A Comparative Study between Image- and Projection-Domain Self-Supervised Learning for Ultra Low-Dose CBCT

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

3 Scopus citations

Abstract

We compare image domain and projection domain denoising approaches with self-supervised learning for ultra low-dose cone-beam CT (CBCT), where number of detected x-ray photons is significantly low. For image-domain self-supervised denoising, we first reconstruct CBCT images with the standard filtered backprojection. For model training, we use blind-spot filtering to partially blind images and recover the blind spots. For projection-domain self-supervised denoising, we regard the post-log projections as training examples of convolutional neural network. From experimental results with various low-dose CBCT settings, the projection-domain denoiser outperforms the image-domain denoiser both in image quality and accuracy for ultra low-dose CBCT.

Original languageEnglish
Title of host publication44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2076-2079
Number of pages4
ISBN (Electronic)9781728127828
DOIs
StatePublished - 2022
Event44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 - Glasgow, United Kingdom
Duration: 11 Jul 202215 Jul 2022

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume2022-July
ISSN (Print)1557-170X

Conference

Conference44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Country/TerritoryUnited Kingdom
CityGlasgow
Period11/07/2215/07/22

Fingerprint

Dive into the research topics of 'A Comparative Study between Image- and Projection-Domain Self-Supervised Learning for Ultra Low-Dose CBCT'. Together they form a unique fingerprint.

Cite this