SS-net: split and spatial attention network for vessel segmentation of retinal OCT angiography
Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which...
Uloženo v:
| Vydáno v: | Applied optics. Optical technology and biomedical optics Ročník 61; číslo 9; s. 2357 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
20.03.2022
|
| Témata: | |
| ISSN: | 1539-4522, 2155-3165, 1539-4522 |
| On-line přístup: | Zjistit podrobnosti o přístupu |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which may lead to inaccurate segmentation for the extremely complex curve structure of retinal vessels. We propose a U-shaped network called SS-Net that is based on the attention mechanism to solve the problem of continuous segmentation of discontinuous vessels of a retinal OCTA. In this SS-Net, the improved SRes Block combines the residual structure and split attention to prevent the disappearance of gradient and gives greater weight to capillary features to form a backbone with an encoder and decoder architecture. In addition, spatial attention is applied to extract key information from spatial dimensions. To enhance the credibility, we use several indicators to evaluate the function of the SS-Net. In two datasets, the important indicators of accuracy reach 0.9258/0.9377, respectively, and a Dice coefficient is achieved, with an improvement of around 3% compared to state-of-the-art models in segmentation. |
|---|---|
| AbstractList | Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which may lead to inaccurate segmentation for the extremely complex curve structure of retinal vessels. We propose a U-shaped network called SS-Net that is based on the attention mechanism to solve the problem of continuous segmentation of discontinuous vessels of a retinal OCTA. In this SS-Net, the improved SRes Block combines the residual structure and split attention to prevent the disappearance of gradient and gives greater weight to capillary features to form a backbone with an encoder and decoder architecture. In addition, spatial attention is applied to extract key information from spatial dimensions. To enhance the credibility, we use several indicators to evaluate the function of the SS-Net. In two datasets, the important indicators of accuracy reach 0.9258/0.9377, respectively, and a Dice coefficient is achieved, with an improvement of around 3% compared to state-of-the-art models in segmentation.Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which may lead to inaccurate segmentation for the extremely complex curve structure of retinal vessels. We propose a U-shaped network called SS-Net that is based on the attention mechanism to solve the problem of continuous segmentation of discontinuous vessels of a retinal OCTA. In this SS-Net, the improved SRes Block combines the residual structure and split attention to prevent the disappearance of gradient and gives greater weight to capillary features to form a backbone with an encoder and decoder architecture. In addition, spatial attention is applied to extract key information from spatial dimensions. To enhance the credibility, we use several indicators to evaluate the function of the SS-Net. In two datasets, the important indicators of accuracy reach 0.9258/0.9377, respectively, and a Dice coefficient is achieved, with an improvement of around 3% compared to state-of-the-art models in segmentation. Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel segmentation on OCTA images plays an important role in disease diagnosis. Most deep learning methods are based on region segmentation, which may lead to inaccurate segmentation for the extremely complex curve structure of retinal vessels. We propose a U-shaped network called SS-Net that is based on the attention mechanism to solve the problem of continuous segmentation of discontinuous vessels of a retinal OCTA. In this SS-Net, the improved SRes Block combines the residual structure and split attention to prevent the disappearance of gradient and gives greater weight to capillary features to form a backbone with an encoder and decoder architecture. In addition, spatial attention is applied to extract key information from spatial dimensions. To enhance the credibility, we use several indicators to evaluate the function of the SS-Net. In two datasets, the important indicators of accuracy reach 0.9258/0.9377, respectively, and a Dice coefficient is achieved, with an improvement of around 3% compared to state-of-the-art models in segmentation. |
| Author | Meng, Jing Qi, Sumin Cui, Baoyu Jiang, Yingjie |
| Author_xml | – sequence: 1 givenname: Yingjie surname: Jiang fullname: Jiang, Yingjie – sequence: 2 givenname: Sumin surname: Qi fullname: Qi, Sumin – sequence: 3 givenname: Jing surname: Meng fullname: Meng, Jing – sequence: 4 givenname: Baoyu surname: Cui fullname: Cui, Baoyu |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35333254$$D View this record in MEDLINE/PubMed |
| BookMark | eNo1kEtPwzAQhC1URB9w4A8gH7mkeP1IHG5VxUuq1EPLlcgk6xJI7BC7oP57IiiX2ZHm2znMlIycd0jIJbA5iFTeLNZzqUBk7IRMOCiVCEjViExAiTyRivMxmYbwzphQMs_OyFgoIQRXckJeNpvEYbyloWvqSI2rBmdibRpqYkQXa-_oAHz7_oNa39MvDAEbGnDXDqn5zb2lPcbaDU_r5XYo2dV-15vu7XBOTq1pAl4c74w8399tl4_Jav3wtFysklKAiInQFehSGwApbWol52VmQec5qhSNzjBn1SCVZmmVWc10VUIKRrOSgVUG-Ixc__V2vf_cY4hFW4cSm8Y49PtQ8FRKBiwHOaBXR3T_2mJVdH3dmv5Q_G_CfwBu0WPj |
| CitedBy_id | crossref_primary_10_3389_fpubh_2022_1056226 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1364/AO.451370 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Physics |
| EISSN | 2155-3165 1539-4522 |
| ExternalDocumentID | 35333254 |
| Genre | Journal Article |
| GroupedDBID | 53G 5GY 8SL ALMA_UNASSIGNED_HOLDINGS CGR CUY CVF ECM EIF H~9 NPM OPLUZ ROP ROS 7X8 |
| ID | FETCH-LOGICAL-c313t-38d18c8a1144f6f422c7f1899e56ea87e90d7e9d806d7f808dc161a80c01f5a12 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000770929600035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1539-4522 |
| IngestDate | Wed Oct 01 13:54:43 EDT 2025 Thu Jan 02 22:55:31 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c313t-38d18c8a1144f6f422c7f1899e56ea87e90d7e9d806d7f808dc161a80c01f5a12 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 35333254 |
| PQID | 2644010914 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2644010914 pubmed_primary_35333254 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-Mar-20 20220320 |
| PublicationDateYYYYMMDD | 2022-03-20 |
| PublicationDate_xml | – month: 03 year: 2022 text: 2022-Mar-20 day: 20 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Applied optics. Optical technology and biomedical optics |
| PublicationTitleAlternate | Appl Opt |
| PublicationYear | 2022 |
| SSID | ssj0035497 ssj0020660 |
| Score | 2.3829255 |
| Snippet | Optical coherence tomography angiography (OCTA) has been widely used in clinical fields because of its noninvasive, high-resolution qualities. Accurate vessel... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 2357 |
| SubjectTerms | Algorithms Capillaries Fluorescein Angiography Retinal Vessels - diagnostic imaging Tomography, Optical Coherence |
| Title | SS-net: split and spatial attention network for vessel segmentation of retinal OCT angiography |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/35333254 https://www.proquest.com/docview/2644010914 |
| Volume | 61 |
| WOSCitedRecordID | wos000770929600035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA5qFbz4ftQXEbxGk93sbtaLlGLxYltohZ5cYh6loNnqrv39Tna3ehIEL2EvyYbJTPJNZvINQleeZSxWkhIWgosC5y0nklJJuHoxYE2MJ1pWxSaSfl9MJumwuXArmrTK5Z5YbdQ6V_6O_MYf3D6Mw_jd_J34qlE-utqU0FhFrRCgjE_pSibfUQTPVE5rvtSUeObwhlkojPlNZ3DNI5gf_R1ZVidMb_u_c9tBWw22xJ1aGXbRinF7aKPK8VTFPnoejYgz5S0uAHiWWDoNX7Aw0MWTbFZpj9jVaeEYsCxeeF7xV1yY6VvzQsnh3GL_7tH_Z9AdwyDTWUN6fYCeevfj7gNpyisQBcIqSSg0E0pI8Ii4jS0PApVYBv6XiWIjRWJSqqHRgsY6sYIKrQAeSkEVZTaSLDhEay535hjhIAU30cKoAJd4JJVILDhmNFaxttoy1kaXS8FloL4-JiGdyT-L7Ed0bXRUSz-b1zwbWQhQNIQBT_7Q-xRtBv5hAg3B7s9Qy4LxmnO0rhblrPi4qPQC2v7w8QuCH8Hz |
| linkProvider | ProQuest |
| 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=SS-net%3A+split+and+spatial+attention+network+for+vessel+segmentation+of+retinal+OCT+angiography&rft.jtitle=Applied+optics.+Optical+technology+and+biomedical+optics&rft.au=Jiang%2C+Yingjie&rft.au=Qi%2C+Sumin&rft.au=Meng%2C+Jing&rft.au=Cui%2C+Baoyu&rft.date=2022-03-20&rft.issn=1539-4522&rft.eissn=1539-4522&rft.volume=61&rft.issue=9&rft.spage=2357&rft_id=info:doi/10.1364%2FAO.451370&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1539-4522&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1539-4522&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1539-4522&client=summon |