Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network

TL;DR

This paper introduces a frequency-aware super-resolution method for OCT images using a cGAN, improving detail reconstruction by addressing frequency bias and demonstrating superior performance across various medical imaging datasets.

Contribution

It proposes a novel frequency-aware framework with specialized modules and loss function, enhancing OCT image super-resolution beyond existing spatial-only methods.

Findings

Outperforms existing deep learning super-resolution methods on OCT data

Demonstrates generalizability to fish corneal and rat retinal images

Effectively super-resolves morphological details in eye imaging

Abstract

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 disregard 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.