Title: Continuous Evaluation of Denoising Strategies in fMRI Using fMRIPrep and Nilearn


Functional magnetic resonance imaging (fMRI) signal measures changes in neuronal activity over time. The signal can be contaminated with unwanted noise, such as movement, which can impact research results. To fix this, researchers perform two steps before data analysis: standardised preprocessing and customised denoising. Scientists consult the denoising benchmark literature for guidance. However, the relevant software is ever-evolving, and benchmarks quickly become obsolete. Here, we present a denoising benchmark that can be repeatedly executed on outputs of preprocessing software fMRIPrep, and provide up-to-date guidelines when a new version comes out. Hosted by the Neurolibre reproducible preprint server, anyone can explore the results without executing the benchmark. We contributed back to Nilearn, a popular open-source project to benefit the wider research community. The data preparation components of the benchmark have served as a prototype for two user-friendly applications for large scale data preprocessing for a deep learning project on identifying transdiagnostic brain biomarkers across various neurodegenerative disorders. Overall, the efforts help the fMRI researchers keep tools up-to-date and sustainable and create machine learning ready features to further explore topics in cognitive neuroscience.


Hao-Ting Wang is interested in using big data to answer cognitive neuroscience questions, such as the neural basis of on-going thoughts and the cognitive processes related to brain health. She earned her PhD in cognitive neuroscience and neuroimaging from the University of York, UK. She is an IVADO postdoctoral fellow at CRIUGM with Prof. Pierre Bellec, where she leads a project centred around identifying transdiagnostic brain biomarkers across various neurodegenerative disorders using multiple open access datasets with deep learning. The need for a large amount of data led to her effort in data engineering for large-scale fMRI data processing. Driven by her expertise in fMRI data processing, functional connectivity, and data workflow construction, she is a core developer to Nilearn, a Python machine learning library for fMRI data, and actively contributes to other open source software. 


Date: 22nd March 2024

Time: (16:00 UTC), (17:00 WAT), (12:00 EDT), (11:00 CDT)

Meeting Link: To be sent to only registered participants


Contact Information


View recordings of previous sessions on our YouTube channel https://www.youtube.com/@COMPASS-nn5or 

Social Media






Leave a Reply

Your email address will not be published. Required fields are marked *