Artificial intelligence as an independent reader of risk-dominant lung nodules: influence of CT reconstruction parameters
Question Patient management in lung cancer screening depends on the risk-dominant nodule, yet no prior studies have assessed the impact of reconstruction parameters on AI performance for these nodules. Findings The difference between reconstruction kernels (AI-D45f/1 mm vs. AI-B80f/1 mm, or AI-B30f/2 mm vs. AI-D45f/2 mm) significantly affected AI's performance in risk-dominant nodule type classification, but not nodule detection. Clinical relevance The use of kernel for AI consistent with radiologist's choice is likely to improve the overall performance of AI-based CAD systems as an independent reader and support greater clinical acceptance and integration of AI tools into routine practice.
Authors
- Marcel van Tuinen (ORCID: https://orcid.org/0000-0002-7374-4890)
- Monique D. Dorrius (ORCID: https://orcid.org/0000-0001-9825-6001)
- Jaeyoun Yi (ORCID: https://orcid.org/0000-0002-7664-9493)
- Marjolein A. Heuvelmans (ORCID: https://orcid.org/0000-0002-5712-4085)
- Geertruida H. de Bock (ORCID: https://orcid.org/0000-0003-3104-4471)
- Donghoon Yu (ORCID: https://orcid.org/0000-0001-7438-7349)
- Matthijs Oudkerk (ORCID: https://orcid.org/0000-0003-2800-4110)
- Zhaoxiang Ye (ORCID: https://orcid.org/0000-0003-3157-8393)
- Yifei Mao (ORCID: https://orcid.org/0000-0003-3766-1374)
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
- Tianjin Medical University Cancer Institute and Hospital (CN)
- Amsterdam University Medical Centers (NL)
Publication Details
- Journal
- European Radiology
- Published
- 2025-08-29
- DOI
- https://doi.org/10.1007/s00330-025-11949-8
- Primary Topic
- Lung Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Koninklijke Nederlandse Akademie van Wetenschappen
- China Scholarship Council