Statistical testing of agreement in overlap-based performance between an AI segmentation device and a multi-expert human panel without requiring a reference standard
The paired-testing method offers a new tool for assessing the agreement between an AI segmentation device and multiple human expert panelists without requiring a reference standard.
Authors
- H. Kenny (ORCID: https://orcid.org/0000-0003-3847-7448)
- Nicholas Petrick (ORCID: https://orcid.org/0000-0001-5167-8899)
- Mike Mikailov (ORCID: https://orcid.org/0000-0002-1700-4230)
- Shuyue Guan (ORCID: https://orcid.org/0000-0002-3779-9368)
- Tingting Hu (ORCID: https://orcid.org/0000-0002-7304-9433)
- F. W. Samuelson (ORCID: https://orcid.org/0000-0002-1130-0303)
- Berkman Sahiner (ORCID: https://orcid.org/0000-0003-2804-2264)
Institutions
- United States Food and Drug Administration (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2025-10-22
- DOI
- https://doi.org/10.1117/1.jmi.12.5.055003
- Primary Topic
- Impact of AI and Big Data on Business and Society
- Type
- article
- Field-Weighted Citation Impact
- 0.00