GenVFNet: Generating Visual Field From Optical Coherence Tomography Angiography by Conditional Generative Adversarial Networks

GenVFNet: Generating Visual Field From Optical Coherence Tomography Angiography by Conditional Generative Adversarial Networks

Glaucoma investigations play an important role in glaucoma management. This study aimed to generate a visual field pattern deviation map (GenVF) from optical coherence tomography angiography (OCTA) using conditional generative adversarial networks (cGAN), namely GenVFNet. cGAN consisted of two compo...

Full description

Saved in:
Bibliographic Details
Main Authors: Anita Manassakorn, Supatana Auethavekiat, Vera Sa-Ing, Sunee Chansangpetch, Kitiya Ratanawongphaibul, Nopphawan Uramphorn, Visanee Tantisevi
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Artificial intelligence
conditional generative adversarial network
deep learning
glaucoma
optical coherence tomography angiography
visual field
Online Access:https://ieeexplore.ieee.org/document/10684695/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Glaucoma investigations play an important role in glaucoma management. This study aimed to generate a visual field pattern deviation map (GenVF) from optical coherence tomography angiography (OCTA) using conditional generative adversarial networks (cGAN), namely GenVFNet. cGAN consisted of two components: generator and discriminator. The generator consisted of encoder and decoder blocks and the discriminator was the classification learner. The training data was Grad-CAM of OCTA (GradOCTA) of glaucomatous eyes. Only eyes with a visual field (VF) compatible with optic disc photograph (DP) and/or optical coherence tomography (OCT) were used. 100 eyes (90.9%) were used for training and the remaining 10 eyes (9.1%) for testing. To conform with the five severity levels in clinical diagnosis, we quantized the generated VF (GenRawVF) from GenVFNet into five levels and named the quantized image GenVF. In the experiment, GenRawVFs were compared with actual pattern deviation images (RealRawVF) using the structural similarity index measure (SSIM), normalized root mean square error (NRMSE), Fr&#x00E9;chet inception distance (FID), and confusion matrix. The average <inline-formula> <tex-math notation="LaTeX">$\times 95$ </tex-math></inline-formula>%CI SSIM, NRMSE, and FID were <inline-formula> <tex-math notation="LaTeX">$0.87\times 0.02$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$0.10\times 0.6$ </tex-math></inline-formula>, and <inline-formula> <tex-math notation="LaTeX">$7.54\times 3.47$ </tex-math></inline-formula>, respectively. GenVFNet was able to construct GenVF, especially in the superior hemifield. In addition, GenVFNet was tested with VFs of eyes whose DP and/or OCT did not correlate with the available VF. According to the expert&#x2019;s opinion, 81 eyes (65.8%) of GenVF were correlated with DP and/or OCT. This study demonstrated the potential of GenVFNet to construct a VF pattern deviation from the OCTA that would be a benefit for patients who cannot perform a reliable VF.
ISSN:2169-3536

Similar Items