Toward ground-truth optical coherence tomography via three-dimensional unsupervised deep learning processing and data

TL;DR

This paper introduces a novel unsupervised 3D deep learning method for OCT that effectively reduces speckle noise, enabling high-quality, speckle-free 3D imaging without requiring labeled data.

Contribution

The study presents a new unsupervised 3D deep learning approach for speckle noise reduction in OCT, leveraging volumetric features to improve image clarity and resolution.

Findings

Achieved high-quality speckle-free 3D OCT imaging

Outperformed previous state-of-the-art methods

Effectively revealed structures obscured by speckle noise

Abstract

Optical coherence tomography (OCT) can perform non-invasive high-resolution three-dimensional (3D) imaging and has been widely used in biomedical fields, while it is inevitably affected by coherence speckle noise which degrades OCT imaging performance and restricts its applications. Here we present a novel speckle-free OCT imaging strategy, named toward-ground-truth OCT (tGT-OCT), that utilizes unsupervised 3D deep-learning processing and leverages OCT 3D imaging features to achieve speckle-free OCT imaging. Specifically, our proposed tGT-OCT utilizes an unsupervised 3D-convolution deep-learning network trained using random 3D volumetric data to distinguish and separate speckle from real structures in 3D imaging volumetric space; moreover, tGT-OCT effectively further reduces speckle noise and reveals structures that would otherwise be obscured by speckle noise while preserving spatial resolution. Results derived from different samples demonstrated the high-quality speckle-free 3D imaging performance of tGT-OCT and its advancement beyond the previous state-of-the-art.