Publication:
Dynamic accommodation measurement using Purkinje reflections and machine learning

dc.contributor.departmentKUTTAM (Koç University Research Center for Translational Medicine)
dc.contributor.departmentDepartment of Electrical and Electronics Engineering
dc.contributor.departmentGraduate School of Sciences and Engineering
dc.contributor.departmentSchool of Medicine
dc.contributor.kuauthorAygün, Uğur
dc.contributor.kuauthorÖzhan, Faik Ozan
dc.contributor.kuauthorÜrey, Hakan
dc.contributor.kuauthorŞahin, Afsun
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.contributor.schoolcollegeinstituteGRADUATE SCHOOL OF SCIENCES AND ENGINEERING
dc.contributor.schoolcollegeinstituteResearch Center
dc.contributor.schoolcollegeinstituteSCHOOL OF MEDICINE
dc.date.accessioned2025-01-19T10:33:29Z
dc.date.issued2023
dc.description.abstractQuantifying eye movement is important for diagnosing various neurological and ocular diseases as well as AR/VR displays. We developed a simple setup for real-time dynamic gaze tracking and accommodation measurements based on Purkinje reflections, which are the reflections from front and back surfaces of the cornea and the eye lens. We used an accurate eye model in ZEMAX to simulate the Purkinje reflection positions at different focus distances of the eye, which matched the experimental data. A neural network was trained to simultaneously predict vergence and accommodation using data collected from 9 subjects. We demonstrated that the use of Purkinje reflection coordinates in machine learning resulted in precise estimation. The proposed system accurately predicted the accommodation with an accuracy better than 0.22 D using subject’s own data and 0.40 D using other subjects’ data with two-point calibration in tests performed with 9 subjects in our setup. © 2023, The Author(s).
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.indexedbyPubMed
dc.description.issue1
dc.description.openaccessAll Open Access; Gold Open Access; Green Open Access
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.description.sponsorshipThe authors would like to thank Fırat Turkkal and Arda Gulersoy for their help in prototype development. This work has been supported by European Innovation Council’s HORIZON-EIC-2021-TRANSITION- CHALLENGES Program, Grant Number 101057672 and Tübitak’s 2247-A National Lead Researchers Program, Project Number 120C145. Faik Ozan Ozhan is also supported by the TUBITAK’s 2210/A Master’s Scholarship Program.
dc.description.volume13
dc.identifier.doi10.1038/s41598-023-47572-0
dc.identifier.issn20452322
dc.identifier.quartileQ1
dc.identifier.scopus2-s2.0-85178883464
dc.identifier.urihttps://doi.org/10.1038/s41598-023-47572-0
dc.identifier.urihttps://hdl.handle.net/20.500.14288/26610
dc.identifier.wos1142614900058
dc.keywordsAccommodation
dc.keywordsOcular
dc.keywordsCornea
dc.keywordsEye movements
dc.keywordsLens
dc.keywordscrystalline
dc.keywordsMachine learning
dc.language.isoeng
dc.publisherNature Research
dc.relation.grantnoHORIZON EUROPE European Innovation Council, EIC, (101057672, 120C145, HORIZON-EIC-2021-TRANSITION); Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, TÜBİTAK
dc.relation.ispartofScientific Reports
dc.subjectMedicine
dc.titleDynamic accommodation measurement using Purkinje reflections and machine learning
dc.typeJournal Article
dspace.entity.typePublication
local.contributor.kuauthorÜrey, Hakan
local.contributor.kuauthorŞahin, Afsun
local.contributor.kuauthorAygün, Uğur
local.contributor.kuauthorÖzhan, Faik Ozan
local.publication.orgunit1College of Engineering
local.publication.orgunit1SCHOOL OF MEDICINE
local.publication.orgunit1GRADUATE SCHOOL OF SCIENCES AND ENGINEERING
local.publication.orgunit1Research Center
local.publication.orgunit2Department of Electrical and Electronics Engineering
local.publication.orgunit2KUTTAM (Koç University Research Center for Translational Medicine)
local.publication.orgunit2School of Medicine
local.publication.orgunit2Graduate School of Sciences and Engineering
relation.isOrgUnitOfPublication91bbe15d-017f-446b-b102-ce755523d939
relation.isOrgUnitOfPublication21598063-a7c5-420d-91ba-0cc9b2db0ea0
relation.isOrgUnitOfPublication3fc31c89-e803-4eb1-af6b-6258bc42c3d8
relation.isOrgUnitOfPublicationd02929e1-2a70-44f0-ae17-7819f587bedd
relation.isOrgUnitOfPublication.latestForDiscovery91bbe15d-017f-446b-b102-ce755523d939
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication434c9663-2b11-4e66-9399-c863e2ebae43
relation.isParentOrgUnitOfPublicationd437580f-9309-4ecb-864a-4af58309d287
relation.isParentOrgUnitOfPublication17f2dc8e-6e54-4fa8-b5e0-d6415123a93e
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
IR05206.pdf
Size:
3.64 MB
Format:
Adobe Portable Document Format