DBSN:Self-supervised Denoising for OCT Images via Dual Blind Strategy and Blind-Spot Network

Chenkun Ge, Xiaojun Yu, Mingshuai Li, Miaoyuan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Blind-spot network and its variants have shown promising results in self-supervised denoising tasks. The aim of these methods is to conceal pixels of noisy image and use self-supervised learning to recover them. However, for OCT(optical coherence tomography) images, which have strong auto-correlation between pixels, more effective mask strategies and denoising optimization techniques are needed to improve these methods. To address this issue, this paper proposes a dual mask strategy and blind-spot network (DBSN). Firstly, a fast global mask mapper is designed to break the correlation between pixels in an OCT image. A conditional mask convolution block with centrally masked convolution is embedded inside the blind-spot network. Images after being fed through the global mask mapper and pixel shuffle are then fed into the blind-spot network according to corresponding conditions to achieve two different blind-spot recoveries. Meanwhile, the lower bound of proposed loss function in the case of convergence is discussed, and changes in the weight of the loss function are adapted during training. Finally, a denoising refinement module is used to improve the denoising effect during the inference stage. Numerous experiments demonstrate that DBSN, as a self-supervised denoising approach, outperforms existing methods on OCT data.

Original languageEnglish
Title of host publicationICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages455-460
Number of pages6
ISBN (Electronic)9798350314014
DOIs
StatePublished - 2023
Event2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023 - Hybrid, Xi'an, China
Duration: 17 Aug 202320 Aug 2023

Publication series

NameICICN 2023 - 2023 IEEE 11th International Conference on Information, Communication and Networks

Conference

Conference2023 IEEE 11th International Conference on Information, Communication and Networks, ICICN 2023
Country/TerritoryChina
CityHybrid, Xi'an
Period17/08/2320/08/23

Keywords

  • blind-spot network
  • denoising
  • optical coherence tomography
  • self-supervised learning

Fingerprint

Dive into the research topics of 'DBSN:Self-supervised Denoising for OCT Images via Dual Blind Strategy and Blind-Spot Network'. Together they form a unique fingerprint.

Cite this