Generative AI for rapid diffusion MRI with improved image quality, reliability, and generalizability
Imaging Neuroscience · 13.06.2024 · 2
DOI: 10.1162/imag_a_00193 ↗Kurz gefasst
Fachartikel in der Zeitschrift Imaging Neuroscience, online erschienen am 13.06.2024. Verfasst von Amir Sadikov und 4 weiteren Autor:innen. Beteiligte Einrichtung: Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We use generative AI to enable rapid diffusion MRI (dMRI) with high fidelity, reproducibility, and generalizability across clinical and research settings. We employ a Swin UNEt Transformers (SWIN) model, trained on Human Connectome Project (HCP) data (n = 1021) and conditioned on registered T1 scans, to perform generalized dMRI denoising. We also qualitatively demonstrate super-resolution with artificially downsampled HCP data. Remarkably, SWIN can be fine-tuned for an out-of-domain dataset with a single example scan, as we demonstrate on dMRI of children with neurodevelopmental disorders (n = 40), adults with acute traumatic brain injury (n = 40), and adolescents with intracerebral hemorrhage due to vascular malformations undergoing resection (n = 8), each cohort scanned on different scanner models with different imaging protocols at different sites. This robustness to scan acquisition parameters, patient populations, scanner types, and sites eliminates the advantages of self-supervised methods over our fully supervised generative AI approach. We exceed current state-of-the-art denoising methods in accuracy and test–retest reliability of rapid diffusion tensor imaging (DTI) requiring only 90 seconds of scan time. SWIN denoising also achieves dramatic improvements over the state-of-the-art for test–retest reliability of intracellular volume fraction and free water fraction measurements and can remove heavy-tail noise, improving biophysical modeling fidelity. SWIN enables rapid diffusion MRI with unprecedented accuracy and reliability, especially at high diffusion weighting for probing biological tissues at microscopic spatial scales. The code and model are publicly available at https://github.com/ucsfncl/dmri-swin.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States.
- Graduate Group in Bioengineering, University of California, San Francisco, CA, United States.
- University of California, Berkeley, CA, United States.
Zitieren
APA
Sadikov, A., Pan, X., Choi, H., Cai, L. T., & Mukherjee, P. (2024). Generative AI for rapid diffusion MRI with improved image quality, reliability, and generalizability. Imaging Neuroscience, 2. https://doi.org/10.1162/imag_a_00193
Vancouver
Sadikov A, Pan X, Choi H, Cai LT, Mukherjee P. Generative AI for rapid diffusion MRI with improved image quality, reliability, and generalizability. Imaging Neuroscience. 2024;2. doi:10.1162/imag_a_00193
BibTeX
@article{Sadikov2024,
author = {Sadikov, Amir and Pan, Xinlei and Choi, Hannah and Cai, Lanya T and Mukherjee, Pratik},
title = {Generative AI for rapid diffusion MRI with improved image quality, reliability, and generalizability},
journal = {Imaging Neuroscience},
year = {2024},
volume = {2},
doi = {10.1162/imag_a_00193}
}
EUVIMED