Saved in:
Bibliographic Details
Main Authors: Wang, Lingyun, Sahel, Jose A, Pi, Shaohua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.10128
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916246558081024
author Wang, Lingyun
Sahel, Jose A
Pi, Shaohua
author_facet Wang, Lingyun
Sahel, Jose A
Pi, Shaohua
contents Optical coherence tomography (OCT) suffers from speckle noise, causing the deterioration of image quality, especially in high-resolution modalities like visible light OCT (vis-OCT). The potential of conventional supervised deep learning denoising methods is limited by the difficulty of obtaining clean data. Here, we proposed an innovative self-supervised strategy called Sub2Full (S2F) for OCT despeckling without clean data. This approach works by acquiring two repeated B-scans, splitting the spectrum of the first repeat as a low-resolution input, and utilizing the full spectrum of the second repeat as the high-resolution target. The proposed method was validated on vis-OCT retinal images visualizing sublaminar structures in outer retina and demonstrated superior performance over conventional Noise2Noise and Noise2Void schemes. The code is available at https://github.com/PittOCT/Sub2Full-OCT-Denoising.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10128
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sub2Full: split spectrum to boost OCT despeckling without clean data
Wang, Lingyun
Sahel, Jose A
Pi, Shaohua
Image and Video Processing
Computer Vision and Pattern Recognition
Optical coherence tomography (OCT) suffers from speckle noise, causing the deterioration of image quality, especially in high-resolution modalities like visible light OCT (vis-OCT). The potential of conventional supervised deep learning denoising methods is limited by the difficulty of obtaining clean data. Here, we proposed an innovative self-supervised strategy called Sub2Full (S2F) for OCT despeckling without clean data. This approach works by acquiring two repeated B-scans, splitting the spectrum of the first repeat as a low-resolution input, and utilizing the full spectrum of the second repeat as the high-resolution target. The proposed method was validated on vis-OCT retinal images visualizing sublaminar structures in outer retina and demonstrated superior performance over conventional Noise2Noise and Noise2Void schemes. The code is available at https://github.com/PittOCT/Sub2Full-OCT-Denoising.
title Sub2Full: split spectrum to boost OCT despeckling without clean data
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.10128