A fetal fMRI specific motion correction algorithm using 2nd order edge features

Dustin Scheinost, John A. Onofrey, Soo H. Kwon, Sarah Cross, Gordon Sze, Laura R. Ment, Xenophon Papademetris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

We present a novel motion correction algorithm designed specifically for fetal functional magnetic imaging resonance (fMRI). Fetal motion is a main limiting factor of fetal fMRI and standard algorithm cannot correct for fetal motion. The goals in designing the algorithm were: (i) the ability to correct for both large and small motion, (ii) the preferential weighting of fetal tissue, (iii) the development of a framework robust to artifacts, and (iv) the automatic censoring of low quality frames. The key feature of the algorithm is the use of 2nd order edge features instead of raw intensity or 1st order edge features. We demonstrate that our algorithm significantly out performs competing approaches.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages1288-1292
Number of pages5
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Externally publishedYes
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2018-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Keywords

  • Fetal fMRI
  • Hessian
  • Motion Correction

Fingerprint Dive into the research topics of 'A fetal fMRI specific motion correction algorithm using 2<sup>nd</sup> order edge features'. Together they form a unique fingerprint.

Cite this