Largest fNIRS dataset collection with brain channel positions shared
Towards fNIRS foundation models: A curated corpus of 67 public datasets with channel positions in MNI space
Human-Computer Interaction
Summary
Functional near-infrared spectroscopy (fNIRS) measures brain activity but hasn’t had big, consistent datasets like other brain imaging methods. The authors gathered 67 public fNIRS datasets from nearly 2,800 people, combined into one large collection with standardized brain channel locations. This helps researchers and engineers use the data together more easily and could speed up developing better brain-monitoring tools. They also provide software to load and preprocess the data automatically.
What this means in practice
- •For medical ai engineers: Build and train foundation models for brain signal analysis using large pooled fNIRS data with standardized channel positions.
- •For brain-computer interface developers: Access consistent and large-scale fNIRS data to improve device algorithms handling varied sensor setups and individuals.
Authors
Santiago Posso-Murillo
Abstract
Brain foundation models have transformed medical artificial intelligence and computational neuroscience by reducing the reliance on task-specific data through large-scale pretraining. While they have been successful with non-invasive neuroimaging data, their adoption in functional near-infrared spectroscopy (fNIRS) has lagged due to the limited size and heterogeneity of public datasets, which are collected under varying protocols, devices, and sensor configurations. In addition, no single fNIRS dataset is comparable in size to the largest datasets in functional magnetic resonance imaging (fMRI), electroencephalography (EEG), or magnetoencephalography (MEG). The fNIRS datasets are also spread across different platforms and often have insufficient information, or lack the protocols that would make them easier to use. Given the advances in EEG foundation models that enable flexible modeling across diverse EEG montages, we curated 1,955 hours of fNIRS data from 67 public datasets spanning 2,798 participants, representing the largest fNIRS curation effort to date. The curated data include oxygenated (HbO) and deoxygenated (HbR) hemoglobin signals along with the three-dimensional position of every channel in the standard space of the Montreal Neurological Institute (MNI), which makes positions comparable across datasets. We release dataloaders that handle each dataset automatically, along with the minimal preprocessing pipeline used to prepare the data, at https://github.com/sposso/fnirs-datasets. This work aims to facilitate the future development of foundation models for fNIRS.