A Lesion-adaptive Segmentation Approach for Tumor Delineation on FDG PET/CT in Diffuse Large B-cell Lymphoma Patients
A straightforward decision-rule approach using SUVpeak and SUVbg successfully selects the preferred method for individual DLBCL lesions across treatment phases and matches ML performance with greater simplicity and clinical applicability. Although supervision remains necessary, this approach helps address the current gap in segmentation methodology for interim and EoT PET, where SUV4.0 may not always be appropriate.
Authors
- Jakoba J. Eertink
- Daniëlle M. E. van Assema (ORCID: https://orcid.org/0000-0003-0555-7441)
- P. Lugtenburg
- Gerben J. C. Zwezerijnen
- Martijn W. Heymans
- Michael D. A. van Elk
- Yvonne W. S. Jauw
- Ronald Boellaard
- Otto S. Hoekstra
- Patricia C. Spa
- Sanne E. Wiegers
- Josée M. Zijlstra
Institutions
- Dutch Cancer Society (NL)
- Northwest Hospital (US)
- GGD Amsterdam (NL)
- Erasmus MC Cancer Institute (NL)
- Medisch Centrum Alkmaar (NL)
- Cancer Center Amsterdam (NL)
- Vrije Universiteit Amsterdam (NL)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2026-02-14
- DOI
- https://doi.org/10.1007/s00259-026-07768-8
- Primary Topic
- Lymphoma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00