Prediction of OCT images of short-term response to anti-VEGF treatment for diabetic macular edema using different generative adversarial networks

Liu, Shaopeng; Hu, Wanlu; Xu, Fabao; Chen, Wenjie; Liu, Jie; Yu, Xuechen; Wang, Zhengfei; Li, Zhongwen; Li, Zhiwen; Yang, Xueying; Song, Boxuan; Wang, Shaopeng; Wang, Kai; Wang, Xinpeng; Hong, Jiaming; Zhang, Li; Li, Jianqiao

doi:10.1016/j.pdpdt.2023.103272

Cited by 7 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of the GAN models used in this study, RegGAN showed the best performance in predicting residual fluid. This result is in accordance with a previous study by Lui et al 15 We hypothesize that this is due to the more refined structure of the RegGAN model compared to the others. RegGAN has been updated from CycleGAN so that the generator is trained with an additional registration network to fit the misaligned noise distribution adaptively.…”

Section: Discussionsupporting

confidence: 93%

“…Lui et al compared the performances of several GAN models for the prediction of OCT appearance 1-month after an uncontrolled anti-VEGF treatment. 15 They reported that 92% of the images were difficult to differentiate from the real OCT images by retinal specialists, which was similar in the present study.…”

Section: Discussionsupporting

confidence: 88%

“…An MAE of 26.74 ± 21.28 µm compared to the real image (327.67 ± 209.11 µm, 8.16% difference) was observed for central macular thickness (CMT) in the study by Liu et al 15 It is unclear how they measured CMT in that study. As the present study utilized one central B-scan from the volume scan, the retinal area was calculated instead of the central subfield macular thickness.…”

Section: Discussionmentioning

confidence: 91%

See 2 more Smart Citations

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network

Baek,

He,

Emamverdi

et al. 2024

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 93%

Section: Discussionsupporting

confidence: 88%

Section: Discussionmentioning

confidence: 91%

See 1 more Smart Citation

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network

Baek,

He,

Emamverdi

et al. 2024

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

“…You et al [32] conducted a survey analyzing the use of GANs in ophthalmology, covering a range of tasks and identifying key challenges. Shaopeng Liu et al [33] assessed six GAN models for predicting diabetic macular edema response to anti-VEGF therapy with OCT images, identifying RegGAN as the most precise in replicating post-treatment results. Furthermore, Xiaojun Yu et al [34] developed MDR-GAN, a generative adversarial network incorporating multi-scale and dilated convolution res-network for OCT retinal image despeckling, demonstrating superior denoising performance compared to existing methods.…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning and Interpretable Analysis-Based Quality Assessment of Synthetic Optical Coherence Tomography Images by CGAN Model for Retinal Diseases

Han,

Yu,

2024

Processes

View full text Add to dashboard Cite

This study investigates the effectiveness of using conditional generative adversarial networks (CGAN) to synthesize Optical Coherence Tomography (OCT) images for medical diagnosis. Specifically, the CGAN model is trained to generate images representing various eye conditions, including normal retina, vitreous warts (DRUSEN), choroidal neovascularization (CNV), and diabetic macular edema (DME), creating a dataset of 102,400 synthetic images per condition. The quality of these images is evaluated using two methods. First, 18 transfer-learning neural networks (including AlexNet, VGGNet16, GoogleNet) assess image quality through model-scoring metrics, resulting in an accuracy rate of 97.4% to 99.9% and an F1 Score of 95.3% to 100% across conditions. Second, interpretative analysis techniques (GRAD-CAM, occlusion sensitivity, LIME) compare the decision score distribution of real and synthetic images, further validating the CGAN network’s performance. The results indicate that CGAN-generated OCT images closely resemble real images and could significantly contribute to medical datasets.

show abstract

Generative deep learning for the development of a type 1 diabetes simulator

Mujahid,

Contreras,

Beneyto

et al. 2024

Commun Med

View full text Add to dashboard Cite

Background Type 1 diabetes (T1D) simulators, crucial for advancing diabetes treatments, often fall short of capturing the entire complexity of the glucose-insulin system due to the imprecise approximation of the physiological models. This study introduces a simulation approach employing a conditional deep generative model. The aim is to overcome the limitations of existing T1D simulators by synthesizing virtual patients that more accurately represent the entire glucose-insulin system physiology. Methods Our methodology utilizes a sequence-to-sequence generative adversarial network to simulate virtual T1D patients causally. Causality is embedded in the model by introducing shifted input-output pairs during training, with a 90-min shift capturing the impact of input insulin and carbohydrates on blood glucose. To validate our approach, we train and evaluate the model using three distinct datasets, each consisting of 27, 12, and 10 T1D patients, respectively. In addition, we subject the trained model to further validation for closed-loop therapy, employing a state-of-the-art controller. Results The generated patients display statistical similarity to real patients when evaluated on the time-in-range results for each of the standard blood glucose ranges in T1D management along with means and variability outcomes. When tested for causality, authentic causal links are identified between the insulin, carbohydrates, and blood glucose levels of the virtual patients. The trained generative model demonstrates behaviours that are closer to reality compared to conventional T1D simulators when subjected to closed-loop insulin therapy using a state-of-the-art controller. Conclusions These results highlight our approach’s capability to accurately capture physiological dynamics and establish genuine causal relationships, holding promise for enhancing the development and evaluation of therapies in diabetes.

show abstract

Prediction of OCT images of short-term response to anti-VEGF treatment for diabetic macular edema using different generative adversarial networks

Cited by 7 publications

References 25 publications

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network

Prediction of Long-Term Treatment Outcomes for Diabetic Macular Edema Using a Generative Adversarial Network

Transfer Learning and Interpretable Analysis-Based Quality Assessment of Synthetic Optical Coherence Tomography Images by CGAN Model for Retinal Diseases

Generative deep learning for the development of a type 1 diabetes simulator

Contact Info

Product

Resources

About