EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-supervised multimodal swin UNETR for PET/CT segmentation of diffuse large B-cell lymphoma

Sajad Keshavarz, Elham Saeedzadeh, Hossein Arabi, Elnaz Jenabi-Haghparast, Dariush Sardari

Cancer Treatment and Research Communications · 2026 · 49 · 101369

DOI: 10.1016/j.ctarc.2026.101369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Treatment and Research Communications, 2026. Verfasst von Sajad Keshavarz und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Radiation Engineering, SR.C., Islamic Azad University, Tehran, Iran. Electronic address: sajad.keshavarz@srbiau.ac.ir. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of diffuse large B-cell lymphoma (DLBCL) is critical for reliable PET/CT-based quantification and total metabolic tumor volume (TMTV) estimation. However, most deep learning approaches rely on limited annotated datasets and conventional convolutional architectures, which may restrict generalization and training stability. In this study, we propose a multimodal PET/CT Swin UNETR framework enhanced through large-scale self-supervised pretraining. A total of 717 FDG-PET/CT scans were collected from a single center, including 500 unlabeled volumes used for self-supervised pretraining and 217 expert-annotated cases for supervised learning. The labeled dataset was randomly divided into 174 training cases and an independent held-out test cohort of 43 cases. A standardized preprocessing pipeline with isotropic resampling and voxel harmonization was applied to ensure spatial consistency. The proposed SSL + PET/CT Swin UNETR achieved a Dice score of 0.723 (95% CI: 0.70-0.75), IoU of 0.648, HD of 15.0 mm, and HD95 of 8.8 mm on a held-out internal test set, evaluated supervised baseline models (p < 0.001, Wilcoxon signed-rank test). TMTV regression analysis demonstrated strong correlation with ground-truth measurements (R² = 0.929) with minimal systematic bias in Bland-Altman evaluation. These findings demonstrate the potential of multimodal self-supervised learning to improve automated DLBCL lesion segmentation in PET/CT images and support future research on robust quantitative image analysis.

Schlagwörter

Stichwörter der Autor:innen

18-FDGDLBCLPET/CTSegmentationSwin UNETR

Autor:innen und Institutionen

  • Department of Medical Radiation Engineering, SR.C., Islamic Azad University, Tehran, Iran. Electronic address: sajad.keshavarz@srbiau.ac.ir.
  • Department of Medical Radiation Engineering, SR.C., Islamic Azad University, Tehran, Iran. Electronic address: es.saeedzadeh@iau.ac.ir.
  • Department of Medical Imaging, Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland. Electronic address: Hossein.arabi@unige.ch.
  • Department of Diagnostic Imaging, The Hospital for Sick Children (SickKids), University of Toronto, Toronto, Ontario, Canada. Electronic address: elnaz.jenabihaghparast@sickkids.ca.
  • Department of Medical Radiation Engineering, SR.C., Islamic Azad University, Tehran, Iran. Electronic address: sardari@srbiau.ac.ir.

Zitieren

APA

Keshavarz, S., Saeedzadeh, E., Arabi, H., Jenabi-Haghparast, E., & Sardari, D. (2026). Self-supervised multimodal swin UNETR for PET/CT segmentation of diffuse large B-cell lymphoma. Cancer Treatment and Research Communications, 49, 101369. https://doi.org/10.1016/j.ctarc.2026.101369

Vancouver

Keshavarz S, Saeedzadeh E, Arabi H, Jenabi-Haghparast E, Sardari D. Self-supervised multimodal swin UNETR for PET/CT segmentation of diffuse large B-cell lymphoma. Cancer Treatment and Research Communications. 2026;49:101369. doi:10.1016/j.ctarc.2026.101369

BibTeX
@article{Keshavarz2026,
  author = {Keshavarz, Sajad and Saeedzadeh, Elham and Arabi, Hossein and Jenabi-Haghparast, Elnaz and Sardari, Dariush},
  title = {Self-supervised multimodal swin UNETR for PET/CT segmentation of diffuse large B-cell lymphoma},
  journal = {Cancer Treatment and Research Communications},
  year = {2026},
  volume = {49},
  pages = {101369},
  doi = {10.1016/j.ctarc.2026.101369}
}
Kostenlos starten →