High-speed multicontrast dynamic OCT by using deep learning

Simple item page
dc.contributor.authorLiu, Yusong
dc.contributor.authorAbd El-Sadek, Ibrahim
dc.contributor.authorMorishita, Rion
dc.contributor.authorPadungatthakij, Chettanat
dc.contributor.authorFurukawa, Atsuko
dc.contributor.authorMatsusaka, Satoshi
dc.contributor.authorYasuno, Yoshiaki
dc.date.accessioned2026-08-06T10:54:57Z
dc.date.available2026-08-06T10:54:57Z
dc.date.issued2026-03-05
dc.description.abstractWe proposed a deep learning approach to significantly accelerate multi-contrast dynamic optical coherence tomography (MC-DOCT) imaging. We trained a three-dimensional UNet with a long short-Term memory module to simultaneously generate authentic logarithmic intensity variance (aLIV) and swiftness images from only 4 OCT frames with nonuniform time intervals, instead of conventional 32 frames. This method accurately visualized multiple functional domains in in vitro samples such as breast cancer spheroids, colon cancer spheroids and alveolar organoids, which is consistent with ground truth computed from 32 OCT frames. Our method provides a promising solution for reducing MC-DOCT acquisition time from 1 minute to 6 seconds.
dc.identifier.citationProceedings of SPIE the International Society for Optical Engineering, 13850, 2026
dc.identifier.doi10.1117/12.3084922
dc.identifier.issn0277786X
dc.identifier.other2-s2.0-105039224896
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17958
dc.sourceProceedings of SPIE the International Society for Optical Engineering
dc.subjectDeep learning
dc.subjectDynamic OCT
dc.subjectTumor spheroid
dc.titleHigh-speed multicontrast dynamic OCT by using deep learning
dc.typeConference Paper

Files

Collections

Research