Artificial intelligence for TNM staging in NSCLC: a critical appraisal of segmentation utility in [1⁸F]FDG PET/CT
Clinically driven metrics and cause-based error analysis offer valuable insight into AI segmentation performance. The evaluated model showed excellent lesion sensitivity but a tendency towards systematic overprediction across TNM categories. On a lesion level M-stage false positives and undersegmentation in the hilar region emerged as the main driver of clinically relevant upstaging. Despite promising lesion detection sensitivity, only 67.7% UICC-stagings were accurate using AI masks, indicating that diagnostic AI may support, though not yet replace, manual lesion evaluation in NSCLC [<sup>1</sup>⁸F]FDG PET/CT.
Authors
- Michael Ingrisch (ORCID: https://orcid.org/0000-0003-0268-9078)
- Lisa C. Adams (ORCID: https://orcid.org/0000-0001-5836-4542)
- Matthias P. Fabritius (ORCID: https://orcid.org/0000-0002-3471-4701)
- R. Ebner (ORCID: https://orcid.org/0009-0001-0851-0094)
- Lalith Kumar Shiyam Sundar (ORCID: https://orcid.org/0000-0003-3004-7937)
- Rudolf Alexander Werner (ORCID: https://orcid.org/0000-0003-3372-6046)
- Johanna Ta
- Amanda Tufman (ORCID: https://orcid.org/0000-0001-9243-9050)
- Gabriel T. Sheikh (ORCID: https://orcid.org/0000-0002-7026-9203)
- Jens Ricke (ORCID: https://orcid.org/0000-0001-8762-8594)
- Jakob Dexl (ORCID: https://orcid.org/0000-0002-0617-0460)
- Maurice M. Heimer (ORCID: https://orcid.org/0000-0002-0940-0161)
- Friederike Herr (ORCID: https://orcid.org/0009-0004-0835-0328)
- Katharina Jeblick (ORCID: https://orcid.org/0000-0002-8678-7152)
- Clemens C. Cyran (ORCID: https://orcid.org/0000-0001-5630-6242)
- Leon Orasanin
Institutions
- Johns Hopkins University (US)
- Johns Hopkins Medicine (US)
- LMU Klinikum (DE)
- München Klinik (DE)
- German Center for Lung Research (DE)
- Munich Center for Machine Learning
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2025-11-23
- DOI
- https://doi.org/10.1007/s00259-025-07677-2
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bayerisches Staatsministerium für Wissenschaft und Kunst
- Fonds de Recherche du Québec - Santé