Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging
Journal of Personalized Medicine · 01.06.2023 · 13 (6) · 939
DOI: 10.3390/jpm13060939 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Personalized Medicine, online erschienen am 01.06.2023. Verfasst von Ching-Yu Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi 62247, Taiwan. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council of Taiwan, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation-National Chung Cheng University Joint Research Program, Ministry of Science and Technology, the Republic of China.
Abstract (Originalsprache)
The severity of diabetic retinopathy (DR) is directly correlated to changes in both the oxygen utilization rate of retinal tissue as well as the blood oxygen saturation of both arteries and veins. Therefore, the current stage of DR in a patient can be identified by analyzing the oxygen content in blood vessels through fundus images. This enables medical professionals to make accurate and prompt judgments regarding the patient’s condition. However, in order to use this method to implement supplementary medical treatment, blood vessels under fundus images need to be determined first, and arteries and veins then need to be differentiated from one another. Therefore, the entire study was split into three sections. After first removing the background from the fundus images using image processing, the blood vessels in the images were then separated from the background. Second, the method of hyperspectral imaging (HSI) was utilized in order to construct the spectral data. The HSI algorithm was utilized in order to perform analysis and simulations on the overall reflection spectrum of the retinal image. Thirdly, principal component analysis (PCA) was performed in order to both simplify the data and acquire the major principal components score plot for retinopathy in arteries and veins at all stages. In the final step, arteries and veins in the original fundus images were separated using the principal components score plots for each stage. As retinopathy progresses, the difference in reflectance between the arteries and veins gradually decreases. This results in a more difficult differentiation of PCA results in later stages, along with decreased precision and sensitivity. As a consequence of this, the precision and sensitivity of the HSI method in DR patients who are in the normal stage and those who are in the proliferative DR (PDR) stage are the highest and lowest, respectively. On the other hand, the indicator values are comparable between the background DR (BDR) and pre-proliferative DR (PPDR) stages due to the fact that both stages exhibit comparable clinical-pathological severity characteristics. The results indicate that the sensitivity values of arteries are 82.4%, 77.5%, 78.1%, and 72.9% in the normal, BDR, PPDR, and PDR, while for veins, these values are 88.5%, 85.4%, 81.4%, and 75.1% in the normal, BDR, PPDR, and PDR, respectively.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ophthalmology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi 62247, Taiwan.
- Department of Mechanical Engineering, National Chung Cheng University, Chiayi 62102, Taiwan.
- Department of Ophthalmology, Kaohsiung Armed Forces General Hospital, Kaohsiung 80284, Taiwan.
- Director of Technology Development, Hitspectra Intelligent Technology Co., Ltd., Kaohsiung 80661, Taiwan.
ORCID-Profile: Ching-Yu Wang, Arvind Mukundan, Hsiang-Chen Wang
Förderung
- National Science and Technology Council of Taiwan
- Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation-National Chung Cheng University Joint Research Program
- Ministry of Science and Technology, the Republic of China
- Kaohsiung Armed Forces General Hospital research project
Zitieren
APA
Wang, C. Y., Mukundan, A., Liu, Y. S., Tsao, Y. M., Lin, F. C., Fan, W. S., & Wang, H. C. (2023). Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging. Journal of Personalized Medicine, 13(6), 939. https://doi.org/10.3390/jpm13060939
Vancouver
Wang CY, Mukundan A, Liu YS, Tsao YM, Lin FC, Fan WS, et al. Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging. Journal of Personalized Medicine. 2023;13(6):939. doi:10.3390/jpm13060939
BibTeX
@article{Wang2023,
author = {Wang, Ching-Yu and Mukundan, Arvind and Liu, Yu-Sin and Tsao, Yu-Ming and Lin, Fen-Chi and Fan, Wen-Shuang and Wang, Hsiang-Chen},
title = {Optical Identification of Diabetic Retinopathy Using Hyperspectral Imaging},
journal = {Journal of Personalized Medicine},
year = {2023},
volume = {13},
number = {6},
pages = {939},
doi = {10.3390/jpm13060939}
}
EUVIMED