Supervised vs. unsupervised radiomics reproducibility across dose-level variations and partial volume correction methods in total-body PET imaging
Biomedical Signal Processing and Control · 2026-08 · 122 · 110307
DOI: 10.1016/j.bspc.2026.110307 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2026-08. Verfasst von Mohammad Saber Azimi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: School of Medicine, Shanghai Jiao Tong University, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, University of Bern.
Abstract (Originalsprache)
Background and objective : To provide a systematic reproducibility analysis of radiomic features in total-body [ 18 F]-FDG PET imaging, assessing the effects of dose variation, partial volume correction (PVC), and harmonization.
Methods
A dual-center total-body [ 18 F]-FDG PET dataset (n = 170 scans, 85 per center) acquired on the uEXPLORER and Biograph Vision Quadra systems was retrospectively subsampled from list-mode data to simulate four relative count levels (100%, 50%, 10%, 2%). PVC was performed using Richardson–Lucy (RL) and reblurred Van-Cittert (RVC) deconvolution, with non-PVC images serving as reference. Radiomic features (n = 93) were extracted from PET images. ComBat harmonization was applied across centers. Reproducibility was assessed using: (i) intraclass correlation coefficient (ICC), (ii) PCA/UMAP-based drift distances, and (iii) Linear Discriminant Analysis (LDA).
Results
Across-dose ICC showed that > 60% of features fell into the Poor category (ICC 11 at 2%, reflecting strong dose dependence. PVC offered limited benefit: RL slightly outperformed non-PVC, whereas RVC consistently induced the largest drifts (up to 61% higher). ComBat harmonization failed to improve stability and occasionally increased variability (+13% for RL at 50%). LDA confirmed these findings: dose levels showed measurable separability in discriminant space, whereas PVC methods overlapped substantially, and harmonization effects were negligible, with before–after conditions appearing nearly indistinguishable.
Conclusions
Radiomics reproducibility in total-body PET is primarily driven by dose level, with PVC effects being task-dependent and harmonization providing negligible benefit.
Förderung
- School of Medicine, Shanghai Jiao Tong University
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- University of Bern
- Ruijin Hospital
- Shanghai Jiao Tong University
- Ligue Genevoise Contre le Cancer
Zitieren
APA
Azimi, M. S., MahdiMaleki, F., MahdiMaleki, F., Cheraghi, M., Alavi, A., & Zaidi, H. (2026). Supervised vs. unsupervised radiomics reproducibility across dose-level variations and partial volume correction methods in total-body PET imaging. Biomedical Signal Processing and Control, 122, 110307. https://doi.org/10.1016/j.bspc.2026.110307
Vancouver
Azimi MS, MahdiMaleki F, MahdiMaleki F, Cheraghi M, Alavi A, Zaidi H. Supervised vs. unsupervised radiomics reproducibility across dose-level variations and partial volume correction methods in total-body PET imaging. Biomedical Signal Processing and Control. 2026;122:110307. doi:10.1016/j.bspc.2026.110307
BibTeX
@article{Azimi2026,
author = {Azimi, Mohammad Saber and MahdiMaleki, Faezeh and MahdiMaleki, Fatemeh and Cheraghi, Maryam and Alavi, Abass and Zaidi, Habib},
title = {Supervised vs. unsupervised radiomics reproducibility across dose-level variations and partial volume correction methods in total-body PET imaging},
journal = {Biomedical Signal Processing and Control},
year = {2026},
volume = {122},
pages = {110307},
doi = {10.1016/j.bspc.2026.110307}
}
EUVIMED