Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Exposure to Feline Viruses in European Wildcats (<i>Felis s. silvestris</i>) in Germany: Spatial Patterns and Environmental Risk Factors.

Viruses·2026
Same author

A Heterogeneous Graph Neural Network Framework for Multi-Horizon Stroke Mortality Prediction.

medRxiv : the preprint server for health sciences·2026
Same author

Effectiveness of Physical Activity Interventions Using Wearables and Smartphone Applications for Individuals With Cardiovascular Diseases and Stroke: A Systematic Review and Meta-Analysis.

Journal of the American Heart Association·2026
Same author

European cancer data sharing: Analyses of an international survey.

International journal of medical informatics·2026
Same author

Infrastructure and policy reforms to facilitate collaboration in medical research.

Nature reviews. Nephrology·2026
Same author

CCR5 and CD74 are potential therapeutic targets for necroinflammation in preclinical cholesterol crystal embolism.

Science translational medicine·2026
Same journal

Margin Adequacy in Phyllodes Tumours Revisited: Reappraisal of the Evidence Base and Knowledge Gaps.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same journal

Genomic Characterization of Classic Adamantinoma, Osteofibrous Dysplasia, and Osteofibrous Dysplasia-like Adamantinoma.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same journal

Immunophenotypic, Cytogenetic, and Molecular Characterization of NUP98-Rearranged Pediatric Myeloid Neoplasms.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same journal

Chromoanagenesis in Myelodysplastic Syndromes Is Associated With Highly Complex Karyotype, TP53 Disruption and Dismal Prognosis.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same journal

Co-Existent Endometrial and Fallopian Tube Carcinoma, Molecular and Pathological Features for Risk Stratification.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same journal

RUNX2 Rearrangement as a Recurrent Molecular Event and Diagnostic Marker in Salivary Gland Keratocystoma.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
See all related articles

Related Experiment Video

Updated: Aug 29, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

197

Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology.

André Homeyer1, Christian Geißler2, Lars Ole Schwen3

  • 1Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359, Bremen, Germany. andre.homeyer@mevis.fraunhofer.de.

Modern Pathology : an Official Journal of the United States and Canadian Academy of Pathology, Inc
|September 10, 2022
PubMed
Summary
This summary is machine-generated.

Creating test datasets for artificial intelligence (AI) in pathology requires clear guidelines. This study provides recommendations for AI developers and pathologists to ensure reliable performance evaluation and regulatory approval of AI diagnostic tools.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.6K
Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues
06:44

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Published on: March 29, 2021

2.6K

Related Experiment Videos

Last Updated: Aug 29, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:30

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

197
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.6K
Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues
06:44

Automated Dissection Protocol for Tumor Enrichment in Low Tumor Content Tissues

Published on: March 29, 2021

2.6K

Area of Science:

  • Digital Pathology
  • Medical Artificial Intelligence (AI)
  • Regulatory Science

Background:

  • AI solutions for digital histology image analysis show potential for enhancing pathological diagnosis.
  • Evaluating AI predictive performance and obtaining regulatory approval are crucial before clinical implementation.
  • Compiling appropriate test datasets for AI evaluation in pathology is challenging due to a lack of specific recommendations.

Purpose of the Study:

  • To summarize key aspects and literature findings on test datasets for AI in pathology.
  • To derive general recommendations for compiling robust test datasets.
  • To address critical questions regarding dataset size, bias detection, reporting, and regulatory requirements.

Main Methods:

  • Convened a multi-stakeholder committee including AI developers, pathologists, and researchers.
  • Conducted extensive literature reviews on existing practices for test datasets in pathology.
  • Synthesized discussions and literature findings to formulate recommendations.

Main Results:

  • Identified key considerations for test dataset compilation, including image quantity, handling low-prevalence data, bias detection, and reporting standards.
  • Discussed international regulatory requirements for AI in pathology.
  • Provided actionable recommendations to guide AI developers and aid regulatory agencies.

Conclusions:

  • Standardized recommendations for test datasets are essential for validating AI performance in pathology.
  • These guidelines will help AI developers demonstrate product utility and assist pathologists/regulators in verifying performance.
  • Further research is needed to define criteria for representative datasets to enhance AI autonomy and diagnostic workflow integration.