FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images
The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. T...
Saved in:
Published in | IEEE access Vol. 9; pp. 159071 - 159080 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. To train the regression model, we transform the ground-truth center coordinates of optic disc and fovea of the IDRiD dataset to heatmaps using a 2D-Gaussian equation. The model is capable of pinpointing any single pixel in a vast 2D image space. The model is tested on IDRiD test dataset, Messidor, and G1020 datasets. The model outperforms the state-of-the-art methods on these datasets. The model is very robust and generic, which can be trained and used for the simultaneous localization of multiple landmarks in different medical image datasets. The full implementation code and the trained model with weights (based on Keras) are available for reuse at https://github.com/bhargav-jb/FundusPosNet . |
---|---|
AbstractList | The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. To train the regression model, we transform the ground-truth center coordinates of optic disc and fovea of the IDRiD dataset to heatmaps using a 2D-Gaussian equation. The model is capable of pinpointing any single pixel in a vast 2D image space. The model is tested on IDRiD test dataset, Messidor, and G1020 datasets. The model outperforms the state-of-the-art methods on these datasets. The model is very robust and generic, which can be trained and used for the simultaneous localization of multiple landmarks in different medical image datasets. The full implementation code and the trained model with weights (based on Keras) are available for reuse at https://github.com/bhargav-jb/FundusPosNet . |
Author | Arjunan, R. Vijaya Shenoy, Sathvik V. Nayak, S. Vighnesh Bhatkalkar, Bhargav J. |
Author_xml | – sequence: 1 givenname: Bhargav J. orcidid: 0000-0002-3282-4341 surname: Bhatkalkar fullname: Bhatkalkar, Bhargav J. organization: Department of Computer Science and Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, Karnataka, India – sequence: 2 givenname: S. Vighnesh orcidid: 0000-0002-8660-618X surname: Nayak fullname: Nayak, S. Vighnesh organization: Department of Computer and Communication Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, India – sequence: 3 givenname: Sathvik V. orcidid: 0000-0002-3293-5690 surname: Shenoy fullname: Shenoy, Sathvik V. organization: Department of Electronics and Communication Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, India – sequence: 4 givenname: R. Vijaya orcidid: 0000-0002-1402-6573 surname: Arjunan fullname: Arjunan, R. Vijaya email: arjun.connects@gmail.com organization: Department of Computer Science and Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, Karnataka, India |
BookMark | eNpNUctuEzEUHaEiUdp-QTeWWCf4NX6wiyYNDQotasvacjx3gqOJPdiTSvAT_DIOU1Xczb26Oi_pvK_OQgxQVdcEzwnB-uOiaW4eH-cUUzJnhEqq8JvqnBKhZ6xm4uy_-111lfMel1HlVcvz6s_qGNpj_hbzHYyf0AItAQa0AZuCDzu0TP4ZAroFOx7sgB5glyBnHwP6GlvoURcTGn8A-hJ9GNEmOtv733Y8AWKH7ofRO7T02SEbWrSKz2BRA2GElJEPqIl94U8J0Ppgd5Avq7ed7TNcveyL6vvq5qm5nW3uP6-bxWbmOFbjjPC63SrVqpppxgCTTlEhBSeY1II70lrA2ipZb7HjVkHHNXHEtUrzLcXWsYtqPem20e7NkPzBpl8mWm_-PWLaGZtK-h4M1lrSWmHXAeVCSCuZ0qwYOCtkx3jR-jBpDSn-PEIezT4eUyjxDRVYlhSSi4JiE8qlmHOC7tWVYHMq0kxFmlOR5qXIwrqeWB4AXhlaEEIFYX8Bjn-aDA |
CODEN | IAECCG |
CitedBy_id | crossref_primary_10_1109_ACCESS_2023_3278596 crossref_primary_10_1016_j_compbiomed_2022_106485 crossref_primary_10_3389_fneur_2022_949805 crossref_primary_10_1109_ACCESS_2022_3178372 |
Cites_doi | 10.1007/978-3-319-46478-7_44 10.1109/TENCON.2017.8227829 10.1109/TMI.2006.885336 10.1016/j.media.2019.03.007 10.1016/j.compmedimag.2013.06.002 10.1117/12.878145 10.1016/j.jocs.2017.02.006 10.1016/0734-189X(85)90016-7 10.1109/CVPR.2016.90 10.1109/CVPR.2015.7298664 10.1145/3285996.3285998 10.1016/j.neunet.2019.08.025 10.1007/978-3-319-46723-8_27 10.1109/IJCNN48605.2020.9207664 10.1016/j.bspc.2017.09.008 10.1109/CVPR.2019.00796 10.1007/978-3-030-00934-2_5 10.1007/978-3-319-41501-7_78 10.1016/j.media.2019.101561 10.1097/00006324-199205000-00006 10.1016/j.media.2009.08.003 10.1016/j.compbiomed.2017.04.016 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
DOI | 10.1109/ACCESS.2021.3127280 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEL CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Materials Research Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library Online url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2169-3536 |
EndPage | 159080 |
ExternalDocumentID | oai_doaj_org_article_09972580cfe24667a73893ae0ca67f34 10_1109_ACCESS_2021_3127280 9611261 |
Genre | orig-research |
GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RIG RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c408t-145db88d853933e01f826764101564c1dae09a875b0c4a8ef491c1cd894b20ac3 |
IEDL.DBID | RIE |
ISSN | 2169-3536 |
IngestDate | Fri Oct 04 13:05:48 EDT 2024 Thu Oct 10 15:19:21 EDT 2024 Fri Aug 23 00:57:37 EDT 2024 Wed Jun 26 19:25:38 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c408t-145db88d853933e01f826764101564c1dae09a875b0c4a8ef491c1cd894b20ac3 |
ORCID | 0000-0002-3282-4341 0000-0002-1402-6573 0000-0002-8660-618X 0000-0002-3293-5690 |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/9611261 |
PQID | 2607875746 |
PQPubID | 4845423 |
PageCount | 10 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_09972580cfe24667a73893ae0ca67f34 proquest_journals_2607875746 ieee_primary_9611261 crossref_primary_10_1109_ACCESS_2021_3127280 |
PublicationCentury | 2000 |
PublicationDate | 20210000 2021-00-00 20210101 2021-01-01 |
PublicationDateYYYYMMDD | 2021-01-01 |
PublicationDate_xml | – year: 2021 text: 20210000 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE access |
PublicationTitleAbbrev | Access |
PublicationYear | 2021 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref13 ref12 ref15 wang (ref7) 2017; 11 ref11 ref10 ref2 ref1 ref17 ronneberger (ref24) 2015 ref16 ref19 ref18 babu (ref22) 2018 tompson (ref6) 2014 ref23 ref26 ref20 yu (ref25) 2015 ref28 ref27 ref29 ren (ref21) 2015 ref8 ref9 ref4 ref3 haloi (ref14) 2016 ref5 |
References_xml | – ident: ref3 doi: 10.1007/978-3-319-46478-7_44 – ident: ref17 doi: 10.1109/TENCON.2017.8227829 – ident: ref11 doi: 10.1109/TMI.2006.885336 – ident: ref2 doi: 10.1016/j.media.2019.03.007 – start-page: 234 year: 2015 ident: ref24 article-title: U-Net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput -Assist Intervent contributor: fullname: ronneberger – ident: ref28 doi: 10.1016/j.compmedimag.2013.06.002 – ident: ref13 doi: 10.1117/12.878145 – volume: 11 start-page: 1 year: 2017 ident: ref7 article-title: The effectiveness of data augmentation in image classification using deep learning publication-title: Convolutional Neural Network for Visual Recognition contributor: fullname: wang – ident: ref19 doi: 10.1016/j.jocs.2017.02.006 – ident: ref27 doi: 10.1016/0734-189X(85)90016-7 – start-page: 91 year: 2015 ident: ref21 article-title: Faster R-CNN: Towards real-time object detection with region proposal networks publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: ren – ident: ref23 doi: 10.1109/CVPR.2016.90 – ident: ref4 doi: 10.1109/CVPR.2015.7298664 – ident: ref20 doi: 10.1145/3285996.3285998 – ident: ref29 doi: 10.1016/j.neunet.2019.08.025 – ident: ref5 doi: 10.1007/978-3-319-46723-8_27 – ident: ref10 doi: 10.1109/IJCNN48605.2020.9207664 – year: 2015 ident: ref25 article-title: Multi-scale context aggregation by dilated convolutions publication-title: arXiv 1511 07122 contributor: fullname: yu – ident: ref1 doi: 10.1016/j.bspc.2017.09.008 – ident: ref26 doi: 10.1109/CVPR.2019.00796 – ident: ref9 doi: 10.1007/978-3-030-00934-2_5 – year: 2018 ident: ref22 article-title: Relation networks for optic disc and fovea localization in retinal images publication-title: arXiv 1812 00883 contributor: fullname: babu – ident: ref15 doi: 10.1007/978-3-319-41501-7_78 – ident: ref8 doi: 10.1016/j.media.2019.101561 – ident: ref16 doi: 10.1097/00006324-199205000-00006 – ident: ref12 doi: 10.1016/j.media.2009.08.003 – ident: ref18 doi: 10.1016/j.compbiomed.2017.04.016 – year: 2016 ident: ref14 article-title: An unsupervised method for detection and validation of the optic disc and the Fovea publication-title: arXiv 1601 06608 contributor: fullname: haloi – start-page: 1799 year: 2014 ident: ref6 article-title: Joint training of a convolutional network and a graphical model for human pose estimation publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: tompson |
SSID | ssj0000816957 |
Score | 2.2944603 |
Snippet | The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 159071 |
SubjectTerms | Adaptive optics Biomedical optical imaging Coders Color Datasets Deep learning Encoders-Decoders Fovea Fundus image Gaussian blob Heating systems heatmap Localization Mathematical models Medical imaging Model testing Nonlinear optics optic disc Optical imaging Regression models regression neural network Retina Two dimensional models |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELVQT3BAQEEstGgOHIlqb2zH5rbdZbVUUBCiUm-Wv1KtRJPVbsrf4C8zjt1qKw69cI2i2J6ZzMyzZt4Q8l7GWkjlbBWiqiteN7ZyioYqON0yh7BFhwQUv57L1QU_uxSXe6O-Uk1YpgfOgjsZOzuFor6NUy5lY5sUYm2k3sqmrTMTKBN7YGr0wYpJLZpCM8SoPpnN53giBIRThjh1mqYy3QtFI2N_GbHyj18eg83yGXlaskSY5d09J49i94I82eMOPCR_ljdp6sb3fnceh48wg0WMGyh0qVew2CY3BqtURm438CNe5YLXDtL0s1-AuSpg7gdn_bob4EuKaKUjE_oWvqEj8bBY7zzYLsCy_x0tpItgTBZh3cEcXeYW8g7g8zX6pN1LcrH89HO-qsp0hcpzqoaKcRGcUgHjta7rSFmLSKORnKXmau5ZQBlri3DGUc-tii3XzDMflOZuSq2vX5GDru_iawIisJqLNlrFFRd1xKyipZ56Jrx1GIQn5MOtoM0mk2iYEXxQbbJeTNKLKXqZkNOkjLtXEwP2-ADtwhS7MA_ZxYQcJlXefUTL1CzFJuToVrWm_K07g5iuScT-XL75H0u_JY_TcfJFzRE5GLY38RhTl8G9G630L1CX580 priority: 102 providerName: Directory of Open Access Journals |
Title | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
URI | https://ieeexplore.ieee.org/document/9611261 https://www.proquest.com/docview/2607875746 https://doaj.org/article/09972580cfe24667a73893ae0ca67f34 |
Volume | 9 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9NAEF6VnuDAqyACpZoDxzrdtdf2LreQEIWKFoSo1Ju1L1dRwY4ShwN_gr_MjL2JeB24WZZtjfXtzsw3Ow_GXhUhywtlTeKDyhKZlSaxivvEW10Li7RFeyKKF5fF4kqeX-fXB-x0XwsTQuiTz8KYLvuzfN-6LYXKznRBBS_Ide4ong61Wvt4Cg2Q0HkZGwsJrs8m0yn-A1LAVCAzTWkO02_Gp-_RH4eq_KWJe_Myf8AudoINWSW3421nx-77Hz0b_1fyh-x-9DNhMiyMR-wgNI_ZvV-6Dx6xH_Mtze342G4uQ_caJjALYQWx4eoNzNakCGFBiehmBZ_CzZAy2wDNT_sC6O0Ceo9w3i6bDt6TTYw1ndDW8AFVkYPZcuPANB7m7bdggELJ6G7CsoEpKt01DBLAu6-o1TZP2NX87efpIonzGRInueoSIXNvlfJo8XWWBS5q5CplIQWVZ0snvAlcGyREljtpVKilFk44r7S0KTcue8oOm7YJzxjkXmQyr4NRUsk8C-iX1NxxJ3JnLJrxETvdAVethjYcVU9fuK4GnCvCuYo4j9gbAnf_KPXQ7m8gKFXcklVfM5wr7uqQyqIoTUnOG8rsTFHWmRyxIwJy_5GI4Ygd75ZKFff7pkJWWNJoAFk8__dbL9hdEnAI3hyzw269DS_RnensSR8GOOlX80-i5vMN |
link.rule.ids | 315,786,790,802,870,2115,4043,27954,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9NAEF5V5QAcyqMgUgrMgWOd7sZre5dbSIjSkgSEWqm31b5cRYAdJQ4H_gR_mVl7E_E6cLMs2xrr252Zb3YehLzOfZrlwujEeZEmPC10YgR1iTOyZAZpi3SBKM4X-fSaX95kNwfkbF8L471vk898P1y2Z_muttsQKjuXeSh4Qa5zB-08LbpqrX1EJYyQkFkRWwsxKs-HoxH-BZLAAUNuOgiTmH4zP22X_jhW5S9d3BqYyQMy34nW5ZV87m8b07ff_-ja-L-yPyRH0dOEYbc0HpEDXz0m93_pP3hMfky2YXLHx3qz8M0bGMLY-xXElqu3MF4HVQjTkIquV_DJ33ZJsxWECWpfAP1dQP8RLutl1cAsWMVY1Ql1CR9QGVkYLzcWdOVgUn_zGkIwGR1OWFYwQrW7hk4CuPiKem3zhFxP3l2Npkmc0JBYTkWTMJ45I4RDmy_T1FNWIlspcs5CgTa3zGlPpUZKZKjlWviSS2aZdUJyM6Dapk_JYVVX_hmBzLGUZ6XXgguepR49k5JaallmtUFD3iNnO-DUqmvEoVoCQ6XqcFYBZxVx7pG3Adz9o6GLdnsDQVFxU6q2ajgT1JZ-wPO80EVw31Bmq_OiTHmPHAcg9x-JGPbI6W6pqLjjNwp5YRGGA_D85N9vvSJ3p1fzmZpdLN4_J_eCsF0o55QcNuutf4HOTWNetmv6J9d_9Ww |
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=FundusPosNet%3A+A+Deep+Learning+Driven+Heatmap+Regression+Model+for+the+Joint+Localization+of+Optic+Disc+and+Fovea+Centers+in+Color+Fundus+Images&rft.jtitle=IEEE+access&rft.au=Bhatkalkar%2C+Bhargav+J.&rft.au=Nayak%2C+S.+Vighnesh&rft.au=Shenoy%2C+Sathvik+V.&rft.au=Arjunan%2C+R.+Vijaya&rft.date=2021&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=9&rft.spage=159071&rft.epage=159080&rft_id=info:doi/10.1109%2FACCESS.2021.3127280&rft.externalDocID=9611261 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |