AI-based image quality assessment of positioning in mammography: considerations and challenges
AI has huge potential for automated assessment of diagnostic image quality. Compared with human reading agreement, substantial disagreement may also be found. Direct transformation of perfect-good-moderate-inadequate scoring into an AI algorithm is challenging.
Authors
- Stefano Gianolini
- Malik Galijašević (ORCID: https://orcid.org/0000-0001-6577-0784)
- Gerlig Widmann (ORCID: https://orcid.org/0000-0002-7255-0672)
- Wolfram Santner (ORCID: https://orcid.org/0000-0002-7244-1222)
- J. Gjesvik
- Tina Santner
- Mickaël Tardy
- Marthe Larsen
- Solveig Hofvind
- Johanne-Gro Stalheim
- Stephanie Frei
Institutions
- Norwegian Institute of Public Health (NO)
- Innsbruck Medical University (AT)
- Universität Innsbruck (AT)
- Institut Génétique Nantes Atlantique (FR)
- Cancer Registry of Norway (NO)
- Associated Radiologists (US)
- University of Bergen (NO)
- Software (Spain) (ES)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2026-02-16
- DOI
- https://doi.org/10.1186/s13244-025-02191-3
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00