Logo do repositório
 
Publicação

Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks

2026-05Artigo científico Acesso aberto
Ver registo simples
datacite.subject.sdg03:Saúde de Qualidade
dc.contributor.authorAfonso, João Duarte
dc.contributor.authorCamacho, Pedro
dc.contributor.authorPereira, Bruno
dc.contributor.authorMarques, João Pedro
dc.contributor.authorLopes, Daniel Simões
dc.contributor.authorCabral, Diogo
dc.date.accessioned2026-05-26T13:32:36Z
dc.date.available2026-05-26T13:32:36Z
dc.date.issued2026-05
dc.descriptionThis work was supported by research grants from Associação de Oftalmologistas para o Estudo da Retina (Bolsa para Investigação em Retina), Sociedade Portuguesa de Oftalmologia (Bolsa de Investigação Clinica 2023), and the Portuguese Recovery and Resilience Program (PRR) via IAPMEI/ANI/FCT (under Agenda C64502239900000057).
dc.description.abstractBackground: Accurate identification of outer retinal bands (ORBs) on spectral-domain optical coherence tomography (SD-OCT) is clinically important for the assessment and monitoring of several retinal diseases. However, manual segmentation of these ORBs is time-consuming and subject to considerable intra- and inter-observer variability. Deep convolutional neural networks (dCNNs) offer a promising approach for achieving more consistent and reproducible segmentation of retinal microstructures, yet their performance for individual ORBs and their dependence on grader reliability remain insufficiently characterized. This study aimed to compare manual grading and different dCNN architectures for the segmentation of individual ORBs in healthy subjects, while assessing the reproducibility of human annotations and the performance of automated methods. Methods: A cross-sectional observational study was conducted using foveal-centered SD-OCT scans obtained from healthy participants. Manual segmentation of the second hyperreflective band (Band 2), the third and fourth hyperreflective bands (Band 3+4), and photoreceptor outer segments (POS) was performed by two trained graders using onboard OCT software. Reproducibility was assessed using the intraclass and interclass correlation coefficient (ICC). Human annotations were used to train different dCNNs pretrained with Sparse masked modelling on unlabelled data. The performance of the dCNNs was evaluated using the dice score and pixel difference analyses. Results: One hundred eyes of healthy subjects were included. The intraclass correlation values were 0.737 (0.689, 0.779), 0.830 (0.795, 0.860), and 0.878 (0.852, 0.900), and the ICCs were 0.104 (-0.049, 0.253), 0.810 (0.740, 0.862), and 0.752 (0.678, 0.812) for Band 2, Band 3+4, and POS, respectively. From the dCNN, DRUNET showed the best performance: 0.916 for Band 2, 0.924 for Band 3+4, and 0.910 for POS. Pixel difference analysis between DRUNET and grader 1 showed a deviation of 0.89±0.44. Conclusions: Manual segmentation of ORBs demonstrated moderate to high repeatability, whereas Band 2 segmentation showed low reproducibility. DRUNET outperformed other dCNN architectures, showing great potential to reduce inter-observer variability.eng
dc.description.sponsorshipThis work was supported by research grants from Associação de Oftalmologistas para o Estudo da Retina (Bolsa para Investigação em Retina), Sociedade Portuguesa de Oftalmologia (Bolsa de Investigação Clinica 2023), and the Portuguese Recovery and Resilience Program (PRR) via IAPMEI/ANI/FCT (under Agenda C64502239900000057).
dc.identifier.citationAfonso JD, Camacho P, Pereira B, Marques JP, Lopes DS, Cabral D. Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks. Quant Imaging Med Surg. 2026;16(5):408.
dc.identifier.doi10.21037/qims-2025-aw-2093
dc.identifier.issn2223-4292
dc.identifier.issn2223-4306
dc.identifier.urihttp://hdl.handle.net/10400.21/22899
dc.language.isoeng
dc.peerreviewedyes
dc.publisherAME Publishing Company
dc.relation.hasversionhttps://qims.amegroups.org/article/view/152216/html
dc.relation.ispartofQuantitative Imaging in Medicine and Surgery
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectOphthalmology
dc.subjectOrthoptics
dc.subjectOptical coherence tomography
dc.subjectOCT
dc.subjectAutomatic segmentation
dc.subjectDeep learning
dc.subjectIntraclass correlation
dc.titleOuter retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networkseng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.issue5
oaire.citation.startPage408
oaire.citation.titleQuantitative Imaging in Medicine and Surgery
oaire.citation.volume16
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameCamacho
person.familyNameCardoso Pereira
person.givenNamePedro
person.givenNameBruno André
person.identifier.ciencia-id271F-B4E1-014E
person.identifier.ciencia-id1E1C-EB74-EB5E
person.identifier.orcid0000-0002-2986-5652
person.identifier.orcid0000-0003-4955-1770
relation.isAuthorOfPublicationc41e9c52-157e-4375-8005-b609cfc374e7
relation.isAuthorOfPublication38b0604f-dd74-4a8a-921c-0ac2eb4fdcc1
relation.isAuthorOfPublication.latestForDiscoveryc41e9c52-157e-4375-8005-b609cfc374e7

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Outer retinal band segmentation in healthy subjects_comparative study between human grading and deep convolutional neural networks.pdf
Tamanho:
1.03 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTeSL - Artigos