Speckle-pattern-preserved denoising by deep learning for dynamic optical coherence tomography

Hsin Jou Wang, Thitiya Seesan, Shuichi Makita, Rion Morishtia, Chia Wei Sun, Yoshiaki Yasuno

Research output: Contribution to conferencePaperpeer-review

Abstract

We proposed a UNet3+ based deep-learning method to reduce the noise in optical coherent tomography (OCT) as keeping fine speckle patterns. The great capacity of noise reduction and dynamic OCT imaging with the noise reduction are demonstrated.

Original languageEnglish
StatePublished - 2024
Event2024 Conference on Lasers and Electro-Optics/Pacific Rim, CLEO-PR 2024 - Incheon, Korea, Republic of
Duration: 4 Aug 20248 Aug 2024

Conference

Conference2024 Conference on Lasers and Electro-Optics/Pacific Rim, CLEO-PR 2024
Country/TerritoryKorea, Republic of
CityIncheon
Period4/08/248/08/24

Fingerprint

Dive into the research topics of 'Speckle-pattern-preserved denoising by deep learning for dynamic optical coherence tomography'. Together they form a unique fingerprint.

Cite this