TY - JOUR
T1 - Employing texture loss to denoise OCT images using generative adversarial networks
AU - Mehdizadeh, Maryam
AU - Saha, Sajib
AU - Alonso-Caneiro, David
AU - Kugelman, Jason
AU - Macnish, Cara
AU - Chen, Fred
N1 - Publisher Copyright:
© 2024 Optica Publishing Group (formerly OSA). All rights reserved.
PY - 2024/4/1
Y1 - 2024/4/1
N2 - OCT is a widely used clinical ophthalmic imaging technique, but the presence of speckle noise can obscure important pathological features and hinder accurate segmentation. This paper presents a novel method for denoising optical coherence tomography (OCT) images using a combination of texture loss and generative adversarial networks (GANs). Previous approaches have integrated deep learning techniques, starting with denoising Convolutional Neural Networks (CNNs) that employed pixel-wise losses. While effective in reducing noise, these methods often introduced a blurring effect in the denoised OCT images. To address this, perceptual losses were introduced, improving denoising performance and overall image quality. Building on these advancements, our research focuses on designing an image reconstruction GAN that generates OCT images with textural similarity to the gold standard, the averaged OCT image. We utilize the PatchGAN discriminator approach as a texture loss to enhance the quality of the reconstructed OCT images. We also compare the performance of UNet and ResNet as generators in the conditional GAN (cGAN) setting, as well as compare PatchGAN with the Wasserstein GAN. Using real clinical foveal-centered OCT retinal scans of children with normal vision, our experiments demonstrate that the combination of PatchGAN and UNet achieves superior performance (PSNR = 32.50) compared to recently proposed methods such as SiameseGAN (PSNR = 31.02). Qualitative experiments involving six masked clinical ophthalmologists also favor the reconstructed OCT images with PatchGAN texture loss. In summary, this paper introduces a novel method for denoising OCT images by incorporating texture loss within a GAN framework. The proposed approach outperforms existing methods and is well-received by clinical experts, offering promising advancements in OCT image reconstruction and facilitating accurate clinical interpretation. We thank Dr Jason Charng, Dr Rachael Heath Jeffery, Dr Danial Roshandel, and Dr Mary Safwat Aziz Attia as the expert image graders for taking part in the qualitative experiments and their helpful discussions. The authors express their gratitude to Professor Scott Read for granting access to the dataset.
AB - OCT is a widely used clinical ophthalmic imaging technique, but the presence of speckle noise can obscure important pathological features and hinder accurate segmentation. This paper presents a novel method for denoising optical coherence tomography (OCT) images using a combination of texture loss and generative adversarial networks (GANs). Previous approaches have integrated deep learning techniques, starting with denoising Convolutional Neural Networks (CNNs) that employed pixel-wise losses. While effective in reducing noise, these methods often introduced a blurring effect in the denoised OCT images. To address this, perceptual losses were introduced, improving denoising performance and overall image quality. Building on these advancements, our research focuses on designing an image reconstruction GAN that generates OCT images with textural similarity to the gold standard, the averaged OCT image. We utilize the PatchGAN discriminator approach as a texture loss to enhance the quality of the reconstructed OCT images. We also compare the performance of UNet and ResNet as generators in the conditional GAN (cGAN) setting, as well as compare PatchGAN with the Wasserstein GAN. Using real clinical foveal-centered OCT retinal scans of children with normal vision, our experiments demonstrate that the combination of PatchGAN and UNet achieves superior performance (PSNR = 32.50) compared to recently proposed methods such as SiameseGAN (PSNR = 31.02). Qualitative experiments involving six masked clinical ophthalmologists also favor the reconstructed OCT images with PatchGAN texture loss. In summary, this paper introduces a novel method for denoising OCT images by incorporating texture loss within a GAN framework. The proposed approach outperforms existing methods and is well-received by clinical experts, offering promising advancements in OCT image reconstruction and facilitating accurate clinical interpretation. We thank Dr Jason Charng, Dr Rachael Heath Jeffery, Dr Danial Roshandel, and Dr Mary Safwat Aziz Attia as the expert image graders for taking part in the qualitative experiments and their helpful discussions. The authors express their gratitude to Professor Scott Read for granting access to the dataset.
UR - http://www.scopus.com/inward/record.url?scp=85189432405&partnerID=8YFLogxK
U2 - 10.1364/BOE.503868
DO - 10.1364/BOE.503868
M3 - Article
C2 - 38633090
AN - SCOPUS:85189432405
SN - 2156-7085
VL - 15
SP - 2262
EP - 2280
JO - Biomedical Optics Express
JF - Biomedical Optics Express
IS - 4
ER -