2022
DOI: 10.3390/jcm11102878
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of the Short-Term Therapeutic Effect of Anti-VEGF Therapy for Diabetic Macular Edema Using a Generative Adversarial Network with OCT Images

Abstract: Purpose: To generate and evaluate individualized post-therapeutic optical coherence tomography (OCT) images that could predict the short-term response of anti-vascular endothelial growth factor (VEGF) therapy for diabetic macular edema (DME) based on pre-therapeutic images using generative adversarial network (GAN). Methods: Real-world imaging data were collected at the Department of Ophthalmology, Qilu Hospital. A total of 561 pairs of pre-therapeutic and post-therapeutic OCT images of patients with DME were … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 11 publications
(5 citation statements)
references
References 22 publications
0
5
0
Order By: Relevance
“…[96][97][98] AI algorithms not only contribute to accurate disease diagnosis but also predict the response of patients with DME to anti-VEGF drug therapy, offering decision support for physicians to personalize treatment and increase opportunities for precision medicine. [89,99,100] Utilizing deep learning and AI, remote monitoring systems can be developed to monitor the retinal conditions of patients in real-time, potentially improving the convenience of diagnosis and treatment as well as alleviating the burden on healthcare systems. [101,102] Although the application of deep learning and AI in the field of DME provides more personalized, accurate, and convenient healthcare services for patients, the advancement of these technologies necessitates addressing a range of challenges, including model interpretability, privacy protection, clinical validation, and formulation of legal regulations.…”
Section: Emerging Research Areasmentioning
confidence: 99%
“…[96][97][98] AI algorithms not only contribute to accurate disease diagnosis but also predict the response of patients with DME to anti-VEGF drug therapy, offering decision support for physicians to personalize treatment and increase opportunities for precision medicine. [89,99,100] Utilizing deep learning and AI, remote monitoring systems can be developed to monitor the retinal conditions of patients in real-time, potentially improving the convenience of diagnosis and treatment as well as alleviating the burden on healthcare systems. [101,102] Although the application of deep learning and AI in the field of DME provides more personalized, accurate, and convenient healthcare services for patients, the advancement of these technologies necessitates addressing a range of challenges, including model interpretability, privacy protection, clinical validation, and formulation of legal regulations.…”
Section: Emerging Research Areasmentioning
confidence: 99%
“…Recently, Xu et al used GANs to create post-treatment OCT images based on baseline images. The MAE of the central macular thickness comparing the synthetic and actual images was 24.51 ± 18.56 μm [ 57 ]. While the observed difference was not negligible, this study underscores the potential of GANs for structural predictions in ophthalmology.…”
Section: Main Textmentioning
confidence: 99%
“…This ability to synthesize data can be useful for training machine learning models on datasets that are limited in size such as SANS data. For example, GANs have been used to generate synthetic OCT images for monitoring of macular edema post-therapy, with results comparable to those obtained from real data [ 100 ]. Ultimately, GANs have the potential to improve the quality and quantity of retinal images obtained during spaceflight, as well as to provide synthetic training data for machine learning models.…”
Section: Generative Adversarial Networkmentioning
confidence: 99%