Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries
Abstract Early-stage glaucoma diagnosis is crucial for preventing permanent structural damage and irreversible vision loss. While various machine-learning approaches have been developed for glaucoma diagnosis, only a few specifically address early-stage detection. Moreover, existing early-stage dete...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-97883-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849700200692580352 |
|---|---|
| author | Ai-Su Yang Hong-Siang Wang Te-Jung Li Chin-Hsin Liu Chung-Ming Chen |
| author_facet | Ai-Su Yang Hong-Siang Wang Te-Jung Li Chin-Hsin Liu Chung-Ming Chen |
| author_sort | Ai-Su Yang |
| collection | DOAJ |
| description | Abstract Early-stage glaucoma diagnosis is crucial for preventing permanent structural damage and irreversible vision loss. While various machine-learning approaches have been developed for glaucoma diagnosis, only a few specifically address early-stage detection. Moreover, existing early-stage detection methods rely on unimodal information and exclude subjects with high myopia, which contradicts clinical practice and overlooks the adverse effect of high myopia on prediction performance. To develop a clinically practical tool, this study proposes a deep-learning-based, end-to-end early-stage glaucoma detection framework designed for a cohort likely with high myopia. This framework uniquely integrates functional information from visual field (VF) parameters of standard automated perimetry (SAP) and Pulsar perimetry (PP) with structural information derived from optical coherence tomography (OCT) thickness maps. It comprises three key components: 3D OCT ganglion cell complex (GCC) layer segmentation, thickness map generation, and early-stage glaucoma detection. Evaluated on 394 subjects using five-time, 10-fold cross-validation, the proposed system achieved a mean area under the receiver operating characteristic (ROC) curve of 0.887 ± 0.006, outperforming the Asaoka method without transfer learning and nine models based solely on VF parameters. Results further confirmed that incorporating SAP and PP parameters was essential for mitigating the adverse effects of high myopia. |
| format | Article |
| id | doaj-art-71bfb4b3f8d24d54bec7939d90889652 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-71bfb4b3f8d24d54bec7939d908896522025-08-20T03:18:22ZengNature PortfolioScientific Reports2045-23222025-04-0115111410.1038/s41598-025-97883-7Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetriesAi-Su Yang0Hong-Siang Wang1Te-Jung Li2Chin-Hsin Liu3Chung-Ming Chen4Department of Biomedical Engineering, National Taiwan UniversityDepartment of Biomedical Engineering, National Taiwan UniversityDepartment of Biomedical Engineering, National Taiwan UniversityDepartment of Ophthalmology, Yonghe Cardinal Tien HospitalDepartment of Biomedical Engineering, National Taiwan UniversityAbstract Early-stage glaucoma diagnosis is crucial for preventing permanent structural damage and irreversible vision loss. While various machine-learning approaches have been developed for glaucoma diagnosis, only a few specifically address early-stage detection. Moreover, existing early-stage detection methods rely on unimodal information and exclude subjects with high myopia, which contradicts clinical practice and overlooks the adverse effect of high myopia on prediction performance. To develop a clinically practical tool, this study proposes a deep-learning-based, end-to-end early-stage glaucoma detection framework designed for a cohort likely with high myopia. This framework uniquely integrates functional information from visual field (VF) parameters of standard automated perimetry (SAP) and Pulsar perimetry (PP) with structural information derived from optical coherence tomography (OCT) thickness maps. It comprises three key components: 3D OCT ganglion cell complex (GCC) layer segmentation, thickness map generation, and early-stage glaucoma detection. Evaluated on 394 subjects using five-time, 10-fold cross-validation, the proposed system achieved a mean area under the receiver operating characteristic (ROC) curve of 0.887 ± 0.006, outperforming the Asaoka method without transfer learning and nine models based solely on VF parameters. Results further confirmed that incorporating SAP and PP parameters was essential for mitigating the adverse effects of high myopia.https://doi.org/10.1038/s41598-025-97883-7Early glaucoma detectionRetinal layer segmentationOptical coherence tomographyStandard automated perimetryPulsar perimetryDeep learning |
| spellingShingle | Ai-Su Yang Hong-Siang Wang Te-Jung Li Chin-Hsin Liu Chung-Ming Chen Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries Scientific Reports Early glaucoma detection Retinal layer segmentation Optical coherence tomography Standard automated perimetry Pulsar perimetry Deep learning |
| title | Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries |
| title_full | Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries |
| title_fullStr | Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries |
| title_full_unstemmed | Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries |
| title_short | Diagnosis of early glaucoma likely combined with high myopia by integrating OCT thickness map and standard automated and Pulsar perimetries |
| title_sort | diagnosis of early glaucoma likely combined with high myopia by integrating oct thickness map and standard automated and pulsar perimetries |
| topic | Early glaucoma detection Retinal layer segmentation Optical coherence tomography Standard automated perimetry Pulsar perimetry Deep learning |
| url | https://doi.org/10.1038/s41598-025-97883-7 |
| work_keys_str_mv | AT aisuyang diagnosisofearlyglaucomalikelycombinedwithhighmyopiabyintegratingoctthicknessmapandstandardautomatedandpulsarperimetries AT hongsiangwang diagnosisofearlyglaucomalikelycombinedwithhighmyopiabyintegratingoctthicknessmapandstandardautomatedandpulsarperimetries AT tejungli diagnosisofearlyglaucomalikelycombinedwithhighmyopiabyintegratingoctthicknessmapandstandardautomatedandpulsarperimetries AT chinhsinliu diagnosisofearlyglaucomalikelycombinedwithhighmyopiabyintegratingoctthicknessmapandstandardautomatedandpulsarperimetries AT chungmingchen diagnosisofearlyglaucomalikelycombinedwithhighmyopiabyintegratingoctthicknessmapandstandardautomatedandpulsarperimetries |