Clinical application of combined CT radiomics and clinical features in survival prediction for pancreatic ductal adenocarcinoma patients

LI Ke; CHEN Jiafei; YANG Jing; CHEN Wei

doi:10.16016/j.2097-0927.202503004

您当前的位置：

首页 >

文章列表页 >

Clinical application of combined CT radiomics and clinical features in survival prediction for pancreatic ductal adenocarcinoma patients

Monographic Reports | 更新时间：2025-07-25

- Clinical application of combined CT radiomics and clinical features in survival prediction for pancreatic ductal adenocarcinoma patients
- Journal of Army Medical University Vol. 47, Issue 14, Pages: 1587-1594(2025)
- 作者机构：
  
  1.陆军军医大学（第三军医大学）：，第一附属医院放射科，重庆，四川乐山
  2.陆军军医大学（第三军医大学）：，武警四川总队医院医学影像科，四川乐山
- 作者简介：
  
  CHEN Wei， E-mail： landcw@tmmu.edu.cn
- 基金信息：
  
  the Key Joint Medical Research Project of Chongqing Science and Technology Commission and Chongqing Health Commission(2023ZDXM008)
- DOI：10.16016/j.2097-0927.202503004
  CLC： R730.7;R735.9;R814.42
- Received：03 March 2025，
  
  Revised：02 April 2025，
  
  Published：30 July 2025
- 稿件说明：
移动端阅览
李可，陈家飞，杨靖，等.CT影像组学联合临床特征对胰腺导管腺癌患者生存预测的应用研究［J］.陆军军医大学学报，2025，47（14）：1587-1594.DOI：10.16016/j.2097-0927.202503004.

LI K，CHEN J F，YANG J，et al.Clinical application of combined CT radiomics and clinical features in survival prediction for pancreatic ductal adenocarcinoma patients［J］.J Army Med Univ，2025，47（14）：1587-1594.DOI：10.16016/j.2097-0927.202503004.
李可，陈家飞，杨靖，等.CT影像组学联合临床特征对胰腺导管腺癌患者生存预测的应用研究［J］.陆军军医大学学报，2025，47（14）：1587-1594.DOI：10.16016/j.2097-0927.202503004. DOI：

LI K，CHEN J F，YANG J，et al.Clinical application of combined CT radiomics and clinical features in survival prediction for pancreatic ductal adenocarcinoma patients［J］.J Army Med Univ，2025，47（14）：1587-1594.DOI：10.16016/j.2097-0927.202503004. DOI：

摘要

目的

构建基于CT影像组学的胰腺导管腺癌（pancreatic ductal adenocarcinoma，PDAC）预后预测模型，为个体化治疗决策提供依据。

方法

回顾性纳入2020年1月至2023年12月在陆军军医大学第一附属医院就诊的118例PDAC患者，按7∶3比例将患者分为训练组（

=83）和验证组（

=35）。采用ITK-SNAP软件对术前增强CT动脉期图像进行3D分割，通过pyradiomics提取影像组学特征。经ICC分析（

0.85）筛选高重复性特征，采用LASSO回归确定核心特征并构建Rad-score。基于Cox回归分析构建影像组学模型及联合临床特征的综合模型，用于预测PDAC患者总生存时间。采用受试者工作特征（ROC）曲线及校准曲线对模型进行评价。

结果

共提取1 453个影像组学特征，经筛选最终确定7个核心特征构建Rad-score。基于Rad-score构建的影像组学预测模型在训练组和验证组的1年生存预测AUC分别为0.796（95%

：0.702~0.890）和0.744（95%

：0.589~0.899）。联合临床特征的综合预测模型分别为0.906（95%

：0.842~0.970）和0.872（95%

：0.753~0.992）。校准曲线显示模型具有良好的预测准确性

。

结论

基于CT影像特征构建的影像组学模型和联合临床特征的综合预测模型具有良好的生存时间预测效能。

Abstract

Objective‍　‍To develop a CT radiomics-based prediction model for prognosis of pancreatic ductal adenocarcinoma (PDAC) in order to provide evidence for individualized treatment decisions.

Methods

A retrospective study was carried on 118 PDAC patients admitted in the First Affiliated Hospital of Army Medical University between January 2020 and December 2023. They were assigned into a training group (

=83) and a validation group (

=35) at a 7∶3 ratio. ITK-SNAP software was used to perform 3-D segmentation on the preoperatively enhanced arterial phase CT images

and radiomic features were extracted using pyradiomics. High-reproducibility features were selected through ICC analysis (

0.85)

and core features were determined using LASSO regression to construct the Rad-score. Cox regression analysis was employed to develop both a radiomics model and a model integrating radiomic and clinical features for predicting overall survival in PDAC patients. Receiver operating characteristic (ROC) curves and calibration curves were plotted to evaluate the prognostic models for survival prediction. ‍

Results

From 1 453 extracted radiomic features

7 core features were finally selected to construct the Rad-score. The radiomics prediction model based on the Rad-score achieved an AUC value of 0.796 (95%

: 0.702~0.890) and 0.744 (95%

: 0.589~0.899) for 1-year survival prediction in the training and validation groups

respectively. The integrated model combining 2 types of features together demonstrated improved performance with an AUC value of 0.906 (95%

: 0.842~0.970) and 0.872 (95%

: 0.753~0.992) in the 2 groups. Calibration curve analysis indicated good prediction accuracy for both models. ‍

Conclusion

Both the CT radiomics-based model and the integrated model incorporating clinical features demonstrate good predictive performance for survival outcomes.

关键词

Keywords

references

MANSOURI S ， DANIEL L ， AMHIS N ， et al . Perioperative oncolytic virotherapy to counteract surgery-induced immunosuppression and improve outcomes in pancreatic ductal adenocarcinoma ［J］. Front Oncol ， 2023 ， 13 ： 1071751 . DOI： 10.3389/fonc.2023.1071751 http://dx.doi.org/10.3389/fonc.2023.1071751 .

MILELLA M ， BASSI C ， BOGGI U ， et al . Evolving pancreatic cancer treatment： From diagnosis to healthcare management ［J］. Crit Rev Oncol Hematol ， 2022 ， 169 ： 103571 . DOI： 10.1016/j.critrevonc.2021.103571 http://dx.doi.org/10.1016/j.critrevonc.2021.103571 .

ZHU B ， WU X M ， GUO T Y ， et al . Epidemiological characteristics of pancreatic cancer in China from 1990 to 2019 ［J］. Cancer Control ， 2021 ， 28 ： 10732748211051536 . DOI： 10.1177/10732748211051536 http://dx.doi.org/10.1177/10732748211051536 .

张旭东，刘浩昂，王志浩，等 . Smad3通过p38/MAPK信号通路调控细胞自噬及凋亡促进胰腺癌进程［J］. 陆军军医大学学报， 2022 ， 44 （ 19 ）： 1968 - 1978 . DOI： 10.16016/j.2097-0927.202205059 http://dx.doi.org/10.16016/j.2097-0927.202205059 .

ZHANG X D ， LIU H A ， WANG Z H ， et al . Smad3 promotes pancreatic cancer progression by regulating autophagy and apoptosis through p38/MAPK signaling pathway ［J］. J Army Med Univ ， 2022 ， 44 （ 19 ）： 1968 - 1978 . DOI： 10.16016/j.2097-0927.202205059 http://dx.doi.org/10.16016/j.2097-0927.202205059 .

DENG Q L ， DONG S ， WANG L ， et al . Development and validation of a nomogram for predicting survival in patients with advanced pancreatic ductal adenocarcinoma ［J］. Sci Rep ， 2017 ， 7 （ 1 ）： 11524 . DOI： 10.1038/s41598-017-11227-8 http://dx.doi.org/10.1038/s41598-017-11227-8 .

OKANO K ， SUZUKI Y . Strategies for early detection of resectable pancreatic cancer ［J］. World J Gastroenterol ， 2014 ， 20 （ 32 ）： 11230 - 11240 . DOI： 10.3748/wjg.v20.i32.11230 http://dx.doi.org/10.3748/wjg.v20.i32.11230 .

WAGNER M W ， BILBILY A ， BEHESHTI M ， et al . Artificial intelligence and radiomics in pediatric molecular imaging ［J］. Methods ， 2021 ， 188 ： 37 - 43 . DOI： 10.1016/j.ymeth.2020.06.008 http://dx.doi.org/10.1016/j.ymeth.2020.06.008 .

JI G W ， WANG K ， XIA Y X ， et al . Application and challenge of radiomics technique in the era of precision medicine for hepatobiliary disease ［J］. Chin J Surg ， 2020 ， 58 （ 10 ）： 749 - 753 . DOI： 10.3760/cma.j.cn112139-20200605-00439 http://dx.doi.org/10.3760/cma.j.cn112139-20200605-00439 .

BIOLETTO F ， PRENCIPE N ， BERTON A M ， et al . Radiomic analysis in pituitary tumors： current knowledge and future perspectives ［J］. J Clin Med ， 2024 ， 13 （ 2 ）： 336 . DOI： 10.3390/jcm13020336 http://dx.doi.org/10.3390/jcm13020336 .

AKSHATHA C R ， HALANAIK D ， NACHIAPPA GANESH R ， et al . Assessment of novel prognostic biomarkers to predict pathological complete response in patients with non-metastatic triple-negative breast cancer using a window of opportunity design ［J］. Ther Adv Med Oncol ， 2024 ， 16 ： 17588359241248329 . DOI： 10.1177/17588359241248329 http://dx.doi.org/10.1177/17588359241248329 .

ELOYAN A ， YUE M S ， KHACHATRYAN D . Tumor heterogeneity estimation for radiomics in cancer ［J］. Stat Med ， 2020 ， 39 （ 30 ）： 4704 - 4723 . DOI： 10.1002/sim.8749 http://dx.doi.org/10.1002/sim.8749 .

PREUSS K ， THACH N ， LIANG X Y ， et al . Using quantitative imaging for personalized medicine in pancreatic cancer： a review of radiomics and deep learning applications ［J］. Cancers （Basel）， 2022 ， 14 （ 7 ）： 1654 . DOI： 10.3390/cancers14071654 http://dx.doi.org/10.3390/cancers14071654 .

MARTI-BONMATI L ， CERDÁ-ALBERICH L ， PÉREZ-GIRBÉS A ， et al . Pancreatic cancer， radiomics and artificial intelligence ［J］. Br J Radiol ， 2022 ， 95 （ 1137 ）： 20220072 . DOI： 10.1259/bjr.20220072 http://dx.doi.org/10.1259/bjr.20220072 .

YAO L H ， ZHANG Z Y ， KELES E ， et al . A review of deep learning and radiomics approaches for pancreatic cancer diagnosis from medical imaging ［J］. Curr Opin Gastroenterol ， 2023 ， 39 （ 5 ）： 436 - 447 . DOI： 10.1097/MOG.0000000000000966 http://dx.doi.org/10.1097/MOG.0000000000000966 .

CASÀ C ， PIRAS A ， D’AVIERO A ， et al . The impact of radiomics in diagnosis and staging of pancreatic cancer ［J］. Ther Adv Gastrointest Endosc ， 2022 ， 15 ： 26317745221081596 . DOI： 10.1177/26317745221081596 http://dx.doi.org/10.1177/26317745221081596 .

YUN G B ， KIM Y H ， LEE Y J ， et al . Tumor heterogeneity of pancreas head cancer assessed by CT texture analysis： association with survival outcomes after curative resection ［J］. Sci Rep ， 2018 ， 8 （ 1 ）： 7226 . DOI： 10.1038/s41598-018-25627-x http://dx.doi.org/10.1038/s41598-018-25627-x .

SALINAS-MIRANDA E ， KHALVATI F ， NAMDAR K ， et al . Validation of prognostic radiomic features from resectable pancreatic ductal adenocarcinoma in patients with advanced disease undergoing chemotherapy ［J］. Can Assoc Radiol J ， 2021 ， 72 （ 4 ）： 605 - 613 . DOI： 10.1177/0846537120968782 http://dx.doi.org/10.1177/0846537120968782 .

YAMASHITA R ， PERRIN T ， CHAKRABORTY J ， et al . Radiomic feature reproducibility in contrast-enhanced CT of the pancreas is affected by variabilities in scan parameters and manual segmentation ［J］. Eur Radiol ， 2020 ， 30 （ 1 ）： 195 - 205 . DOI： 10.1007/s00330-019-06381-8 http://dx.doi.org/10.1007/s00330-019-06381-8 .

YAO J W ， SHI Y ， CAO K ， et al . DeepPrognosis： Preoperative prediction of pancreatic cancer survival and surgical margin via comprehensive understanding of dynamic contrast-enhanced CT imaging and tumor-vascular contact parsing ［J］. Med Image Anal ， 2021 ， 73 ： 102150 . DOI： 10.1016/j.media.2021.102150 http://dx.doi.org/10.1016/j.media.2021.102150 .

XU W ， LIU Y ， LU Z ， et al . A new endoscopic ultrasonography image processing method to evaluate the prognosis for pancreatic cancer treated with interstitial brachytherapy ［J］. World J Gastroenterol ， 2013 ， 19 （ 38 ）： 6479 - 6484 . DOI： 10.3748/wjg.v19.i38.6479 http://dx.doi.org/10.3748/wjg.v19.i38.6479 .

KIM N ， HAN I W ， RYU Y ， et al . Predictive nomogram for early recurrence after pancreatectomy in resectable pancreatic cancer： risk classification using preoperative clinicopathologic factors ［J］. Cancers （Basel）， 2020 ， 12 （ 1 ）： 137 . DOI： 10.3390/cancers12010137 http://dx.doi.org/10.3390/cancers12010137 .

HA S ， CHOI H ， PAENG J C ， et al . Radiomics in oncological PET/CT： a methodological overview ［J］. Nucl Med Mol Imaging ， 2019 ， 53 （ 1 ）： 14 - 29 . DOI： 10.1007/s13139-019-00571-4 http://dx.doi.org/10.1007/s13139-019-00571-4 .

AVANZO M ， WEI L S ， STANCANELLO J ， et al . Machine and deep learning methods for radiomics ［J］. Med Phys ， 2020 ， 47 （ 5 ）： e185 - e202 . DOI： 10.1002/mp.13678 http://dx.doi.org/10.1002/mp.13678 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Value of MRI radiomics based on intratumoral and peritumoral heterogeneity in predicting spatial patterns of locally recurrent high-grade gliomas

Construction and validation of a prediction model for central lymph node metastasis of papillary thyroid carcinoma based on contrast-enhanced venous phase CT radiomics

基于CT影像组学特征联合临床特征预测非小细胞肺癌EGFR突变状态

Development of a prediction model for chemotherapy and immunotherapy response in esophageal squamous cell carcinoma patients using machine learning algorithms

Stratified differentiation of 3 common pulmonary nodules with CT radiomics

Related Author

WANG Shunan

WU Yi

YI Liang

LI Xiaoguang

XIE Huan

LI Xuan

ZHAO Mimi

ZENG Linlan

Related Institution

Department of Digital Medicine, Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）

Department of Neurosurgery， Army Medical Center of PLA/Daping Hospital of Third Military Medical University， Chongqing, Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）

Department of Radiology， Chongqing Clinical Research Centre of Imaging and Nuclear Medicine, Faculty of Biomedical Engineering and Imaging Medicine， Army Medical University （Third Military Medical University）

Hospital of PLA Army

Department of Radiology， No. 9

⁰