% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Zhao:1024665,
author = {Zhao, Chenying and Jarecka, Dorota and Covitz, Sydney and
Chen, Yibei and Eickhoff, Simon B. and Fair, Damien A. and
Franco, Alexandre R. and Halchenko, Yaroslav O. and
Hendrickson, Timothy J. and Hoffstaedter, Felix and
Houghton, Audrey and Kiar, Gregory and Macdonald, Austin and
Mehta, Kahini and Milham, Michael P. and Salo, Taylor and
Hanke, Michael and Ghosh, Satrajit S. and Cieslak, Matthew
and Satterthwaite, Theodore D.},
title = {{A} reproducible and generalizable software workflow for
analysis of large-scale neuroimaging data collections using
{BIDS} {A}pps},
journal = {Imaging neuroscience},
volume = {2},
issn = {2837-6056},
address = {Cambridge, MA},
publisher = {MIT Press},
reportid = {FZJ-2024-02338},
pages = {1 - 19},
year = {2024},
abstract = {Neuroimaging research faces a crisis of reproducibility.
With massive sample sizes and greater data complexity, this
problem becomes more acute. Software that operates on
imaging data defined using the Brain Imaging Data Structure
(BIDS)—the BIDS App—has provided a substantial advance.
However, even using BIDS Apps, a full audit trail of data
processing is a necessary prerequisite for fully
reproducible research. Obtaining a faithful record of the
audit trail is challenging—especially for large datasets.
Recently, the FAIRly big framework was introduced as a way
to facilitate reproducible processing of large-scale data by
leveraging DataLad—a version control system for data
management. However, the current implementation of this
framework was more of a proof of concept, and could not be
immediately reused by other investigators for different use
cases. Here, we introduce the BIDS App Bootstrap (BABS), a
user-friendly and generalizable Python package for
reproducible image processing at scale. BABS facilitates the
reproducible application of BIDS Apps to large-scale
datasets. Leveraging DataLad and the FAIRly big framework,
BABS tracks the full audit trail of data processing in a
scalable way by automatically preparing all scripts
necessary for data processing and version tracking on high
performance computing (HPC) systems. Currently, BABS
supports jobs submissions and audits on Sun Grid Engine
(SGE) and Slurm HPCs with a parsimonious set of programs. To
demonstrate its scalability, we applied BABS to data from
the Healthy Brain Network (HBN; n = 2,565). Taken together,
BABS allows reproducible and scalable image processing and
is broadly extensible via an open-source development
model.Reproducibility, BIDS Apps, software, MRI, big data,
image processing},
cin = {INM-7},
ddc = {050},
cid = {I:(DE-Juel1)INM-7-20090406},
pnm = {5254 - Neuroscientific Data Analytics and AI (POF4-525)},
pid = {G:(DE-HGF)POF4-5254},
typ = {PUB:(DE-HGF)16},
pubmed = {37645999},
UT = {WOS:001531527700014},
doi = {10.1162/imag_a_00074},
url = {https://juser.fz-juelich.de/record/1024665},
}