Deep Learning Model for Volume Measurement of the Remnant Pancreas After Pancreaticoduodenectomy and Distal Pancreatectomy

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.

• Publication year

  2025

• Venue

  Diagnostics

• Publication date

  2025-11-01

• Fields of study

  Medicine, Engineering

• Identifiers
  DOI 10.3390/diagnostics15222834PMID 41300859PMCID 12651614
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers

  2024cited by this paper
• Pancreatic volume and endocrine function changes following pancreaticoduodenectomy for peri-ampullary neoplasms: A retrospective single-center study utilizing pancreas volumetry

  2024cited by this paper
• Swin Unet3D: a three-dimensional medical image segmentation network combining vision transformer and convolution

  2023cited by this paper
• High-Resolution Boundary Detection for Medical Image Segmentation with Piece-Wise Two-Sample T-Test Augmented Loss

  2022cited by this paper
• 3D U-Net: A voxel-based method in binding site prediction of protein structure

  2021cited by this paper
• Automated pancreas segmentation and volumetry using deep neural network on computed tomography

  2021influential reference
• Multi-scale U-like network with attention mechanism for automatic pancreas segmentation

  2021influential reference
• A review of deep learning based methods for medical image multi-organ segmentation.

  2021cited by this paper
• Atrophy of remnant pancreas after pancreatoduodenectomy: Risk factors and effects on quality of life, nutritional status, and pancreatic function

  2021cited by this paper
• Central Pancreatectomy Versus Distal Pancreatectomy and Pancreaticoduodenectomy for Benign and Low-Grade Malignant Neoplasms: A Retrospective and Propensity Score-Matched Study with Long-Term Functional Outcomes and Pancreas Volumetry

  2020cited by this paper
• Distribution and Characteristics of Pancreatic Volume Using Computed Tomography Volumetry

  2020cited by this paper
• Application of the residue number system to reduce hardware costs of the convolutional neural network implementation

  2020cited by this paper
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

  2019cited by this paper
• Clinicopathologic analysis of intraductal papillary neoplasm of bile duct: Korean multicenter cohort study.

  2019cited by this paper
• Comparison of long-term clinical outcomes of external and internal pancreatic stents in pancreaticoduodenectomy: randomized controlled study.

  2019influential reference
• Automated pancreas segmentation from computed tomography and magnetic resonance images: A systematic review

  2019cited by this paper
• Feature Enhancement in Medical Ultrasound Videos Using Contrast-Limited Adaptive Histogram Equalization

  2019cited by this paper
• Brain Tumor Segmentation and Survival Prediction Using 3D Attention UNet

  2019cited by this paper
• U-Net: deep learning for cell counting, detection, and morphometry

  2018cited by this paper
• Blood vessel segmentation algorithms - Review of methods, datasets and evaluation metrics

  2018cited by this paper
• Progression of Pancreatic Branch Duct Intraductal Papillary Mucinous Neoplasm Associates With Cyst Size.

  2018cited by this paper
• Recent treatment patterns and survival outcomes in pancreatic cancer according to clinical stage based on single-center large-cohort data

  2018cited by this paper
• Multi‐atlas pancreas segmentation: Atlas selection based on vessel structure

  2017cited by this paper
• Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks

  2017influential reference
• Smart detection on abnormal breasts in digital mammography based on contrast-limited adaptive histogram equalization and chaotic adaptive real-coded biogeography-based optimization

  2016cited by this paper
• Fast reconstruction of low dose proton CT by sinogram interpolation

  2016cited by this paper
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

  2016cited by this paper
• Incidental pancreatic cystic neoplasms in an asymptomatic healthy population of 21,745 individuals

  2016influential reference
• Detection, Segmentation and Recognition of Face and its Features Using Neural Network

  2016cited by this paper
• U-Net: Convolutional Networks for Biomedical Image Segmentation

  2015cited by this paper
• Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation

  2015cited by this paper
• A Fast Enhancement/Thresholding Based Blood Vessel Segmentation for Retinal Image Using Contrast Limited Adaptive Histogram Equalization

  2014cited by this paper
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

  2014cited by this paper
• Osteoarthritis Classification Using Self Organizing Map Based on Gabor Kernel and Contrast-Limited Adaptive Histogram Equalization

  2013cited by this paper
• Image segmentation evaluation: A survey of unsupervised methods

  2008cited by this paper
• Comparative study of diverse model building strategies for 3D-ASM segmentation of dynamic gated SPECT data

  2007cited by this paper
• Visualizing with VTK: A Tutorial

  2000cited by this paper

• No citing papers are available for this paper.