{
  "abstract": "Digital and artificial intelligence (AI) pathology have advanced rapidly and are increasingly embedded in translational research, clinical trials and regulated diagnostic devices. Multiple reviews have addressed the underlying computational methods, oncology applications and clinical translation barriers; however, the operational and regulatory infrastructure required to deploy these technologies across the full drug-development pipeline remains under-reviewed. This structured narrative review synthesises peer-reviewed literature and regulatory documents identified through searches of PubMed, Embase and Web of Science between January 2019 and April 2026 (78 sources retained) on the end-to-end ecosystem connecting AI-ready tissue biobanks, preclinical pathology, AI-assisted patient screening, clinical-trial endpoint adjudication, central pathology review, Contract Research Organization (CRO) workflows and US Food and Drug Administration (FDA) regulatory pathways governing In Vitro Diagnostics (IVD), Software as a Medical Device (SaMD) and Companion Diagnostics (CDx). Unlike prior method-centric or oncology-clinician-centric reviews, we focus on the infrastructure between models and patients, including Laboratory Information Systems (LIS), Image Management Systems (IMS), AI orchestration and structured reporting under Clinical Laboratory Improvement Amendments, College of American Pathologists, Good Laboratory Practice, Good Clinical Laboratory Practice, Health Insurance Portability and Accountability Act and FDA frameworks. We provide a vendor-agnostic comparison of integrated pathology platforms, a mapping of FDA regulatory pathways (510(k), De Novo, premarket approval) to digital-pathology product categories, a stage-by-stage map from each drug-development challenge to its enabling infrastructure and regulatory framework, and a critical appraisal of the unresolved bottlenecks that gate broad adoption: domain shift, interpretability, annotation cost, algorithmic bias, external validation, regulatory uncertainty and reimbursement. A governed, interoperable LIS, IMS and AI ecosystem is a prerequisite for translating digital-pathology research into regulator-grade evidence. Priorities include external validation against reporting standards (Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis - Artificial Intelligence (TRIPOD-AI), Checklist for Artificial Intelligence in Medical Imaging (CLAIM), Development and Early-stage Clinical Identification and Delegation Evaluation of Artificial Intelligence (DECIDE-AI)), harmonisation with the EU AI Act and EU Medical Device Regulation and cost-effectiveness evaluation in real-world deployment.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computational Pathology, NovinoAI, Fort Lauderdale, Florida, USA.",
    "Frontage Laboratories, Exton, Pennsylvania, USA.",
    "Department of Urology, Good Samaritan Hospital Medical Center, Suffern, New York, USA."
  ],
  "article_type": "review article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Min Zhu"
    },
    {
      "affs": [
        0
      ],
      "name": "Yodit Aschenaki"
    },
    {
      "affs": [
        0
      ],
      "name": "Xinwei Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Rasoul Sali",
      "orcid": "0000-0003-3995-0735"
    },
    {
      "affs": [
        1
      ],
      "name": "Zhongping Lin"
    },
    {
      "affs": [
        2
      ],
      "name": "Christopher Dixon"
    },
    {
      "affs": [
        0
      ],
      "name": "David Y Zhang",
      "orcid": "0009-0007-7682-5198"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3aryjr7zkemv9.bib",
  "cited_by": 0,
  "doi": "10.1136/bmjonc-2026-001208",
  "fulltext_url": "https://europepmc.org/articles/PMC13723797",
  "id": "3aryjr7zkemv9",
  "issns": [
    "2752-7948"
  ],
  "landing_url": "https://europepmc.org/article/MED/42968799",
  "language": "eng",
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "1506"
    ],
    [
      "heading",
      "Review"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7223788369",
  "pdf_url": "https://europepmc.org/articles/PMC13723797?pdf=render",
  "pmcid": "PMC13723797",
  "pmid": "42968799",
  "published": "2026-10-27",
  "publisher": "BMJ Publishing Group",
  "ris": "https://research.draconitic.com/paper/3aryjr7zkemv9.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T15:20:53Z",
      "native_id": "MED:42968799",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42968799"
    },
    {
      "first_seen": "2026-11-04T12:22:22Z",
      "native_id": "PMC13723797",
      "source": "pmc",
      "url": "https://doi.org/10.1136/bmjonc-2026-001208"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "journal-openalex:F27",
      "subfield": "general"
    }
  ],
  "title": "Operationalising digital and AI pathology in translational research and drug development: an infrastructure and regulatory perspective from biobank to companion diagnostic.",
  "title_text": "Operationalising digital and AI pathology in translational research and drug development: an infrastructure and regulatory perspective from biobank to companion diagnostic.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-05T12:20:33Z",
  "url": "https://research.draconitic.com/paper/3aryjr7zkemv9",
  "venue": "BMJ oncology",
  "versions": []
}