Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis

Abstract Background The role of radiomics and abdominal fat analysis in the survival prediction of pancreatic ductal adenocarcinoma (PDAC) has attracted attention. This study aims to develop a preoperative model for predicting early recurrence (ER) in patients pathologically confirmed PDAC, combinin...

Full description

Saved in:
Bibliographic Details
Main Authors: Suo Yu Yan, Fang Ming Chen, Bang Jun Guo, Su Hu, Li Lin, Yi Wen Yang, Xin Yu Jiang, Hui Yao, Chun Hong Hu, Yun Yan Su
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01773-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389141108719616
author Suo Yu Yan
Fang Ming Chen
Bang Jun Guo
Su Hu
Li Lin
Yi Wen Yang
Xin Yu Jiang
Hui Yao
Chun Hong Hu
Yun Yan Su
author_facet Suo Yu Yan
Fang Ming Chen
Bang Jun Guo
Su Hu
Li Lin
Yi Wen Yang
Xin Yu Jiang
Hui Yao
Chun Hong Hu
Yun Yan Su
author_sort Suo Yu Yan
collection DOAJ
description Abstract Background The role of radiomics and abdominal fat analysis in the survival prediction of pancreatic ductal adenocarcinoma (PDAC) has attracted attention. This study aims to develop a preoperative model for predicting early recurrence (ER) in patients pathologically confirmed PDAC, combining radiomic and abdominal fat analysis. Methods A total of 177 patients (Hospital A) were retrospectively analyzed and allocated to the training cohort (n = 124) and internal validation cohort (n = 53). Another 71 patients (Hospital B) group formed the geographic external validation cohort. The threshold of ER was set at 6 months after surgery, and the primary endpoint was to determine the best model to predict ER of PDAC patients. A radiomics model for predicting ER was constructed by the least absolute shrinkage and selection operator Cox regression. Univariate and multivariate Cox regression analyses were used to build a combined model based on radiomics, fat quantitation, and clinical features. The combined model’s performance was assessed using the Harrell concordance index (C-index). Based on the nomogram score, patients were stratified into high-risk and low-risk groups, and survival analysis of different risk groups was performed using the Kaplan-Meier (KM) method. All patients were divided into four subgroups according to recurrence patterns: local recurrence subgroup, distant recurrence subgroup, “local + distant” recurrence subgroup, and “multiple” recurrence subgroup. The predictive efficacy of the combined model was calculated in different subgroups. Results Radiomics scores (P < 0.001), CA19-9 (P = 0.009), and visceral to subcutaneous fat volume ratio(P = 0.009) were selected for the combined model. Compared to clinical and radiomics models, the combined model exhibited the best prediction performance. C indexes of the training cohort, internal validation cohort, and external validation cohort were 0.778 (0.711,0.845), 0.746 (0.632,0.860), and 0.712 (0.612,0.812) respectively, showing the improvement over the clinical model (without radiomics and fat quantitation features) in the internal validation and external validation sets (DeLong test: P = 0.027, P = 0.079). KM analysis showed significant differences between risk groups (all P < 0.05). The combined model also achieved robust performance in different subgroups of recurrence patterns. Conclusion The combined model effectively predicted the probability of ER in PDAC patients and may provide an emerging tool to preoperatively guide personalized treatment. Clinical trial number Not applicable
format Article
id doaj-art-c1a32e9dbd354d90b48dc9a850cc084d
institution Kabale University
issn 1471-2342
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-c1a32e9dbd354d90b48dc9a850cc084d2025-08-20T03:42:02ZengBMCBMC Medical Imaging1471-23422025-07-0125111210.1186/s12880-025-01773-3Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysisSuo Yu Yan0Fang Ming Chen1Bang Jun Guo2Su Hu3Li Lin4Yi Wen Yang5Xin Yu Jiang6Hui Yao7Chun Hong Hu8Yun Yan Su9Department of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, Jiangnan University Medical CenterDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityAbstract Background The role of radiomics and abdominal fat analysis in the survival prediction of pancreatic ductal adenocarcinoma (PDAC) has attracted attention. This study aims to develop a preoperative model for predicting early recurrence (ER) in patients pathologically confirmed PDAC, combining radiomic and abdominal fat analysis. Methods A total of 177 patients (Hospital A) were retrospectively analyzed and allocated to the training cohort (n = 124) and internal validation cohort (n = 53). Another 71 patients (Hospital B) group formed the geographic external validation cohort. The threshold of ER was set at 6 months after surgery, and the primary endpoint was to determine the best model to predict ER of PDAC patients. A radiomics model for predicting ER was constructed by the least absolute shrinkage and selection operator Cox regression. Univariate and multivariate Cox regression analyses were used to build a combined model based on radiomics, fat quantitation, and clinical features. The combined model’s performance was assessed using the Harrell concordance index (C-index). Based on the nomogram score, patients were stratified into high-risk and low-risk groups, and survival analysis of different risk groups was performed using the Kaplan-Meier (KM) method. All patients were divided into four subgroups according to recurrence patterns: local recurrence subgroup, distant recurrence subgroup, “local + distant” recurrence subgroup, and “multiple” recurrence subgroup. The predictive efficacy of the combined model was calculated in different subgroups. Results Radiomics scores (P < 0.001), CA19-9 (P = 0.009), and visceral to subcutaneous fat volume ratio(P = 0.009) were selected for the combined model. Compared to clinical and radiomics models, the combined model exhibited the best prediction performance. C indexes of the training cohort, internal validation cohort, and external validation cohort were 0.778 (0.711,0.845), 0.746 (0.632,0.860), and 0.712 (0.612,0.812) respectively, showing the improvement over the clinical model (without radiomics and fat quantitation features) in the internal validation and external validation sets (DeLong test: P = 0.027, P = 0.079). KM analysis showed significant differences between risk groups (all P < 0.05). The combined model also achieved robust performance in different subgroups of recurrence patterns. Conclusion The combined model effectively predicted the probability of ER in PDAC patients and may provide an emerging tool to preoperatively guide personalized treatment. Clinical trial number Not applicablehttps://doi.org/10.1186/s12880-025-01773-3Pancreatic cancerComputed tomographyRecurrenceAbdominal fatRadiomics
spellingShingle Suo Yu Yan
Fang Ming Chen
Bang Jun Guo
Su Hu
Li Lin
Yi Wen Yang
Xin Yu Jiang
Hui Yao
Chun Hong Hu
Yun Yan Su
Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
BMC Medical Imaging
Pancreatic cancer
Computed tomography
Recurrence
Abdominal fat
Radiomics
title Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
title_full Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
title_fullStr Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
title_full_unstemmed Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
title_short Preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma: combining radiomics and abdominal fat analysis
title_sort preoperative prediction for early recurrence in patients with pancreatic ductal adenocarcinoma combining radiomics and abdominal fat analysis
topic Pancreatic cancer
Computed tomography
Recurrence
Abdominal fat
Radiomics
url https://doi.org/10.1186/s12880-025-01773-3
work_keys_str_mv AT suoyuyan preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT fangmingchen preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT bangjunguo preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT suhu preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT lilin preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT yiwenyang preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT xinyujiang preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT huiyao preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT chunhonghu preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis
AT yunyansu preoperativepredictionforearlyrecurrenceinpatientswithpancreaticductaladenocarcinomacombiningradiomicsandabdominalfatanalysis