TY - JOUR
T1 - Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network
AU - Li, Xueshen
AU - Dong, Zhenxing
AU - Liu, Hongshan
AU - Kang-Mieler, Jennifer J.
AU - Ling, Yuye
AU - Gan, Yu
N1 - Publisher Copyright:
© 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.
PY - 2023/10/1
Y1 - 2023/10/1
N2 - Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregards frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.
AB - Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregards frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.
UR - http://www.scopus.com/inward/record.url?scp=85174337981&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174337981&partnerID=8YFLogxK
U2 - 10.1364/BOE.494557
DO - 10.1364/BOE.494557
M3 - Article
AN - SCOPUS:85174337981
VL - 14
SP - 5148
EP - 5161
JO - Biomedical Optics Express
JF - Biomedical Optics Express
IS - 10
ER -