WAVE-UNET: Wavelength based Image Reconstruction method using attention UNET for OCT images

TL;DR

This paper introduces WAVE-UNET, a deep learning framework that directly reconstructs high-quality OCT images from wavelength space data, bypassing complex linearization and calibration steps, and reducing noise and artifacts.

Contribution

The novel WAVE-UNET model leverages attention UNET architecture to improve OCT image reconstruction directly from wavelength data, eliminating the need for wavelength linearization and calibration.

Findings

Outperforms traditional OCT reconstruction methods in image quality.

Reduces system complexity and processing time.

Effectively suppresses speckle noise in OCT images.

Abstract

In this work, we propose to leverage a deep-learning (DL) based reconstruction framework for high quality Swept-Source Optical Coherence Tomography (SS-OCT) images, by incorporating wavelength ({\lambda}) space interferometric fringes. Generally, the SS-OCT captured fringe is linear in wavelength space and if Inverse Discrete Fourier Transform (IDFT) is applied to extract depth-resolved spectral information, the resultant images are blurred due to the broadened Point Spread Function (PSF). Thus, the recorded wavelength space fringe is to be scaled to uniform grid in wavenumber (k) space using k-linearization and calibration involving interpolations which may result in loss of information along with increased system complexity. Another challenge in OCT is the speckle noise, inherent in the low coherence interferometry-based systems. Hence, we propose a systematic design methodology WAVE-UNET to reconstruct the high-quality OCT images directly from the {\lambda}-space to reduce the complexity. The novel design paradigm surpasses the linearization procedures and uses DL to enhance the realism and quality of raw {\lambda}-space scans. This framework uses modified UNET having attention gating and residual connections, with IDFT processed {\lambda}-space fringes as the input. The method consistently outperforms the traditional OCT system by generating good-quality B-scans with highly reduced time-complexity.