Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy
Diagnostics · 08.11.2025 · 15 (22) · 2834
DOI: 10.3390/diagnostics15222834 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 08.11.2025. Verfasst von Young Jae Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Gachon Biomedical & Convergence Institute, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Trade, Industry and Energy, Korea Pancreas Surgery Club, Gachon University College of Medicine.
Abstract (Originalsprache)
Background/Objectives: Accurate volumetry of the remnant pancreas after pancreatectomy is crucial for assessing postoperative endocrine and exocrine function but remains challenging due to anatomical variability and complex postoperative morphology. This study aimed to develop and validate a deep learning (DL)-based model for automatic segmentation and volumetry of the remnant pancreas using abdominal CT images.
Methods
A total of 1067 CT scans from 341 patients who underwent pancreaticoduodenectomy and 512 scans from 184 patients who underwent distal pancreatectomy were analyzed. Ground truth masks were manually delineated and verified through multi-expert consensus. Six 3D segmentation models were trained and compared, including four convolution-based U-Net variants (basic, dense, residual, and residual dense) and two transformer-based models (Trans U-Net and Swin U-Net). Model performance was evaluated using five-fold cross-validation with sensitivity, specificity, precision, accuracy, and Dice similarity coefficient.
Results
The Residual Dense U-Net achieved the best performance among convolutional models, with dice similarity coefficient (DSC) values of 0.7655 ± 0.0052 for pancreaticoduodenectomy and 0.8086 ± 0.0091 for distal pancreatectomy. Transformer-based models showed slightly higher DSCs (Swin U-Net: 0.7787 ± 0.0062 and 0.8132 ± 0.0101), with statistically significant but numerically small improvements (p < 0.01).
Conclusions
The proposed DL-based approach enables accurate and reproducible postoperative pancreas segmentation and volumetry. Automated volumetric assessment may support objective evaluation of remnant pancreatic function and provide a foundation for predictive modeling in long-term clinical management after pancreatectomy.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Gachon Biomedical & Convergence Institute, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea.
- Medical Devices R & D Center, Gachon University Gil Medical Center, Incheon 21565, Republic of Korea.
- Department of Surgery, Gachon University Gil Medical Center, Gachon University College of Medicine, Incheon 21565, Republic of Korea.
- Department of Biomedical Engineering, Gachon University Gil Medical Center, Gachon University College of Medicine, Incheon 21565, Republic of Korea.
ORCID-Profile: Young Jae Kim, Juhui Lee, Jaehun Yang, Kwang Gi Kim, Doo-Ho Lee
Förderung
- Ministry of Trade, Industry and Energy
- Korea Pancreas Surgery Club
- Gachon University College of Medicine
- the Technology Innovation Program
- the Ministry of Trade, Industry & Energy (MOTIE, Korea) and by the Clinical Research Supporting Program of the Korea Pancreas Surgery Club
- Gachon University research fund
Zitieren
APA
Kim, Y. J., Lee, J., Park, Y. H., Yang, J., Kim, D., Kim, K. G., & Lee, D. H. (2025). Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy. Diagnostics, 15(22), 2834. https://doi.org/10.3390/diagnostics15222834
Vancouver
Kim YJ, Lee J, Park YH, Yang J, Kim D, Kim KG, et al. Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy. Diagnostics. 2025;15(22):2834. doi:10.3390/diagnostics15222834
BibTeX
@article{Kim2025,
author = {Kim, Young Jae and Lee, Juhui and Park, Yeon-Ho and Yang, Jaehun and Kim, Doojin and Kim, Kwang Gi and Lee, Doo-Ho},
title = {Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {22},
pages = {2834},
doi = {10.3390/diagnostics15222834}
}
EUVIMED