Inter-Observer Reproducibility of [18F]FDG PET/CT Radiomic Features in Primary Breast Carcinoma
Journal of Imaging · 04.07.2026 · 12 (7) · 300
DOI: 10.3390/jimaging12070300 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 04.07.2026. Verfasst von Alexandru Mitoi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Doctoral Program Studies, University of Medicine and Pharmacy "Carol Davila", 050474 Bucharest, Romania. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Radiomic feature stability is a necessary condition for clinical translation, yet the impact of inter-observer segmentation variability remains insufficiently characterized for [18F]FDG PET/CT in breast carcinoma. We evaluated the inter-observer reproducibility of 107 original radiomic features extracted from [18F]FDG PET/CT images of 42 patients with biopsy-proven, treatment-naive primary breast carcinoma, using an IBSI-aligned PyRadiomics workflow. Two nuclear medicine physicians independently segmented each tumor using semi-automatic Otsu thresholding to generate an initial tumor mask, followed by manual correction. Reproducibility was quantified using ICC(A,1) with bootstrap-derived 95% confidence intervals. A two-stage reproducibility and redundancy-based feature reduction strategy, combining an ICC threshold with Spearman correlation-based redundancy removal, was applied across nine threshold combinations, and features were classified into three pre-specified stability categories. The segmentation agreement was good, with a mean Dice coefficient of 0.847. Most features showed excellent reproducibility (81/107, 75.7% with ICC ≥ 0.90; median ICC 0.972), whereas shape features based on maximum lesion extension showed poor reproducibility (ICC 0.10–0.25). The reduction strategy resulted in 19 stable non-redundant features, with eight retained across all threshold combinations; 79 features (73.8%) met high-stability criteria. These results and the proposed stability classification framework provide a methodological basis for future predictive PET radiomics studies in breast carcinoma.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Doctoral Program Studies, University of Medicine and Pharmacy "Carol Davila", 050474 Bucharest, Romania.
- Department of Nuclear Medicine, Carol Davila University of Medicine and Pharmacy, 010825 Bucharest, Romania.
- Clinic of Nuclear Medicine, University Emergency Central Military Hospital "Dr. Carol Davila", 010825 Bucharest, Romania.
- Department of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy "Carol Davila", 050474 Bucharest, Romania.
- Clinical Laboratory of Radiology and Medical Imaging, Clinical Hospital "Prof. Dr. Theodor Burghele", 050664 Bucharest, Romania.
- Department of Diabetes and Nutrition, Medicine Faculty, Titu Maiorescu University, 031593 Bucharest, Romania.
ORCID-Profile: Alexandru Mitoi, Raluca Mititelu, Cosmin Medar, Constantin Ciprian, Ioan-Nicolae Mateș
Zitieren
APA
Mitoi, A., Mititelu, R., Medar, C., Bolocan, V. O., Ciprian, C., & Mateș, I. N. (2026). Inter-Observer Reproducibility of [18F]FDG PET/CT Radiomic Features in Primary Breast Carcinoma. Journal of Imaging, 12(7), 300. https://doi.org/10.3390/jimaging12070300
Vancouver
Mitoi A, Mititelu R, Medar C, Bolocan VO, Ciprian C, Mateș IN. Inter-Observer Reproducibility of [18F]FDG PET/CT Radiomic Features in Primary Breast Carcinoma. Journal of Imaging. 2026;12(7):300. doi:10.3390/jimaging12070300
BibTeX
@article{Mitoi2026,
author = {Mitoi, Alexandru and Mititelu, Raluca and Medar, Cosmin and Bolocan, Vlad Octavian and Ciprian, Constantin and Mateș, Ioan-Nicolae},
title = {Inter-Observer Reproducibility of [18F]FDG PET/CT Radiomic Features in Primary Breast Carcinoma},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {300},
doi = {10.3390/jimaging12070300}
}
EUVIMED