Accessing Mesoscale Functional Organization from Standard Functional MRI Leveraging AI-Based Super-Resolution
- 1Massachusetts General Hospital, Harvard Medical School
Abstract
Access to the fine-scale functional organization of the human brain is essential for understanding cognition and neurological disorders yet remains beyond the reach of conventional functional MRI (fMRI) because of its limited spatial resolution and contrast-to-noise ratio. To overcome this limitation, we developed f-LENNS (functional Localization Enhancement via Neural-Net-Sharpening), an artificial intelligence (AI)-based framework that enhances the effective spatial resolution of reconstructed fMRI magnitude images. The model was trained exclusively on high-resolution synthetic MRI data using extensive domain randomization and no adversarial or generative components. This approach enables robust out-of-the-box generalization (without retraining) to experimental datasets obtained with diverse acquisitions, while effectively curbing hallucination. Our experiments show that our publicly available model substantially improves the spatial fidelity of functional activation maps across multiple imaging paradigms and generalizes to a cohort of individuals with atypical brain function caused by amblyopia (lazy eye). F-LENNS consistently outperforms conventional resolution enhancement approaches, including interpolation-based upsampling and sharpening methods. These findings demonstrate that AI-driven super-resolution combined with domain randomization can overcome domain shifts arising from differences in MRI acquisition, enabling scalable, fine-scale functional brain mapping with widely available MRI hardware.
Related
- Meso2EM: a cross-scale CLEM workflow linking mesoscale functional imaging to targeted electron microscopy
- Leveraging state-of-the-art AI structure predictors to generate atomic resolution ensembles of intrinsically disordered proteins
- SABER: a multiparental tomato population leveraging wild relative diversity for high-resolution QTL mapping
- Mesoscale functional architecture in medial posterior parietal cortex
- Mesoscale Functional Reorganization of Cortical Networks After Cortical Spreading Depression
BibTeX
@misc{nasr2026accessing,
title = {{Accessing Mesoscale Functional Organization from Standard Functional MRI Leveraging AI-Based Super-Resolution}},
author = {S. Nasr and H. B. Li and D. Zemlyanker and L. Huber and M. S. Rosen and J. E. Iglesias},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.07.765069},
url = {https://www.biorxiv.org/content/10.64898/2026.11.07.765069v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Accessing Mesoscale Functional Organization from Standard Functional MRI Leveraging AI-Based Super-Resolution
AU - S. Nasr
AU - H. B. Li
AU - D. Zemlyanker
AU - L. Huber
AU - M. S. Rosen
AU - J. E. Iglesias
PY - 2026
DA - 2026/11/07
PB - bioRxiv
DO - 10.64898/2026.11.07.765069
UR - https://www.biorxiv.org/content/10.64898/2026.11.07.765069v1
AB - Access to the fine-scale functional organization of the human brain is essential for understanding cognition and neurological disorders yet remains beyond the reach of conventional functional MRI (fMRI) because of its limited spatial resolution and contrast-to-noise ratio. To overcome this limitation, we developed f-LENNS (functional Localization Enhancement via Neural-Net-Sharpening), an artificial intelligence (AI)-based framework that enhances the effective spatial resolution of reconstructed fMRI magnitude images. The model was trained exclusively on high-resolution synthetic MRI data using extensive domain randomization and no adversarial or generative components. This approach enables robust out-of-the-box generalization (without retraining) to experimental datasets obtained with diverse acquisitions, while effectively curbing hallucination. Our experiments show that our publicly available model substantially improves the spatial fidelity of functional activation maps across multiple imaging paradigms and generalizes to a cohort of individuals with atypical brain function caused by amblyopia (lazy eye). F-LENNS consistently outperforms conventional resolution enhancement approaches, including interpolation-based upsampling and sharpening methods. These findings demonstrate that AI-driven super-resolution combined with domain randomization can overcome domain shifts arising from differences in MRI acquisition, enabling scalable, fine-scale functional brain mapping with widely available MRI hardware.
ER -