مشروع البحث: SEZGĠSEL OPTĠMĠZAS ON YONTEMĠ ĠLE ĠNSAN RETĠNA G RÜNTÜLERĠNDE OPTĠK DĠSK SEGMENTAS ONU VE DERĠN ĞRENME ĠLE HASTALIK TEġHĠSĠ
| dc.contributor.advisor | DR. ABDULKADĠR KARACI | |
| dc.date.accessioned | 2025-08-19T07:57:46Z | |
| dc.date.available | 2025-08-19T07:57:46Z | |
| dc.description | Comprehensive experiments are conducted to identify optimal hyperparameters, significantly enhancing the accuracy of Glokom detection. GWO achieved an average sensitivity of 96.04%, a specificity of 99.58%, an accuracy of 99.39%, a DICE coefficient of 94.15%, and a Jaccard index of 90.4% on the Drishti-GS1 dataset for segmentation. For classification, the Swin Transformer model achieved high test accuracy of 100% for hold-out validation and 88.18% for 3-fold cross-validation on the Drishti-GS1 dataset. Additionally, on the ORIGA dataset, the Swin Transformer model obtained remarkable results with 96.15% test accuracy for hold-out validation and InceptionV3 achieved 93.84% test accuracy for 5-fold cross-validation. Compared to previous studies, the proposed models in this work have demonstrated superior performance. | |
| dc.description.abstract | Glaucoma is a prevalent eye disease characterized by damage to the optic nerve, often resulting in irreversible vision loss. Its insidious nature, particularly in early stages with minimal symptoms, complicates timely diagnosis and intervention. This study addresses the critical challenge of localizing and segmenting the optic disc in retinal images, along with classifying Glokom's presence to enhance diagnostic accuracy. This study introduces a novel approach for optic disc segmentation in human retina images using Grey Wolf Optimization (GWO), a nature-inspired meta-heuristic algorithm that simulates the social behavior of grey wolves, marking its first application in this context. | |
| dc.identifier | 665 | |
| dc.identifier.uri | https://dspace.academy.edu.ly/handle/123456789/1719 | |
| dc.subject | OĞRENME ĠLE HASTALIK TEġHĠSĠ” | |
| dc.title | SEZGĠSEL OPTĠMĠZAS ON YONTEMĠ ĠLE ĠNSAN RETĠNA G RÜNTÜLERĠNDE OPTĠK DĠSK SEGMENTAS ONU VE DERĠN ĞRENME ĠLE HASTALIK TEġHĠSĠ | |
| dspace.entity.type | Project | |
| project.endDate | 2025 | |
| project.funder.name | هندسة المواد | |
| project.investigator | حميدة علي المشرقي | |
| project.startDate | 2024 | |
| relation.isOrgUnitOfProject | d08f9c20-9b29-40ba-986c-2744c5edb342 | |
| relation.isOrgUnitOfProject.latestForDiscovery | d08f9c20-9b29-40ba-986c-2744c5edb342 |