Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/33779
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hemelings, Ruben | - |
dc.contributor.author | Elen, Bart | - |
dc.contributor.author | Blaschko, Matthew B. | - |
dc.contributor.author | Jacob, Julie | - |
dc.contributor.author | Stalmans, Ingeborg | - |
dc.contributor.author | DE BOEVER, Patrick | - |
dc.date.accessioned | 2021-03-30T09:47:44Z | - |
dc.date.available | 2021-03-30T09:47:44Z | - |
dc.date.issued | 2021 | - |
dc.date.submitted | 2021-03-16T13:09:55Z | - |
dc.identifier.citation | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 199 (Art N° 105920) | - |
dc.identifier.issn | 0169-2607 | - |
dc.identifier.uri | http://hdl.handle.net/1942/33779 | - |
dc.description.abstract | Background and Objectives: Pathological myopia (PM) is the seventh leading cause of blindness, with a reported global prevalence up to 3%. Early and automated PM detection from fundus images could aid to prevent blindness in a world population that is characterized by a rising myopia prevalence. We aim to assess the use of convolutional neural networks (CNNs) for the detection of PM and semantic segmentation of myopia-induced lesions from fundus images on a recently introduced reference data set. Methods: This investigation reports on the results of CNNs developed for the recently introduced Pathological Myopia (PALM) dataset, which consists of 1200 images. Our CNN bundles lesion segmentation and PM classification, as the two tasks are heavily intertwined. Domain knowledge is also inserted through the introduction of a new Optic Nerve Head (ONH)-based prediction enhancement for the segmentation of atrophy and fovea localization. Finally, we are the first to approach fovea localization using segmentation instead of detection or regression models. Evaluation metrics include area under the receiver operating characteristic curve (AUC) for PM detection, Euclidean distance for fovea localization, and Dice and F1 metrics for the semantic segmentation tasks (optic disc, retinal atrophy and retinal detachment). Results: Models trained with 400 available training images achieved an AUC of 0.9867 for PM detection, and a Euclidean distance of 58.27 pixels on the fovea localization task, evaluated on a test set of 400 images. Dice and F1 metrics for semantic segmentation of lesions scored 0.9303 and 0.9869 on optic disc, 0.8001 and 0.9135 on retinal atrophy, and 0.8073 and 0.7059 on retinal detachment, respectively. Conclusions: We report a successful approach for a simultaneous classification of pathological myopia and segmentation of associated lesions. Our work was acknowledged with an award in the context of the "Pathological Myopia detection from retinal images" challenge held during the IEEE International Symposium on Biomedical Imaging (April 2019). Considering that (pathological) myopia cases are often identified as false positives and negatives in glaucoma deep learning models, we envisage that the current work could aid in future research to discriminate between glaucomatous and highly-myopic eyes, complemented by the localization and segmentation of landmarks such as fovea, optic disc and atrophy. (C) 2021 Elsevier B.V. All rights reserved. | - |
dc.description.sponsorship | The first author is jointly supported by the Research Group Ophthalmology, KU Leuven and VITO NV. This research received funding from the Flemish Government under the "Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen" programme. No outside entities have been involved in the study design, in the collection, analysis and interpretation of data, in the writing of the manuscript, nor in the decision to submit the manuscript for publication. Thus, the authors declare that there are no conflicts of interest in this work. | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER IRELAND LTD | - |
dc.rights | 2021 Elsevier B.V. All rights reserved | - |
dc.subject.other | Pathological myopia | - |
dc.subject.other | fovea localization | - |
dc.subject.other | peripapillary atrophy | - |
dc.subject.other | retinal detachment | - |
dc.subject.other | convolutional neural network | - |
dc.subject.other | fundus image | - |
dc.subject.other | glaucoma | - |
dc.title | Pathological myopia classification with simultaneous lesion segmentation using deep learning | - |
dc.type | Journal Contribution | - |
dc.identifier.volume | 199 | - |
local.format.pages | 9 | - |
local.bibliographicCitation.jcat | A1 | - |
dc.description.notes | Hemelings, R (corresponding author), Katholieke Univ Leuven, VITO, Vito Hlth, Ind Zone Vlasmeer 7, B-2400 Mol, Belgium. | - |
dc.description.notes | ruben.hemelings@kuleuven.be | - |
dc.description.other | Hemelings, R (corresponding author), Katholieke Univ Leuven, VITO, Vito Hlth, Ind Zone Vlasmeer 7, B-2400 Mol, Belgium. ruben.hemelings@kuleuven.be | - |
local.publisher.place | ELSEVIER HOUSE, BROOKVALE PLAZA, EAST PARK SHANNON, CO, CLARE, 00000, IRELAND | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
local.bibliographicCitation.artnr | 105920 | - |
dc.identifier.doi | 10.1016/j.cmpb.2020.105920 | - |
dc.identifier.pmid | 33412285 | - |
dc.identifier.isi | WOS:000618824800001 | - |
dc.contributor.orcid | De Boever, Patrick/0000-0002-5197-8215 | - |
dc.identifier.eissn | 1872-7565 | - |
local.provider.type | wosris | - |
local.uhasselt.uhpub | yes | - |
local.description.affiliation | [Hemelings, Ruben; Stalmans, Ingeborg] Katholieke Univ Leuven, Res Grp Ophthalmol, Herestr 49, B-3000 Leuven, Belgium. | - |
local.description.affiliation | [Jacob, Julie; Stalmans, Ingeborg] UZ Leuven, Ophthalmol Dept, Herestr 49, B-3000 Leuven, Belgium. | - |
local.description.affiliation | [Blaschko, Matthew B.] Katholieke Univ Leuven, ESAT PSI, Kasteelpk Arenberg 10, B-3001 Leuven, Belgium. | - |
local.description.affiliation | [De Boever, Patrick] Hasselt Univ, Agoralaan Bldg D, B-3590 Diepenbeek, Belgium. | - |
local.description.affiliation | [Hemelings, Ruben; Elen, Bart; De Boever, Patrick] VITO NV, Boeretang 200, B-2400 Mol, Belgium. | - |
local.uhasselt.international | no | - |
item.validation | ecoom 2022 | - |
item.fulltext | With Fulltext | - |
item.fullcitation | Hemelings, Ruben; Elen, Bart; Blaschko, Matthew B.; Jacob, Julie; Stalmans, Ingeborg & DE BOEVER, Patrick (2021) Pathological myopia classification with simultaneous lesion segmentation using deep learning. In: COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 199 (Art N° 105920). | - |
item.accessRights | Open Access | - |
item.contributor | Hemelings, Ruben | - |
item.contributor | Elen, Bart | - |
item.contributor | Blaschko, Matthew B. | - |
item.contributor | Jacob, Julie | - |
item.contributor | Stalmans, Ingeborg | - |
item.contributor | DE BOEVER, Patrick | - |
crisitem.journal.issn | 0169-2607 | - |
crisitem.journal.eissn | 1872-7565 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1-s2.0-S0169260720317533-main (1).pdf Restricted Access | Published version | 1.36 MB | Adobe PDF | View/Open Request a copy |
PALM_RevisionNov2020_trackchanges_PDB_BE_RHFINAL.pdf | Peer-reviewed author version | 1.72 MB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
31
checked on Jul 10, 2024
Page view(s)
36
checked on Sep 5, 2022
Download(s)
8
checked on Sep 5, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.