% 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:1046787,
      author       = {Thönnißen, Julia and Oliveira, Sarah and Oberstraß,
                      Alexander and Kropp, Jan-Oliver and Gui, Xiaoyun and
                      Schiffer, Christian and Dickscheid, Timo},
      title        = {{A} {P}erspective on {FAIR} and {S}calable {A}ccess to
                      {L}arge {I}mage {D}ata},
      publisher    = {Zenodo},
      reportid     = {FZJ-2025-03954},
      pages        = {1-3},
      year         = {2025},
      abstract     = {The rapid development of new imaging technologies across
                      scientific domains–especially high-throughput
                      technologies–results in a growing volume of image datasets
                      in the Tera- to Petabyte scale. Efficient visualization and
                      analysis of such massive image resources is critical but
                      remains challenging due to the sheer size of the data, its
                      continuous growth, and the limitations of conventional
                      software tools to address these problems. Tools for
                      visualization, annotation and analysis of large image data
                      are confronted with the fundamental dilemma of balancing
                      computational efficiency and memory requirements. Many tools
                      are unable to process large datasets due to memory
                      constraints, requiring workarounds like downsampling. On the
                      other hand, solutions that can handle large data efficiently
                      often rely on specialized or even proprietary file formats,
                      limiting interoperability with other software. This reflects
                      diverging requirements: storage favours compression for
                      efficiency, analysis demands fast data access, and
                      visualization requires tiled, multi-resolution
                      representations. Lacking a unified approach for these
                      conflicting needs, the operation of large and dynamically
                      evolving image repositories in practice often requires
                      undesirable data conversions and costly data duplication. In
                      addressing these challenges, the bioimaging community
                      increasingly adheres to the FAIR principles [1] through
                      national and international initiatives [2], [3], [4]. For
                      example, the Open Microscopy Environment (OME) fosters
                      standards such as OME-TIFF [5] and its cloud-native
                      successor OME-NGFF [6]; BioFormats [7] and OMERO [8]
                      facilitate metadata-rich data handling across diverse
                      platforms; and BrAinPI [9] provides web-based visualization
                      of images via Neuroglancer [10]. These tools represent
                      important developments towards more efficient and
                      standardized use of bioimaging data. However, for very large
                      and dynamically growing repositories, it is still not
                      feasible to settle on a single standard for a subset of
                      these tools, in particular in the light of very diverging
                      needs for massively parallel processing on HPC systems.
                      Therefore, converting data to a single target format is
                      often not a practical solution. We propose a concept for a
                      modular image delivery service which acts as a middleware
                      between large image data resources and applications, serving
                      image data from a cloud resource in multiple requested
                      representations on demand. The service allows reading data
                      stored in different input file formats, applying coordinate
                      transformations and filtering operations on-the-fly, and
                      serving the results in a range of different output formats
                      and layouts. Building upon a common framework for reading
                      and transforming data, an extensible set of access points
                      connects the service to client applications: Lightweight
                      REST APIs allow web-based mutli-resolution access (e.g., in
                      common formats such as used in Neuroglancer and
                      OpenSeadragon base viewers); mountable filesystem interfaces
                      enable linking the repository to file-oriented solutions
                      (e.g., OMERO, ImageJ); and programmatic access from
                      customizable software tools (e.g., Napari). To provide
                      compatibility with upcoming image data standards like BIDS
                      [11] and minimize conversion efforts, the service is able to
                      dynamically expose standard-conform views into arbitrarily
                      organized datasets. The proposed approach for reading and
                      transforming data on-the-fly eliminates the need for
                      redundant storage and application-specific conversions of
                      datasets, improving workflow efficiency and sustainability.
                      In summary, we advocate for the development of a flexible
                      and extensible image data service that supports large-scale
                      analysis, dynamic transformations, multi-tool
                      interoperability, and compatibility with community standards
                      for large image datasets. This way it supports the FAIR
                      principles, reduces integration barriers, meets the
                      performance demands of modern imaging research, and still
                      fosters the use of existing community developments.},
      month         = {Aug},
      date          = {2025-08-26},
      organization  = {2nd Conference on Research Data
                       Infrastructure (CoRDI), Aachen
                       (Germany), 26 Aug 2025 - 28 Aug 2025},
      keywords     = {data access (Other) / visualization (Other) /
                      interoperability (Other) / bioimaging (Other)},
      cin          = {INM-1},
      cid          = {I:(DE-Juel1)INM-1-20090406},
      pnm          = {5254 - Neuroscientific Data Analytics and AI (POF4-525) /
                      DFG project G:(GEPRIS)501864659 - NFDI4BIOIMAGE - Nationale
                      Forschungsdateninfrastruktur für Mikroskopie und
                      Bildanalyse (501864659) / EBRAINS 2.0 - EBRAINS 2.0: A
                      Research Infrastructure to Advance Neuroscience and Brain
                      Health (101147319) / HIBALL - Helmholtz International
                      BigBrain Analytics and Learning Laboratory (HIBALL)
                      (InterLabs-0015) / JL SMHB - Joint Lab Supercomputing and
                      Modeling for the Human Brain (JL SMHB-2021-2027) / X-BRAIN
                      (ZT-I-PF-4-061)},
      pid          = {G:(DE-HGF)POF4-5254 / G:(GEPRIS)501864659 /
                      G:(EU-Grant)101147319 / G:(DE-HGF)InterLabs-0015 /
                      G:(DE-Juel1)JL SMHB-2021-2027 / G:(DE-HGF)ZT-I-PF-4-061},
      typ          = {PUB:(DE-HGF)8},
      doi          = {10.5281/zenodo.16736220},
      url          = {https://juser.fz-juelich.de/record/1046787},
}