE.18.019413 |
| ContentType | Journal Article |
| Copyright | 2020 Copyright © 2020. Published by Elsevier B.V. |
| Copyright_xml | – notice: 2020 – notice: Copyright © 2020. Published by Elsevier B.V. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.cmpb.2020.105788 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| 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 |
| EISSN | 1872-7565 |
| ExternalDocumentID | 33130492 10_1016_j_cmpb_2020_105788 S0169260720316217 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .1- .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5RE 5VS 7-5 71M 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMZM ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACLOT ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFPUW AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EFKBS EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HMK HMO HVGLF HZ~ IHE J1W KOM LG9 M29 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- ROL RPZ SAE SBC SDF SDG SEL SES SEW SPC SPCBC SSH SSV SSZ T5K UHS WUQ XPP Z5R ZGI ZY4 ~G- ~HD AACTN AAIAV ABLVK ABTAH ABYKQ AFKWA AJBFU AJOXV AMFUW LCYCR RIG 9DU AAYXX CITATION AFCTW CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c451t-ee0dfd9eedf3df42980aec9e73f9f89559666ce6462b3aefbebc78e89e59b86e3 |
| ISICitedReferencesCount | 13 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000598417100003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0169-2607 1872-7565 |
| IngestDate | Sun Sep 28 01:03:41 EDT 2025 Thu Apr 03 07:09:34 EDT 2025 Tue Nov 18 22:25:03 EST 2025 Sat Nov 29 07:22:48 EST 2025 Fri Feb 23 02:48:17 EST 2024 Tue Oct 14 19:31:46 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Rodent OCT Intensity profile Rat OCT Optical coherence tomography Convolutional neural networks Layer segmentation |
| Language | English |
| License | Copyright © 2020. Published by Elsevier B.V. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c451t-ee0dfd9eedf3df42980aec9e73f9f89559666ce6462b3aefbebc78e89e59b86e3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0169260720316217 |
| PMID | 33130492 |
| PQID | 2456858890 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2456858890 pubmed_primary_33130492 crossref_primary_10_1016_j_cmpb_2020_105788 crossref_citationtrail_10_1016_j_cmpb_2020_105788 elsevier_sciencedirect_doi_10_1016_j_cmpb_2020_105788 elsevier_clinicalkey_doi_10_1016_j_cmpb_2020_105788 |
| PublicationCentury | 2000 |
| PublicationDate | January 2021 2021-01-00 2021-Jan 20210101 |
| PublicationDateYYYYMMDD | 2021-01-01 |
| PublicationDate_xml | – month: 01 year: 2021 text: January 2021 |
| PublicationDecade | 2020 |
| PublicationPlace | Ireland |
| PublicationPlace_xml | – name: Ireland |
| PublicationTitle | Computer methods and programs in biomedicine |
| PublicationTitleAlternate | Comput Methods Programs Biomed |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Chen, Ong, Luo, Lee, Chia, Galvao, Metzger, Gifford, Chin, Ali (bib0007) 2020; vol. 11313 Lu, l. Cheung, Liu, Lim, s. Leung, Wong (bib0020) 2010; 57 Chiu, Li, Nicholas, Toth, Izatt, Farsiu (bib0008) 2010; 18 Dufour, Ceklic, Abdillahi, Schroder, Dzanet, Wolf-Schnurrbusch, Kowal (bib0009) 2013; 32 Srinivasan, Heflin, Izatt, Arshavsky, Farsiu (bib0029) 2014; 5 Roy, Conjeti, Sheet, Katouzian, Navab, Wachinger (bib0026) 2017 del Amor, Morales, Colomer, Mossi, Woldbye, Klemp, Larsen, Naranjo (bib0001) 2019 Nair, Hinton (bib0023) 2010 Roy, Conjeti, Karri, Sheet, Katouzian, Wachinger, Navab (bib0025) 2017; 8 He, Carass, Yun, Zhao, Jedynak, Solomon, Saidha, Calabresi, Prince (bib0013) 2017 Ioffe, Szegedy (bib0014) 2015 Kugelman, Alonso-Caneiro, Read, Hamwood, Vincent, Chen, Collins (bib0017) 2019; 9 Antony, Abràmoff, Harper, Jeong, Sohn, Kwon, Kardon, Garvin (bib0002) 2013; 4 Liu, Fu, Pan, Liu, Hu, Liu, Zhang (bib0019) 2018 Ruan, Xue, Li, Liu, Lu, Chen, Liu, Niu, Li (bib0027) 2019; 10 Lang, Carass, Hauser, Sotirchos, Calabresi, Ying, Prince (bib0018) 2013; 4 Shelhamer, Long, Darrell (bib0028) 2017; 39 Pekala, Joshi, Freund, Bressler, DeBuc, Burlina (bib0024) 2018 Fang, Cunefare, Wang, Guymer, Li, Farsiu (bib0010) 2017; 8 Yazdanpanah, Hamarneh, Smith, Sarunic (bib0031) 2011; 30 Mishra, Wong, Bizheva, Clausi (bib0021) 2009; 17 Beucher, Meyer (bib0006) 1993; 34 Jing, Boglarka, Erika, Palya, Mark, E., Cabrera (bib0015) 2016; 9 Bertalmio, Bertozzi, Sapiro (bib0005) 2001; vol. 1 Badrinarayanan, Kendall, Cipolla (bib0004) 2017; 39 Kiaee, Fahimi, Rabbani (bib0016) 2018 Vedaldi, Lenc (bib0030) 2015 Gopinath, Rangrej, Sivaswamy (bib0012) 2017 Antony, Kim, Lang, Carass, Prince, Zack (bib0003) 2017; 12 Morales, Colomer, Mossi, del Amor, Woldbye, Klemp, Larsen, Naranjo (bib0022) 2020 Garvin, Abramoff, Wu, Russell, Burns, Sonka (bib0011) 2009; 28 Lang (10.1016/j.cmpb.2020.105788_bib0018) 2013; 4 Kugelman (10.1016/j.cmpb.2020.105788_bib0017) 2019; 9 Roy (10.1016/j.cmpb.2020.105788_bib0025) 2017; 8 Antony (10.1016/j.cmpb.2020.105788_bib0002) 2013; 4 del Amor (10.1016/j.cmpb.2020.105788_bib0001) 2019 Garvin (10.1016/j.cmpb.2020.105788_bib0011) 2009; 28 Antony (10.1016/j.cmpb.2020.105788_bib0003) 2017; 12 Dufour (10.1016/j.cmpb.2020.105788_bib0009) 2013; 32 Ruan (10.1016/j.cmpb.2020.105788_bib0027) 2019; 10 Vedaldi (10.1016/j.cmpb.2020.105788_bib0030) 2015 He (10.1016/j.cmpb.2020.105788_bib0013) 2017 Roy (10.1016/j.cmpb.2020.105788_bib0026) 2017 Srinivasan (10.1016/j.cmpb.2020.105788_bib0029) 2014; 5 Nair (10.1016/j.cmpb.2020.105788_bib0023) 2010 Chen (10.1016/j.cmpb.2020.105788_bib0007) 2020; vol. 11313 Jing (10.1016/j.cmpb.2020.105788_bib0015) 2016; 9 Yazdanpanah (10.1016/j.cmpb.2020.105788_bib0031) 2011; 30 Morales (10.1016/j.cmpb.2020.105788_bib0022) 2020 Beucher (10.1016/j.cmpb.2020.105788_bib0006) 1993; 34 Shelhamer (10.1016/j.cmpb.2020.105788_bib0028) 2017; 39 Lu (10.1016/j.cmpb.2020.105788_bib0020) 2010; 57 Mishra (10.1016/j.cmpb.2020.105788_bib0021) 2009; 17 Badrinarayanan (10.1016/j.cmpb.2020.105788_bib0004) 2017; 39 Gopinath (10.1016/j.cmpb.2020.105788_bib0012) 2017 Pekala (10.1016/j.cmpb.2020.105788_bib0024) 2018 Kiaee (10.1016/j.cmpb.2020.105788_bib0016) 2018 Liu (10.1016/j.cmpb.2020.105788_sbref0019) 2018 Bertalmio (10.1016/j.cmpb.2020.105788_sbref0005) 2001; vol. 1 Ioffe (10.1016/j.cmpb.2020.105788_bib0014) 2015 Chiu (10.1016/j.cmpb.2020.105788_bib0008) 2010; 18 Fang (10.1016/j.cmpb.2020.105788_bib0010) 2017; 8 |
| References_xml | – volume: 18 start-page: 19413 year: 2010 end-page: 19428 ident: bib0008 article-title: Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation publication-title: Opt. Express – year: 2018 ident: bib0019 article-title: Automated layer segmentation of retinal optical coherence tomography images using a deep feature enhanced structured random forests classifier publication-title: IEEE Journal of Biomedical and Health Informatics – start-page: 807 year: 2010 end-page: 814 ident: bib0023 article-title: Rectified linear units improve restricted boltzmann machines publication-title: Proceedings of the 27th International Conference on International Conference on Machine Learning – volume: 17 start-page: 23719 year: 2009 end-page: 23728 ident: bib0021 article-title: Intra-retinal layer segmentation in optical coherence tomography images publication-title: Opt. Express – year: 2019 ident: bib0001 article-title: Towards automatic glaucoma assessment: an encoder-decoder CNN for retinal layer segmentation in rodent OCT images publication-title: Proceedings of the 2019 27th European Signal Processing Conference (EUSIPCO) – volume: 57 start-page: 2605 year: 2010 end-page: 2608 ident: bib0020 article-title: Automated layer segmentation of optical coherence tomography images publication-title: IEEE Trans. Biom. Eng. – volume: 34 start-page: 433 year: 1993 end-page: 481 ident: bib0006 article-title: The morphological approach to segmentation: the watershed transformation. Mathematical morphology in image processing publication-title: Opt. Eng. – start-page: 202 year: 2017 end-page: 209 ident: bib0013 article-title: Towards topological correct segmentation of macular OCT from cascaded FCNs publication-title: Fetal, Infant and Ophthalmic Medical Image Analysis – volume: 9 start-page: 478 year: 2016 end-page: 489 ident: bib0015 article-title: Performance evaluation of automated segmentation software on optical coherence tomography volume data publication-title: J. Biophotonics – volume: 8 start-page: 3627 year: 2017 end-page: 3642 ident: bib0025 article-title: ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks publication-title: Biomed. Opt. Express – volume: 4 start-page: 1133 year: 2013 end-page: 1152 ident: bib0018 article-title: Retinal layer segmentation of macular OCT images using boundary classification publication-title: Biomed. Opt. Express – start-page: 105788 year: 2020 ident: bib0022 article-title: Data for: Retinal layer segmentation in rodent OCT images: local intensity profiles & fully convolutional neural networks, Mendeley Data, V1 publication-title: Comput. Methods Programs Biomed. – year: 2015 ident: bib0030 article-title: Matconvnet – convolutional neural networks for MATLAB publication-title: Proceeding of the ACM Int. Conf. on Multimedia – year: 2017 ident: bib0012 article-title: A deep learning framework for segmentation of retinal layers from OCT images publication-title: CoRR – start-page: 2795 year: 2018 end-page: 2799 ident: bib0016 article-title: Intra-retinal layer segmentation of optical coherence tomography using 3d fully convolutional networks publication-title: 2018 25th IEEE International Conference on Image Processing (ICIP) – volume: 9 year: 2019 ident: bib0017 article-title: Automatic choroidal segmentation in OCT images using supervised deep learning methods publication-title: Sci. Rep. – volume: 10 start-page: 3987 year: 2019 end-page: 4002 ident: bib0027 article-title: Multi-phase level set algorithm based on fully convolutional networks (FCN-MLS) for retinal layer segmentation in SD-OCT images with central serous chorioretinopathy (CSC) publication-title: Biomed. Opt. Express – volume: vol. 1 year: 2001 ident: bib0005 article-title: Navier-Stokes, fluid dynamics, and image and video inpainting publication-title: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 – volume: vol. 11313 start-page: 821 year: 2020 end-page: 825 ident: bib0007 article-title: Comparison of training strategies for the segmentation of retina layers in optical coherence tomography images of rodent eyes using convolutional neural networks publication-title: Medical Imaging 2020: Image Processing – volume: 8 start-page: 2732 year: 2017 end-page: 2744 ident: bib0010 article-title: Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search publication-title: Biomed. Opt. Express – volume: 12 start-page: 1 year: 2017 end-page: 17 ident: bib0003 article-title: Automated segmentation of mouse OCT volumes (ASiMOV): validation & clinical study of a light damage model publication-title: PLOS ONE – volume: 39 start-page: 2481 year: 2017 end-page: 2495 ident: bib0004 article-title: SegNet: a deep convolutional encoder-decoder architecture for image segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – volume: 39 start-page: 640 year: 2017 end-page: 651 ident: bib0028 article-title: Fully convolutional networks for semantic segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. – volume: 5 start-page: 348 year: 2014 end-page: 365 ident: bib0029 article-title: Automatic segmentation of up to ten layer boundaries in SD-OCT images of the mouse retina with and without missing layers due to pathology publication-title: Biomed. Opt. Express – volume: 32 start-page: 531 year: 2013 end-page: 543 ident: bib0009 article-title: Graph-based multi-surface segmentation of OCT data using trained hard and soft constraints publication-title: IEEE Trans. Med. Imaging – start-page: 448 year: 2015 end-page: 456 ident: bib0014 article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift publication-title: Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 – year: 2018 ident: bib0024 article-title: Deep learning based retinal OCT segmentation publication-title: CoRR – start-page: 231 year: 2017 end-page: 239 ident: bib0026 article-title: Error corrective boosting for learning fully convolutional networks with limited data publication-title: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2017 – volume: 30 start-page: 484 year: 2011 end-page: 496 ident: bib0031 article-title: Segmentation of intra-retinal layers from optical coherence tomography images using an active contour approach publication-title: IEEE Trans. Med. Imaging – volume: 4 start-page: 2712 year: 2013 end-page: 2728 ident: bib0002 article-title: A combined machine-learning and graph-based framework for the segmentation of retinal surfaces in SD-OCT volumes publication-title: Biomed. Opt. Express – volume: 28 start-page: 1436 year: 2009 end-page: 1447 ident: bib0011 article-title: Automated 3-d intraretinal layer segmentation of macular spectral-domain optical coherence tomography images publication-title: IEEE Trans. Med. Imaging – volume: 4 start-page: 1133 issue: 7 year: 2013 ident: 10.1016/j.cmpb.2020.105788_bib0018 article-title: Retinal layer segmentation of macular OCT images using boundary classification publication-title: Biomed. Opt. Express doi: 10.1364/BOE.4.001133 – year: 2015 ident: 10.1016/j.cmpb.2020.105788_bib0030 article-title: Matconvnet – convolutional neural networks for MATLAB – volume: 12 start-page: 1 issue: 8 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0003 article-title: Automated segmentation of mouse OCT volumes (ASiMOV): validation & clinical study of a light damage model publication-title: PLOS ONE doi: 10.1371/journal.pone.0181059 – volume: 34 start-page: 433 year: 1993 ident: 10.1016/j.cmpb.2020.105788_bib0006 article-title: The morphological approach to segmentation: the watershed transformation. Mathematical morphology in image processing publication-title: Opt. Eng. – volume: 8 start-page: 2732 issue: 5 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0010 article-title: Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search publication-title: Biomed. Opt. Express doi: 10.1364/BOE.8.002732 – start-page: 202 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0013 article-title: Towards topological correct segmentation of macular OCT from cascaded FCNs – volume: 32 start-page: 531 issue: 3 year: 2013 ident: 10.1016/j.cmpb.2020.105788_bib0009 article-title: Graph-based multi-surface segmentation of OCT data using trained hard and soft constraints publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2012.2225152 – volume: 17 start-page: 23719 issue: 26 year: 2009 ident: 10.1016/j.cmpb.2020.105788_bib0021 article-title: Intra-retinal layer segmentation in optical coherence tomography images publication-title: Opt. Express doi: 10.1364/OE.17.023719 – volume: 30 start-page: 484 issue: 2 year: 2011 ident: 10.1016/j.cmpb.2020.105788_bib0031 article-title: Segmentation of intra-retinal layers from optical coherence tomography images using an active contour approach publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2010.2087390 – volume: vol. 11313 start-page: 821 year: 2020 ident: 10.1016/j.cmpb.2020.105788_bib0007 article-title: Comparison of training strategies for the segmentation of retina layers in optical coherence tomography images of rodent eyes using convolutional neural networks – year: 2018 ident: 10.1016/j.cmpb.2020.105788_sbref0019 article-title: Automated layer segmentation of retinal optical coherence tomography images using a deep feature enhanced structured random forests classifier publication-title: IEEE Journal of Biomedical and Health Informatics – volume: 57 start-page: 2605 issue: 10 year: 2010 ident: 10.1016/j.cmpb.2020.105788_bib0020 article-title: Automated layer segmentation of optical coherence tomography images publication-title: IEEE Trans. Biom. Eng. doi: 10.1109/TBME.2010.2055057 – start-page: 807 year: 2010 ident: 10.1016/j.cmpb.2020.105788_bib0023 article-title: Rectified linear units improve restricted boltzmann machines – volume: 28 start-page: 1436 issue: 9 year: 2009 ident: 10.1016/j.cmpb.2020.105788_bib0011 article-title: Automated 3-d intraretinal layer segmentation of macular spectral-domain optical coherence tomography images publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2009.2016958 – start-page: 2795 year: 2018 ident: 10.1016/j.cmpb.2020.105788_bib0016 article-title: Intra-retinal layer segmentation of optical coherence tomography using 3d fully convolutional networks – volume: 39 start-page: 2481 issue: 12 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0004 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 – start-page: 231 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0026 article-title: Error corrective boosting for learning fully convolutional networks with limited data – year: 2019 ident: 10.1016/j.cmpb.2020.105788_bib0001 article-title: Towards automatic glaucoma assessment: an encoder-decoder CNN for retinal layer segmentation in rodent OCT images – start-page: 448 year: 2015 ident: 10.1016/j.cmpb.2020.105788_bib0014 article-title: Batch normalization: accelerating deep network training by reducing internal covariate shift – volume: 39 start-page: 640 issue: 4 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0028 article-title: Fully convolutional networks for semantic segmentation publication-title: IEEE Trans. Pattern Anal. Mach.Intell. doi: 10.1109/TPAMI.2016.2572683 – volume: 10 start-page: 3987 issue: 8 year: 2019 ident: 10.1016/j.cmpb.2020.105788_bib0027 article-title: Multi-phase level set algorithm based on fully convolutional networks (FCN-MLS) for retinal layer segmentation in SD-OCT images with central serous chorioretinopathy (CSC) publication-title: Biomed. Opt. Express doi: 10.1364/BOE.10.003987 – volume: vol. 1 year: 2001 ident: 10.1016/j.cmpb.2020.105788_sbref0005 article-title: Navier-Stokes, fluid dynamics, and image and video inpainting – year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0012 article-title: A deep learning framework for segmentation of retinal layers from OCT images publication-title: CoRR – start-page: 105788 year: 2020 ident: 10.1016/j.cmpb.2020.105788_bib0022 article-title: Data for: Retinal layer segmentation in rodent OCT images: local intensity profiles & fully convolutional neural networks, Mendeley Data, V1 publication-title: Comput. Methods Programs Biomed. – volume: 5 start-page: 348 issue: 2 year: 2014 ident: 10.1016/j.cmpb.2020.105788_bib0029 article-title: Automatic segmentation of up to ten layer boundaries in SD-OCT images of the mouse retina with and without missing layers due to pathology publication-title: Biomed. Opt. Express doi: 10.1364/BOE.5.000348 – volume: 9 issue: 13298 year: 2019 ident: 10.1016/j.cmpb.2020.105788_bib0017 article-title: Automatic choroidal segmentation in OCT images using supervised deep learning methods publication-title: Sci. Rep. – year: 2018 ident: 10.1016/j.cmpb.2020.105788_bib0024 article-title: Deep learning based retinal OCT segmentation publication-title: CoRR – volume: 4 start-page: 2712 issue: 12 year: 2013 ident: 10.1016/j.cmpb.2020.105788_bib0002 article-title: A combined machine-learning and graph-based framework for the segmentation of retinal surfaces in SD-OCT volumes publication-title: Biomed. Opt. Express doi: 10.1364/BOE.4.002712 – volume: 9 start-page: 478 issue: 5 year: 2016 ident: 10.1016/j.cmpb.2020.105788_bib0015 article-title: Performance evaluation of automated segmentation software on optical coherence tomography volume data publication-title: J. Biophotonics doi: 10.1002/jbio.201500239 – volume: 8 start-page: 3627 issue: 8 year: 2017 ident: 10.1016/j.cmpb.2020.105788_bib0025 article-title: ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks publication-title: Biomed. Opt. Express doi: 10.1364/BOE.8.003627 – volume: 18 start-page: 19413 issue: 18 year: 2010 ident: 10.1016/j.cmpb.2020.105788_bib0008 article-title: Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation publication-title: Opt. Express doi: 10.1364/OE.18.019413 |
| SSID | ssj0002556 |
| Score | 2.3599942 |
| Snippet | •Two approaches to detect retinal layers in rat OCT images are presented.•One approach is based on classical image processing and the other on deep... Optical coherence tomography (OCT) is a useful technique to monitor retinal layer state both in humans and animal models. Automated OCT analysis in rats is of... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 105788 |
| SubjectTerms | Animals Convolutional neural networks Intensity profile Layer segmentation Neural Networks, Computer Optical coherence tomography Rat OCT Rats Retina - diagnostic imaging Rodent OCT Rodentia Software Tomography, Optical Coherence |
| Title | Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0169260720316217 https://dx.doi.org/10.1016/j.cmpb.2020.105788 https://www.ncbi.nlm.nih.gov/pubmed/33130492 https://www.proquest.com/docview/2456858890 |
| Volume | 198 |
| WOSCitedRecordID | wos000598417100003&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: 1872-7565 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002556 issn: 0169-2607 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELe6DiFeJr7pgMlIiJcqVRI3ic1bNYYA0YGgSH2LbMdBndqkartp-9P47zh_pe1QB3vgpa0S23Jzv5zPvt_dIfQadhhhKWMZlJJx2KBIEQgi40BEcUgEk2nSF6bYRHZ6Ssdj9rXV-uVjYS6mWVXRy0s2_6-ihmsgbB06ewtxN4PCBfgNQodPEDt8_pPgv-kgZnjwU36lMzWrnzMXXmQ4jaAvtff_y_GoO5mBLjGMuM96QTOZIypD0XCFvJcGF_qA_sqw0920oanOgmm-DId8uWnh-jIRrjb10mUiMCwww721Af9bDv2hThNg9dV3aL5Ys4dANbvyLoNiMTFe_ahad4MX2rkxrMO_O-z5m4UC7M1qRx-X5v67evOQI442DjncuWfKAth6ZVuK29avdqpXFyy2FQL_WBXsAcVZT87mogfD2-rGtvF2Cu5rS2NDWPRcuLNcj5HrMXI7xh7aj7OE0TbaH3w8GX9qzACd280mlrczdxFbllx4fSa7rKJdux5j_YzuowO3bcEDC7cHqKWqh-ju0MnxEaod6rBBHd5EHZ5U2KIOA-qwRd1bbDCHG8xhjzn8BhvE4S3EYYs47BH3GP14fzI6_hC4Wh6B7CfRKlAqLMqCgUVWkqIEI4iGXEmmMlKykuo0iLCPlirtp7EgXJVCCZlRRZlKmKCpIk9Qu6or9QxhzlUa8yTO4Kn2M5FykqahioqkoIVkIe-gyD_LXLpE97reyjTfLcUO6jZ95jbNy42tiRdR7gOYYcnNAW839kqaXs68tWbrX_u98ijIQfdrhx6vVH2-zDVpgSaUsrCDnlp4NLMnJNIe9PjwVv_sObq3fv1eoPZqca5eojvyYjVZLo7QXjamRw7ovwHDTd07 |
| 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=Retinal+layer+segmentation+in+rodent+OCT+images%3A+Local+intensity+profiles+%26+fully+convolutional+neural+networks&rft.jtitle=Computer+methods+and+programs+in+biomedicine&rft.au=Morales%2C+Sandra&rft.au=Colomer%2C+Adri%C3%A1n&rft.au=Mossi%2C+Jos%C3%A9+M.&rft.au=del+Amor%2C+Roc%C3%ADo&rft.date=2021-01-01&rft.issn=0169-2607&rft.volume=198&rft.spage=105788&rft_id=info:doi/10.1016%2Fj.cmpb.2020.105788&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cmpb_2020_105788 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0169-2607&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0169-2607&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0169-2607&client=summon |