Consistent explainable image quality assessment for medical imaging
The proposed system, powered by NormGrad, significantly improves the reliability of automated medical image quality evaluations. The introduction of the Difference of Means metric offers a unique way to assess saliency detector consistency, supporting NormGrad's potential for widespread clinical adoption.
Authors
- Caner Özer (ORCID: https://orcid.org/0000-0001-9044-143X)
- Arda Güler (ORCID: https://orcid.org/0000-0002-5763-6785)
- Ayşel Türkvatan (ORCID: https://orcid.org/0000-0002-3150-5787)
Institutions
- King's College London (GB)
- Istanbul Technical University (TR)
- Burdur Mehmet Akif Ersoy Üniversitesi (TR)
- University of Twente (NL)
Publication Details
- Journal
- Health Information Science and Systems
- Published
- 2026-01-20
- DOI
- https://doi.org/10.1007/s13755-025-00411-0
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Türkiye Bilimsel ve Teknolojik Araştırma Kurumu
- Istanbul Teknik Üniversitesi