A multi-view CNN model to predict resolving of new lung nodules on follow-up low-dose chest CT
Predicting the resolution of new intermediate lung nodules in lung cancer screening CT is a challenge. Our multi-view CNN model showed an AUC of 0.81, a specificity of 0.93, and a sensitivity of 0.63 at the nodule level. The multi-view model demonstrated a significant improvement in AUC compared to the three 2D models, one 2.5D model, and one 3D model.
Authors
- Marcel van Tuinen (ORCID: https://orcid.org/0000-0002-7374-4890)
- Jingxuan Wang (ORCID: https://orcid.org/0000-0002-1648-2679)
- Rozemarijn Vliegenthart (ORCID: https://orcid.org/0000-0002-7262-3376)
- Peter M. A. van Ooijen (ORCID: https://orcid.org/0000-0002-8995-1210)
- Xiaowen Zhang (ORCID: https://orcid.org/0000-0003-3825-6995)
- Wei Tang (ORCID: https://orcid.org/0000-0002-6351-4338)
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2025-06-27
- DOI
- https://doi.org/10.1186/s13244-025-02000-x
- Citations
- 4
- Primary Topic
- Lung Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 6.07
Funders
- Rijksuniversiteit Groningen
- China Scholarship Council