% 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”.

@INPROCEEDINGS{Thnnien:1033590,
      author       = {Thönnißen, Julia and Dickscheid, Timo and Hanke, Michael},
      title        = {{S}calable {D}ata {M}anagement for {H}igh-{R}esolution
                      {M}icroscopy of the {H}uman {B}rain: {C}hallenges and
                      {F}uture {D}irections},
      reportid     = {FZJ-2024-06470},
      year         = {2024},
      abstract     = {In order to investigate the complex structural and
                      functional organization of the human brain, data must be
                      integrated across multiple modalities and resolutions. This
                      requires the implementation of scalable workflows for data
                      extraction, AI-driven analysis, and visualization. A key
                      challenge in this process is the storage and organization of
                      large image datasets in suitable repositories. Due to the
                      prohibitive cost of data duplication at this scale, storage
                      systems must adhere to community standards, enable
                      provenance tracking, and meet the performance demands of
                      high-throughput data ingestion, highly parallel processing
                      on HPC systems, and random access for interactive
                      visualization. In this context we address the case of
                      building a repository of high-resolution microscopy scans
                      for whole human brain sections in the order of multiple
                      petabytes.Digitizing a human brain using whole-slide imaging
                      of cell body stained tissue sections requires capturing
                      about 7,000-8,000 histological sections at 20 micrometer
                      thickness using high-throughput scanners. When aiming for an
                      isotropic resolution of 1 micrometer, each histological
                      section generates 29 TIFF images (“z-stack”),
                      representing different focus levels. These images are
                      automatically transferred to a gateway server for initial
                      organization and automated quality control (QC). After QC,
                      the z-stack is moved to a parallel file system (GPFS) on a
                      supercomputer, generating approximately 2 petabytes of image
                      data across 200,000 files for a single brain. These data are
                      then accessed by various applications and pipelines, each
                      with distinct requirements. HPC applications, such as deep
                      learning-based cell segmentation and brain mapping, rely on
                      fast random access and parallel I/O to efficiently stream
                      image patches to GPUs. In contrast, remote visualization and
                      annotation require access via an HTTP service, along with
                      higher-capacity storage for serving diverse data
                      concurrently. A multi-tier HPC storage system addresses
                      these needs: the high-performance storage tier offers low
                      latency and high bandwidth for analysis, while the
                      capacity-optimized extended storage tier meets visualization
                      requirements. Controlled data staging across these tiers is
                      crucial and is managed using DataLad, which enables
                      well-defined staging, comprehensive tracking, and version
                      control of image datasets across distributed storage
                      systems. Each brain section is organized as a distinct
                      DataLad dataset to minimize the number of files per
                      repository.However, the current data management approach
                      presents two major challenges. First, the TIFF format lacks
                      support for parallel I/O, leading to data duplication when
                      converting to HDF5 for HPC workflows. Second, the existing
                      data organization is not aligned with community standards,
                      hindering collaboration. Therefore, a major objective is
                      standardization of both file formats and folder structures.
                      However, adopting standards such as the Brain Imaging Data
                      Structure (BIDS) poses significant challenges due to the
                      large number of files created by multiple folders and
                      sidecar files, as well as the small-file structure of
                      OME-ZARR, which is incompatible with GPFS file systems that
                      require inode restrictions.To address these challenges,
                      optimizing the size of DataLad datasets and exploring ways
                      to reduce inode usage are essential. Questions remain about
                      whether file formats like ZARR v3 or HDF5, which minimize
                      inode consumption, should be integrated into the BIDS
                      standard. Community discussions may provide solutions to
                      these issues.},
      month         = {Nov},
      date          = {2024-11-19},
      organization  = {INM Retreat 2024, Jülich (Germany),
                       19 Nov 2024 - 20 Nov 2024},
      subtyp        = {After Call},
      cin          = {INM-1},
      cid          = {I:(DE-Juel1)INM-1-20090406},
      pnm          = {5251 - Multilevel Brain Organization and Variability
                      (POF4-525) / 5254 - Neuroscientific Data Analytics and AI
                      (POF4-525) / HIBALL - Helmholtz International BigBrain
                      Analytics and Learning Laboratory (HIBALL) (InterLabs-0015)
                      / EBRAINS 2.0 - EBRAINS 2.0: A Research Infrastructure to
                      Advance Neuroscience and Brain Health (101147319) / DFG
                      project G:(GEPRIS)501864659 - NFDI4BIOIMAGE - Nationale
                      Forschungsdateninfrastruktur für Mikroskopie und
                      Bildanalyse (501864659)},
      pid          = {G:(DE-HGF)POF4-5251 / G:(DE-HGF)POF4-5254 /
                      G:(DE-HGF)InterLabs-0015 / G:(EU-Grant)101147319 /
                      G:(GEPRIS)501864659},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/1033590},
}