Recommendations for the creation of benchmark datasets for reproducible artificial intelligence in radiology

Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited generalizability hinders their widespread adoption. Currently, most research groups and industry have limited access to the data needed for e...

Full description

Saved in:
Bibliographic Details
Published in:Insights into imaging 2024-10, Vol.15 (1), p.248-12, Article 248
Main Authors: Sourlos, Nikos, Vliegenthart, Rozemarijn, Santinha, Joao, Klontzas, Michail E., Cuocolo, Renato, Huisman, Merel, van Ooijen, Peter
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial intelligence (AI) software
Benchmark dataset
Benchmarks
Bias
Datasets
Diagnostic Radiology
Guideline
Image quality
Imaging
Internal Medicine
Interventional Radiology
Medicine
Medicine & Public Health
Neuroradiology
Radiology
Software
Ultrasound
Validation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited generalizability hinders their widespread adoption. Currently, most research groups and industry have limited access to the data needed for external validation studies. The creation and accessibility of benchmark datasets to validate such solutions represents a critical step towards generalizability, for which an array of aspects ranging from preprocessing to regulatory issues and biostatistical principles come into play. In this article, the authors provide recommendations for the creation of benchmark datasets in radiology, explain current limitations in this realm, and explore potential new approaches. Clinical relevance statement Benchmark datasets, facilitating validation of AI software performance can contribute to the adoption of AI in clinical practice. Key Points Benchmark datasets are essential for the validation of AI software performance. Factors like image quality and representativeness of cases should be considered. Benchmark datasets can help adoption by increasing the trustworthiness and robustness of AI. Graphical Abstract
ISSN:1869-4101
1869-4101
DOI:10.1186/s13244-024-01833-2