Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage
A methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/9/6/1613 |
| _version_ | 1797566972144123904 |
|---|---|
| author | Hsin-Yu Yao Kuang-Wen Tseng Hong-Thai Nguyen Chie-Tong Kuo Hsiang-Chen Wang |
| author_facet | Hsin-Yu Yao Kuang-Wen Tseng Hong-Thai Nguyen Chie-Tong Kuo Hsiang-Chen Wang |
| author_sort | Hsin-Yu Yao |
| collection | DOAJ |
| description | A methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the average simulated spectra are categorized by using a principal component analysis (PCA) score plot. Third, Beer-Lambert law is applied to calculate vessel oxygen saturation in the ophthalmoscope images, and oxygenation maps are obtained. The average reflectance spectra and PCA results indicate that average reflectance changes with the deterioration of DR. The G-channel gradually decreases because of vascular disease, whereas the R-channel gradually increases with oxygen saturation in the vessels. As DR deteriorates, the oxygen utilization of retinal tissues gradually decreases, and thus oxygen saturation in the veins gradually increases. The sensitivity of diagnosis is based on the severity of retinopathy due to diabetes. Normal, background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR) are arranged in order of 90.00%, 81.13%, 87.75%, and 93.75%, respectively; the accuracy is 90%, 86%, 86%, 90%, respectively. The F1-scores are 90% (Normal), 83.49% (BDR), 86.86% (PPDR), and 91.83% (PDR), and the accuracy rates are 95%, 91.5%, 93.5%, and 96%, respectively. |
| first_indexed | 2024-03-10T19:35:02Z |
| format | Article |
| id | doaj.art-c0d443382bb64310a39cc7e7c21c90d9 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T19:35:02Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-c0d443382bb64310a39cc7e7c21c90d92023-11-20T01:48:15ZengMDPI AGJournal of Clinical Medicine2077-03832020-05-0196161310.3390/jcm9061613Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy StageHsin-Yu Yao0Kuang-Wen Tseng1Hong-Thai Nguyen2Chie-Tong Kuo3Hsiang-Chen Wang4Department of Ophthalmology, Kaohsiung Armed Forced General Hospital, Kaohsiung City 80284, TaiwanDepartment of Medicine, Mackay Medical College, 46, Sec. 3, Zhongzheng Rd., Sanzhi Dist., New Taipei 25245, TaiwanDepartment of Mechanical Engineering and Center for Innovative Research on Aging Society (CIRAS), National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, TaiwanDepartment of Optometry and Innovation Incubation Center, Shu-Zen Junior College of Medicine and Management, Kaohsiung 821, TaiwanDepartment of Mechanical Engineering and Center for Innovative Research on Aging Society (CIRAS), National Chung Cheng University, 168, University Rd., Min Hsiung, Chia Yi 62102, TaiwanA methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the average simulated spectra are categorized by using a principal component analysis (PCA) score plot. Third, Beer-Lambert law is applied to calculate vessel oxygen saturation in the ophthalmoscope images, and oxygenation maps are obtained. The average reflectance spectra and PCA results indicate that average reflectance changes with the deterioration of DR. The G-channel gradually decreases because of vascular disease, whereas the R-channel gradually increases with oxygen saturation in the vessels. As DR deteriorates, the oxygen utilization of retinal tissues gradually decreases, and thus oxygen saturation in the veins gradually increases. The sensitivity of diagnosis is based on the severity of retinopathy due to diabetes. Normal, background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR) are arranged in order of 90.00%, 81.13%, 87.75%, and 93.75%, respectively; the accuracy is 90%, 86%, 86%, 90%, respectively. The F1-scores are 90% (Normal), 83.49% (BDR), 86.86% (PPDR), and 91.83% (PDR), and the accuracy rates are 95%, 91.5%, 93.5%, and 96%, respectively.https://www.mdpi.com/2077-0383/9/6/1613diabetic retinopathy stagehyperspectral imagingophthalmoscopefluorescein angiographyoptical coherence tomography |
| spellingShingle | Hsin-Yu Yao Kuang-Wen Tseng Hong-Thai Nguyen Chie-Tong Kuo Hsiang-Chen Wang Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage Journal of Clinical Medicine diabetic retinopathy stage hyperspectral imaging ophthalmoscope fluorescein angiography optical coherence tomography |
| title | Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage |
| title_full | Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage |
| title_fullStr | Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage |
| title_full_unstemmed | Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage |
| title_short | Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage |
| title_sort | hyperspectral ophthalmoscope images for the diagnosis of diabetic retinopathy stage |
| topic | diabetic retinopathy stage hyperspectral imaging ophthalmoscope fluorescein angiography optical coherence tomography |
| url | https://www.mdpi.com/2077-0383/9/6/1613 |
| work_keys_str_mv | AT hsinyuyao hyperspectralophthalmoscopeimagesforthediagnosisofdiabeticretinopathystage AT kuangwentseng hyperspectralophthalmoscopeimagesforthediagnosisofdiabeticretinopathystage AT hongthainguyen hyperspectralophthalmoscopeimagesforthediagnosisofdiabeticretinopathystage AT chietongkuo hyperspectralophthalmoscopeimagesforthediagnosisofdiabeticretinopathystage AT hsiangchenwang hyperspectralophthalmoscopeimagesforthediagnosisofdiabeticretinopathystage |