Academic Journal
View in EDS

Automatic Segmentation of Retinal Fluid and Photoreceptor Layer from Optical Coherence Tomography Images of Diabetic Macular Edema Patients Using Deep Learning and Associations with Visual Acuity

Bibliographic Details
Title: Automatic Segmentation of Retinal Fluid and Photoreceptor Layer from Optical Coherence Tomography Images of Diabetic Macular Edema Patients Using Deep Learning and Associations with Visual Acuity
Authors: Huan-Yu Hsu, Yu-Bai Chou, Ying-Chun Jheng, Zih-Kai Kao, Hsin-Yi Huang, Hung-Ruei Chen, De-Kuang Hwang, Shih-Jen Chen, Shih-Hwa Chiou, Yu-Te Wu
Source: Biomedicines, Vol 10, Iss 6, p 1269 (2022)
Publisher Information: MDPI AG, 2022.
Publication Year: 2022
Collection: LCC:Biology (General)
Subject Terms: optical coherence tomography segmentation, deep learning, diabetic macular edema, visual acuity, Biology (General), QH301-705.5
More Details: Diabetic macular edema (DME) is a highly common cause of vision loss in patients with diabetes. Optical coherence tomography (OCT) is crucial in classifying DME and tracking the results of DME treatment. The presence of intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) and the disruption of the ellipsoid zone (EZ), which is part of the photoreceptor layer, are three crucial factors affecting the best corrected visual acuity (BCVA). However, the manual segmentation of retinal fluid and the EZ from retinal OCT images is laborious and time-consuming. Current methods focus only on the segmentation of retinal features, lacking a correlation with visual acuity. Therefore, we proposed a modified U-net, a deep learning algorithm, to segment these features from OCT images of patients with DME. We also correlated these features with visual acuity. The IRC, SRF, and EZ of the OCT retinal images were manually labeled and checked by doctors. We trained the modified U-net model on these labeled images. Our model achieved Sørensen–Dice coefficients of 0.80 and 0.89 for IRC and SRF, respectively. The area under the receiver operating characteristic curve (ROC) for EZ disruption was 0.88. Linear regression indicated that EZ disruption was the factor most strongly correlated with BCVA. This finding agrees with that of previous studies on OCT images. Thus, we demonstrate that our segmentation network can be feasibly applied to OCT image segmentation and assist physicians in assessing the severity of the disease.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2227-9059
Relation: https://www.mdpi.com/2227-9059/10/6/1269; https://doaj.org/toc/2227-9059
DOI: 10.3390/biomedicines10061269
Access URL: https://doaj.org/article/4ef06942a98d4bc0b4df653323842415
Accession Number: edsdoj.4ef06942a98d4bc0b4df653323842415
Database: Directory of Open Access Journals
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsdoj&genre=article&issn=22279059&ISBN=&volume=10&issue=6&date=20220501&spage=1269&pages=1269-1269&title=Biomedicines&atitle=Automatic%20Segmentation%20of%20Retinal%20Fluid%20and%20Photoreceptor%20Layer%20from%20Optical%20Coherence%20Tomography%20Images%20of%20Diabetic%20Macular%20Edema%20Patients%20Using%20Deep%20Learning%20and%20Associations%20with%20Visual%20Acuity&aulast=Huan-Yu%20Hsu&id=DOI:10.3390/biomedicines10061269
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
  – Url: https://doaj.org/article/4ef06942a98d4bc0b4df653323842415
    Name: EDS - DOAJ (s8985755)
    Category: fullText
    Text: View record from DOAJ
    MouseOverText: View record from DOAJ
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.4ef06942a98d4bc0b4df653323842415
RelevancyScore: 917
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 917.376770019531
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Automatic Segmentation of Retinal Fluid and Photoreceptor Layer from Optical Coherence Tomography Images of Diabetic Macular Edema Patients Using Deep Learning and Associations with Visual Acuity
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Huan-Yu+Hsu%22">Huan-Yu Hsu</searchLink><br /><searchLink fieldCode="AR" term="%22Yu-Bai+Chou%22">Yu-Bai Chou</searchLink><br /><searchLink fieldCode="AR" term="%22Ying-Chun+Jheng%22">Ying-Chun Jheng</searchLink><br /><searchLink fieldCode="AR" term="%22Zih-Kai+Kao%22">Zih-Kai Kao</searchLink><br /><searchLink fieldCode="AR" term="%22Hsin-Yi+Huang%22">Hsin-Yi Huang</searchLink><br /><searchLink fieldCode="AR" term="%22Hung-Ruei+Chen%22">Hung-Ruei Chen</searchLink><br /><searchLink fieldCode="AR" term="%22De-Kuang+Hwang%22">De-Kuang Hwang</searchLink><br /><searchLink fieldCode="AR" term="%22Shih-Jen+Chen%22">Shih-Jen Chen</searchLink><br /><searchLink fieldCode="AR" term="%22Shih-Hwa+Chiou%22">Shih-Hwa Chiou</searchLink><br /><searchLink fieldCode="AR" term="%22Yu-Te+Wu%22">Yu-Te Wu</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Biomedicines, Vol 10, Iss 6, p 1269 (2022)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: MDPI AG, 2022.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2022
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Biology (General)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22optical+coherence+tomography+segmentation%22">optical coherence tomography segmentation</searchLink><br /><searchLink fieldCode="DE" term="%22deep+learning%22">deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22diabetic+macular+edema%22">diabetic macular edema</searchLink><br /><searchLink fieldCode="DE" term="%22visual+acuity%22">visual acuity</searchLink><br /><searchLink fieldCode="DE" term="%22Biology+%28General%29%22">Biology (General)</searchLink><br /><searchLink fieldCode="DE" term="%22QH301-705%2E5%22">QH301-705.5</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Diabetic macular edema (DME) is a highly common cause of vision loss in patients with diabetes. Optical coherence tomography (OCT) is crucial in classifying DME and tracking the results of DME treatment. The presence of intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) and the disruption of the ellipsoid zone (EZ), which is part of the photoreceptor layer, are three crucial factors affecting the best corrected visual acuity (BCVA). However, the manual segmentation of retinal fluid and the EZ from retinal OCT images is laborious and time-consuming. Current methods focus only on the segmentation of retinal features, lacking a correlation with visual acuity. Therefore, we proposed a modified U-net, a deep learning algorithm, to segment these features from OCT images of patients with DME. We also correlated these features with visual acuity. The IRC, SRF, and EZ of the OCT retinal images were manually labeled and checked by doctors. We trained the modified U-net model on these labeled images. Our model achieved Sørensen–Dice coefficients of 0.80 and 0.89 for IRC and SRF, respectively. The area under the receiver operating characteristic curve (ROC) for EZ disruption was 0.88. Linear regression indicated that EZ disruption was the factor most strongly correlated with BCVA. This finding agrees with that of previous studies on OCT images. Thus, we demonstrate that our segmentation network can be feasibly applied to OCT image segmentation and assist physicians in assessing the severity of the disease.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2227-9059
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://www.mdpi.com/2227-9059/10/6/1269; https://doaj.org/toc/2227-9059
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/biomedicines10061269
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/4ef06942a98d4bc0b4df653323842415" linkWindow="_blank">https://doaj.org/article/4ef06942a98d4bc0b4df653323842415</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.4ef06942a98d4bc0b4df653323842415
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.4ef06942a98d4bc0b4df653323842415
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/biomedicines10061269
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: 1269
    Subjects:
      – SubjectFull: optical coherence tomography segmentation
        Type: general
      – SubjectFull: deep learning
        Type: general
      – SubjectFull: diabetic macular edema
        Type: general
      – SubjectFull: visual acuity
        Type: general
      – SubjectFull: Biology (General)
        Type: general
      – SubjectFull: QH301-705.5
        Type: general
    Titles:
      – TitleFull: Automatic Segmentation of Retinal Fluid and Photoreceptor Layer from Optical Coherence Tomography Images of Diabetic Macular Edema Patients Using Deep Learning and Associations with Visual Acuity
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huan-Yu Hsu
      – PersonEntity:
          Name:
            NameFull: Yu-Bai Chou
      – PersonEntity:
          Name:
            NameFull: Ying-Chun Jheng
      – PersonEntity:
          Name:
            NameFull: Zih-Kai Kao
      – PersonEntity:
          Name:
            NameFull: Hsin-Yi Huang
      – PersonEntity:
          Name:
            NameFull: Hung-Ruei Chen
      – PersonEntity:
          Name:
            NameFull: De-Kuang Hwang
      – PersonEntity:
          Name:
            NameFull: Shih-Jen Chen
      – PersonEntity:
          Name:
            NameFull: Shih-Hwa Chiou
      – PersonEntity:
          Name:
            NameFull: Yu-Te Wu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 22279059
          Numbering:
            – Type: volume
              Value: 10
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Biomedicines
              Type: main
ResultId 1