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 language||English (US)|
|Title of host publication||2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|State||Published - May 23 2018|
|Event||15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States|
Duration: Apr 4 2018 → Apr 7 2018
|Name||Proceedings - International Symposium on Biomedical Imaging|
|Other||15th IEEE International Symposium on Biomedical Imaging, ISBI 2018|
|Period||4/4/18 → 4/7/18|
Bibliographical notePublisher Copyright:
© 2018 IEEE.
- Fetal fMRI
- Motion Correction