{
  "abstract": "Introduction: Automated extraction of slide metadata remains a major bottleneck in digital pathology, especially in settings where barcode identifiers are missing, damaged, or inconsistent. Manual transcription of case, block, and stain information is error-prone and does not scale. Building on our previous whole-slide image (WSI)-Babel-Fish framework, we developed WSI-Babel-Shark, a more extensible pipeline for reliable metadata extraction across heterogeneous slide-label layouts. Materials and methods: WSI-Babel-Shark integrates data matrix code decoding, region of interest (ROI)-based optical character recognition (OCR), and rule-based metadata parsing within a modular Python and Docker architecture. To handle diverse institutional label formats, the system incorporates a deep learning-based label layout classifier using a ResNet-18 backbone, fused with handcrafted descriptors and prototype-based open-set recognition to categorize labels into 10 predefined layout groups. A graphical interface supports ROI annotation, dataset management, and configuration editing. Performance was evaluated on 270 WSIs (.svs and .ndpi formats) and cross-validated using 110 slides from the previously published WSI-Babel-Fish dataset to assess backward compatibility. Results: The label layout classifier achieved an overall accuracy of 97.4%, with macro-averaged precision, recall, and F1-score of 0.98 while reliably rejecting previously unseen layouts. End-to-end pipeline evaluation achieved complete SlideID reconstruction for 258 of 267 evaluable WSIs (96.6%). Independent comparison of OCR-derived metadata with the corresponding Data Matrix-decoded metadata on 236 slides demonstrated complete metadata concordance for 230 slides (97.5%), whereas field-level concordance ranged from 98.3% to 100.0% across all evaluated metadata fields. Cross-dataset analysis confirmed full compatibility with WSI-Babel-Fish label structures. Conclusion: WSI-Babel-Shark advances automated metadata extraction from WSIs by introducing a label-layout classification framework validated on heterogeneous label layouts and incorporating open-set recognition, together with standardized ROI annotation and a fully containerized implementation. The framework ensures reproducible linkage between digitized slides and lab information, is designed to facilitate interoperability with lab information systems, and provides a scalable foundation for large-scale digital pathology workflows. The complete implementation is openly available at: https://github.com/cpheidelberg/WSI-Babel-Shark .",
  "abstract_shown": true,
  "affiliations": [
    "Section Computational Pathology Heidelberg, Institute of Pathology Heidelberg, University Hospital Heidelberg, University of Heidelberg, Heidelberg, Germany; Corresponding author.",
    "Section Computational Pathology Heidelberg, Institute of Pathology Heidelberg, University Hospital Heidelberg, University of Heidelberg, Heidelberg, Germany",
    "Section Computational Pathology Heidelberg, Institute of Pathology Heidelberg, University Hospital Heidelberg, University of Heidelberg, Heidelberg, Germany; Data Analysis and Modeling in Medicine, Mannheim Institute for Intelligent Systems in Medicine (MIISM), Heidelberg University, Mannheim, Germany",
    "Section Computational Pathology Heidelberg, Institute of Pathology Heidelberg, University Hospital Heidelberg, University of Heidelberg, Heidelberg, Germany; Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shahram Aliyari"
    },
    {
      "affs": [
        1
      ],
      "name": "Maximilian Legnar"
    },
    {
      "affs": [
        2
      ],
      "name": "Christoph Blattgerste"
    },
    {
      "affs": [
        1
      ],
      "name": "Ayk Jessen"
    },
    {
      "affs": [
        1
      ],
      "name": "Balamurugan Thirukonda Subramanian Balakrishnan"
    },
    {
      "affs": [
        1
      ],
      "name": "Nils Englert"
    },
    {
      "affs": [
        1
      ],
      "name": "Philip S.J. Kaib"
    },
    {
      "affs": [
        1
      ],
      "name": "Mark Sementsov"
    },
    {
      "affs": [
        1
      ],
      "name": "Constantin Schwab"
    },
    {
      "affs": [
        3
      ],
      "name": "Cleo-Aron Weis"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/28n1g5wb10hmy.bib",
  "cited_by": 0,
  "doi": "10.1016/j.jpi.2026.100722",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S2153353926001847",
  "id": "28n1g5wb10hmy",
  "issns": [
    "2153-3539",
    "2229-5089"
  ],
  "landing_url": "https://doi.org/10.1016/j.jpi.2026.100722",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research Article"
    ],
    [
      "lcc",
      "R858-859.7"
    ],
    [
      "lcc",
      "RB1-214"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7214232503",
  "pdf_url": "https://www.sciencedirect.com/science/article/pii/S2153353926001847/pdf",
  "pmcid": "PMC13721096",
  "pmid": "42965064",
  "published": "2026-09-24",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/28n1g5wb10hmy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:51Z",
      "native_id": "0dcc618725bf49028eed62d1f1a3262e",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.jpi.2026.100722"
    },
    {
      "first_seen": "2026-10-31T12:21:37Z",
      "native_id": "PMC:PMC13721096",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13721096"
    },
    {
      "first_seen": "2026-11-03T12:21:50Z",
      "native_id": "PMC13721096",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.jpi.2026.100722"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R858-859.7",
      "subfield": "general"
    }
  ],
  "title": "WSI-Babel-Shark: A modular pipeline for robust metadata extraction from heterogeneous whole slide image labels in digital pathology",
  "title_text": "WSI-Babel-Shark: A modular pipeline for robust metadata extraction from heterogeneous whole slide image labels in digital pathology",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:21:50Z",
  "url": "https://research.draconitic.com/paper/28n1g5wb10hmy",
  "venue": "Journal of Pathology Informatics",
  "versions": []
}