Search results for #fMRIPrep
DeepPrep can complete both s/fMRI preprocessing within 40 mins for a single scan and low to 8.5 mins/scan in a batch setup, over 10-fold faster than #fMRIPrep. Outputs of DeepPrep are similar or superior to those of fMRIPrep.
Recently, more and more #deeplearning models have been developed to accelerate individual steps of the preprocessing process. Yet, there's still lacking an end2end pipeline that integrates these modules in a manner similar to #fMRIPrep. Thus, the birth of DeepPrep is timely.
🚀Excited to share our #preprint on DeepPrep: a high-speed, scalable preprocessing pipeline for s/fMRI, empowered by SOTA #deeplearning algorithms. What takes #fMRIPrep 7 hrs, DeepPrep achieves in just 40 mins! Dive into the details🧵 @hesheng3 @sattertt shorturl.at/eBEP8
5. Tidy up "junk" files Energy is needed to store and backup data. you can reduce your footprint by deleting files you don't need. For #fMRIPrep, junk files make up to 96% of total size. Our tool fMRIPrepCleanup, automatically finds/removes this data: github.com/NickESouter/fM…
3. Preprocess conservatively Reduce compute required for your research by only performing preprocessing steps that are necessary. In our recent study, we provide tips on how to minimise emissions from #fMRIPrep while still getting good quality data: osf.io/preprints/osf/…
@HaoTingW713 on developing de-noising toolbox with #fmriprep in @nilearn depends critically on @BIDSstandard and open tool developers in reducing burden of preparing and sharing #opendata. Supporting these roles is crucial cornerstone of #openscience ecosystems @TheNeuro_MNI
Perfecting #fMRIPrep 🙌
Attending @russpoldrack's live talk! Looking forward to gaining insights from the #fmri preprocessing pipeline #fmriPrep, applying some ideas with our @EegManyPipes project, especially exploring the "glass box" visualization! #OHBMBrainhack #workflows
Attending @russpoldrack's live talk! Looking forward to gaining insights from the #fmri preprocessing pipeline #fmriPrep, applying some ideas with our @EegManyPipes project, especially exploring the "glass box" visualization! #OHBMBrainhack #workflows https://t.co/GdqtHfBwXD
We apply this reproducible benchmark to investigate the robustness of the conclusions across two @OpenNeuroOrg datasets and two LTS versions of #fMRIPrep. 5/8
We love #fmriprep, but the confound documentation is a bit long and difficult to navigate. It’s not a trivial job to get the right regressors implemented in the benchmarks done on non-fMRIPrep workflow. 2/8
Our work “A reproducible benchmark of resting-state #fMRI denoising strategies using #fMRIPrep and @nilearn” is now officially on the reproducible preprint service @NeuroLibre and @biorxiv_neursci 🎉 neurolibre.org/papers/10.5545… 1/8
Anyone collecting #multiecho #MRI data (including phase reversed images) and using #fMRIPrep? How are you setting up the AP/PA pairs in distortion correction? @OHBM_Trainees
#DeepMReye now has a wrapper for #BIDS data! pypi.org/project/bidsmr… This is great for example to decode gaze position in #fMRI datasets processed with #fMRIprep Thank you @RemiGau for this amazing contribution to our package! w/@CYHSM
#DeepMReye now has a wrapper for #BIDS data! pypi.org/project/bidsmr… This is great for example to decode gaze position in #fMRI datasets processed with #fMRIprep Thank you @RemiGau for this amazing contribution to our package! w/@CYHSM
Without Twitter, I never would have applied for @kylesburger's reproducible neuroscience workshop or @neurohackademy... Since then, my PhD and now postdoc work involves using or helping others use #fMRIPREP on a weekly basis, & I recently worked on a manuscript with @oesteban 🥲
Check out the #COGNESTIC's 'fMRI Analysis' materials on github.com/dcdace/COGNEST… Any comments/suggestions for future improvement are welcome! @BIDSstandard, #heudiconv, #PyBIDS, #MRIQC, #fMRIPrep, #Nilearn
Check out the #COGNESTIC's 'fMRI Analysis' materials on github.com/dcdace/COGNEST… Any comments/suggestions for future improvement are welcome! @BIDSstandard, #heudiconv, #PyBIDS, #MRIQC, #fMRIPrep, #Nilearn