A Comparative Study of 2D and 3D U-Net-Based Architectures for Pancreas and Tumor Segmentation in CT Imaging
Celal Bayar Üniversitesi Fen Bilimleri Dergisi · 30.06.2026 · 22 (2) · 309-319
DOI: 10.18466/cbayarfbe.1730380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Celal Bayar Üniversitesi Fen Bilimleri Dergisi, online erschienen am 30.06.2026. Verfasst von İbrahim Şen und 7 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: AKGUN Computer Incorporated Company.
Abstract (Originalsprache)
Pancreatic cancer ranks among the deadliest forms of cancer, largely due to its asymptomatic progression, late-stage diagnosis, and the pancreas’s deep-seated and anatomically complex location within the abdominal cavity. These factors collectively prevent early detection, which is critical for improving patient outcomes. Deep learning-based segmentation models, particularly those based on the U-Net architecture, have demonstrated strong potential for the automatic identification of pancreas and pancreatic tumors in computed tomography (CT) images. This study presents a comparative analysis of 2D and 3D U-Net architectures for the segmentation of the pancreas and its tumors. The results show that the 3D Res-U-Net achieved the best performance, with a Dice score of 0.81 for pancreas segmentation and 0.51 for tumor segmentation, outperforming both the 2D U-Net and the 3D U-Net. Additionally, inference time analysis for real-time clinical settings showed that the 2D U-Net enables the fastest predictions, whereas the 3D U-Net and 3D Res-U-Net require significantly higher computation, underscoring key trade-offs for clinical deployment. These findings offer valuable insights into model selection and optimization strategies for real-world clinical applications. The findings underscore the feasibility of developing efficient deep learning-based systems to support early diagnosis and personalized treatment planning for pancreatic cancer.
Förderung
- AKGUN Computer Incorporated Company
Zitieren
APA
Şen, İ., Çelikten, A., Bingöl, E., Demir, M. K., Akpulat, A., Demirel, S., Budak, A., & Karataş, H. (2026). A Comparative Study of 2D and 3D U-Net-Based Architectures for Pancreas and Tumor Segmentation in CT Imaging. Celal Bayar Üniversitesi Fen Bilimleri Dergisi, 22(2), 309-319. https://doi.org/10.18466/cbayarfbe.1730380
Vancouver
Şen İ, Çelikten A, Bingöl E, Demir MK, Akpulat A, Demirel S, et al. A Comparative Study of 2D and 3D U-Net-Based Architectures for Pancreas and Tumor Segmentation in CT Imaging. Celal Bayar Üniversitesi Fen Bilimleri Dergisi. 2026;22(2):309-319. doi:10.18466/cbayarfbe.1730380
BibTeX
@article{en2026,
author = {Şen, İbrahim and Çelikten, Azer and Bingöl, Ece and Demir, Muhammed Kerem and Akpulat, Andac and Demirel, Semih and Budak, Abdulkadir and Karataş, Hakan},
title = {A Comparative Study of 2D and 3D U-Net-Based Architectures for Pancreas and Tumor Segmentation in CT Imaging},
journal = {Celal Bayar Üniversitesi Fen Bilimleri Dergisi},
year = {2026},
volume = {22},
number = {2},
pages = {309--319},
doi = {10.18466/cbayarfbe.1730380}
}
EUVIMED