Diabetic retinopathy grading with respect to the segmented lesions

dc.contributor.authorKheradfallah, Hoda
dc.date.accessioned2022-05-19T15:39:39Z
dc.date.available2022-05-19T15:39:39Z
dc.date.issued2022-05-19
dc.date.submitted2022-05-14
dc.description.abstractOne of the leading causes of irreversible vision loss is Diabetic Retinopathy (DR). The International Clinical Diabetic Retinopathy scale (ICDRS) provides grading criteria for DR. Deep Convolutional Neural Networks (DCNNs) have high performance in DR grading in terms of classification evaluation metrics; however, these metrics are not sufficient for evaluation. The eXplainable Artificial Intelligence (XAI) methodology provides insight into the decisions made by networks by producing sparce, generic heat maps highlighting the most critical DR features. XAI also could not satisfy clinical criteria due to the lack of explanation on the number and types of lesions. Hence, we propose a computational tool box that provides lesion-based explanation according to grading system criteria for determining severity levels. According to ICDRS, DR has 10 major lesions and 4 severity levels. Experienced clinicians annotated 143 DR fundus images and we developed a toolbox containing 9 lesion-specified segmentation networks. Networks should detect lesions with high annotation resolution and then compute DR severity grade according to ICDRS. The network that was employed in this study is the optimized version of Holistically Nested Edge Detection Network (HEDNet). Using this model, the lesions such as hard exudates (Ex), cotton wool spots (CWS), neovascularization(NV), intraretinal haemorrhages (IHE) and vitreous preretinal haemorrhages (VPHE) were properly detected but the prediction of lesions such as venous beading (VB), microaneurysms (MA), intraretinal microvascular abnormalities (IRMA) and fibrous proliferation (FP) had lower mAPs. Consequently, this will affect the value of grading which uses the segmented masks of all contributing lesions.en
dc.identifier.urihttp://hdl.handle.net/10012/18305
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.relation.uriAPTOS 2019en
dc.relation.uriFGADRen
dc.subjectXAIen
dc.subjectexplainable AIen
dc.subjectdeep learningen
dc.subjectsegmentationen
dc.subjectAPTOSen
dc.subjectFGADRen
dc.titleDiabetic retinopathy grading with respect to the segmented lesionsen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Scienceen
uws-etd.degree.departmentSchool of Optometry and Vision Scienceen
uws-etd.degree.departmentSystems Design Engineering
uws-etd.degree.disciplineVision Scienceen
uws-etd.degree.disciplineFaculty of Engineering
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.embargo.terms0en
uws.contributor.advisorLakshminarayanan, Vasudevan
uws.contributor.advisorZelek, John
uws.contributor.affiliation1Faculty of Scienceen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Kheradfallah_Hoda.pdf
Size:
1.3 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.4 KB
Format:
Item-specific license agreed upon to submission
Description: