Motion-Informed 3D Deep Learning Reconstruction in Patients with Cognitive Impairment
Motion-informed DL reconstruction improved both morphometric accuracy and perceived image quality on 3D T1-weighted brain MRI. This technique may enhance diagnostic utility and reduce scan failure rates in motion-prone patients with cognitive impairment.
Authors
- Nelson Gil (ORCID: https://orcid.org/0000-0002-0771-2292)
- Shohei Fujita (ORCID: https://orcid.org/0000-0003-4276-6226)
- Daniel Polak (ORCID: https://orcid.org/0000-0001-9781-1528)
- Wei‐Ching Lo (ORCID: https://orcid.org/0000-0002-1893-0500)
- Bryan Clifford (ORCID: https://orcid.org/0000-0002-1966-0581)
- Stephen Cauley (ORCID: https://orcid.org/0000-0002-6147-6016)
- Daniel Nicolas Splitthoff (ORCID: https://orcid.org/0000-0003-4032-9516)
- Chen-Hua Chiang
- Susie Y. Huang (ORCID: https://orcid.org/0000-0003-2950-7254)
- Sittaya Buathong (ORCID: https://orcid.org/0009-0007-5467-7825)
- John Conklin
- Dominik Nickel (ORCID: https://orcid.org/0000-0002-0360-7233)
- Yantu Huang
Institutions
- Siemens (Germany) (DE)
- Harvard University (US)
- Harvard–MIT Division of Health Sciences and Technology (US)
- Medical Solutions (GB)
- Athinoula A. Martinos Center for Biomedical Imaging (US)
- Siemens Healthcare (United States) (US)
- Taipei Medical University-Shuang Ho Hospital (TW)
- Resonance Research (United States) (US)
- Taipei Medical University (TW)
Publication Details
- Journal
- American Journal of Neuroradiology
- Published
- 2025-10-08
- DOI
- https://doi.org/10.3174/ajnr.a8977
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00