基于<sup>18</sup>F-FDG PET/CT的Delta影像组学逻辑回归模型预测局部晚期胰腺导管腺癌患者新辅助治疗术后进展-东南大学学报医学版

基于¹⁸F-FDG PET/CT的Delta影像组学逻辑回归模型预测局部晚期胰腺导管腺癌患者新辅助治疗术后进展

单位：1. 南京中医药大学鼓楼临床医学院, 江苏南京 210008;
2. 南京鼓楼医院核医学科, 江苏南京 210008;
3. 南京鼓楼医院肿瘤科, 江苏南京 210008;
4. 南京鼓楼医院胰腺与代谢外科, 江苏南京 210008

分类号：R735.9

出版年·卷·期（页码）：2026·45·第一期（44-50）

摘要：

目的:探索基于¹⁸F-FDG PET/CT的Delta影像组学特征在预测局部晚期胰腺导管腺癌(LAPC)患者接受新辅助治疗(NAT)并手术切除后疾病进展(PD)中的价值。方法:回顾性选取2022年3月至2024年7月在南京鼓楼医院接受NAT并成功手术切除病灶的33例LAPC患者,收集其基线资料和术前的PET/CT影像资料及临床特征,根据是否进展分为PD组(n=13)和non-PD组(n=20),由专业核医学科医师勾画感兴趣区(ROI)并提取影像组学特征,基于筛选出的5个delta影像组学特征采用Logistic回归模型建立delta影像组学模型。结果:患者临床特征和传统PET/CT代谢参数与PD无显著相关性(P>0.05)。delta影像组学模型有较好的预测能力,AUC为0.94(95%CI:0.86~1.00),表现出较高的敏感度(76.92%)与特异度(95.00%)。决策曲线分析(DCA)显示该预测模型预测价值较高,具有一定的临床意义。结论:基于¹⁸F-FDG PET/CT的Delta影像组学模型可有效预测LAPC术后疾病进展,为术后风险分层和个体化管理提供重要依据。

Objective: To investigate the value of ¹⁸F-FDG PET/CT-based delta radiomics features in predicting disease progression(PD) in patients with locally advanced pancreatic ductal adenocarcinoma(LAPC) who underwent neoadjuvant therapy(NAT) followed by surgical resection. Methods: This retrospective study included 33 patients with LAPC who received NAT and subsequently underwent successful surgical resection at Nanjing Drum Tower Hospital between March 2022 and July 2024. Baseline clinical data and preoperative PET/CT imaging data and clinical characteristics were collected. Patients were divided into a PD group(n=13) and a non-PD(n=20) group according to postoperative disease progression status. Regions of interest(ROIs) were manually delineated by experienced nuclear medicine physicians, and radiomics features were extracted. Five selected delta radiomics features were used to construct a delta radiomics model based on Logistic regression. Results: No significant associations were observed between clinical characteristics or conventional PET/CT metabolic parameters and PD(P>0.05). The delta radiomics model demonstrated strong predictive performance, with an AUC of 0.94(95%CI: 0.86-1.00), achieving a sensitivity of 76.92% and specificity of 95.00%. Decision curve analysis(DCA) indicated a high net clinical benefit, suggesting favorable clinical utility of the model. Conclusion: The ¹⁸F-FDG PET/CT-based delta radiomics model can effectively predict postoperative disease progression in patients with LAPC, providing valuable support for postoperative risk stratification and individualized patient management.

参考文献：

[1] SIEGEL R L,GIAQUINTO A N,JEMAL A.Cancer statistics,2024[J].CA Cancer J Clin,2024,74(1):12-49.
[2] ESHMUMINOV D,AMINJONOV B,PALM R F,et al.FOLFIRINOX or gemcitabine-based chemotherapy for borderline resectable and locally advanced pancreatic cancer:a multi-institutional,patient-level,meta-analysis and systematic review[J].Ann Surg Oncol,2023,30(7):4417-4428.
[3] GHANEH P,PALMER D,CICCONI S,et al.Immediate surgery compared with short-course neoadjuvant gemcitabine plus capecitabine,FOLFIRINOX,or chemoradiotherapy in patients with borderline resectable pancreatic cancer(ESPAC5):a four-arm,multicentre,randomised,phase 2 trial[J].Lancet Gastroenterol Hepatol,2023,8(2):157-168.
[4] DU J,LU C,MAO L,et al.PD-1 blockade plus chemoradiotherapy as preoperative therapy for patients with BRPC/LAPC:a biomolecular exploratory,phase II trial[J].Cell Rep Med,2023,4(3):100972.
[5] CHEN Z,LV Y,LI H,et al.Meta-analysis of FOLFIRINOX-based neoadjuvant therapy for locally advanced pancreatic cancer[J].Medicine(Baltimore),2021,100(3):e24068.
[6] LIU S,DU S,GAO S,et al.A delta-radiomic lymph node model using dynamic contrast enhanced MRI for the early prediction of axillary response after neoadjuvant chemotherapy in breast cancer patients[J].BMC Cancer,2023,23(1):15.
[7] HAN X,WANG Y,JIA X,et al.Predictive value of delta-radiomic features for prognosis of advanced non-small cell lung cancer patients undergoing immune checkpoint inhibitor therapy[J].Transl Lung Cancer Res,2024,13(6):1247-1263.
[8] KIM S J,CHOI J Y,AHN Y C,et al.The prognostic value of radiomic features from pre-and post-treatment(18)F-FDG PET imaging in patients with nasopharyngeal carcinoma[J].Sci Rep,2023,13(1):8462.
[9] 王慧慧,魏正琦,潘犇,等.Delta影像组学联合临床特征评估EGFR-TKI治疗肺腺癌的疗效[J].放射学实践,2025,40(4):464-469.
[10] CUSUMANO D,BOLDRINI L,YADAV P,et al.Delta radiomics analysis for local control prediction in pancreatic cancer patients treated using magnetic resonance guided radiotherapy[J].Diagnostics(Basel),2021,11(1):72.
[11] ZINS M,MATOS C,CASSINOTTO C.Pancreatic adenocarcinoma staging in the era of preoperative chemotherapy and radiation therapy[J].Radiology,2018,287(2):374-390.
[12] WANG X Y,YANG F,JIN C,et al.Utility of PET/CT in diagnosis,staging,assessment of resectability and metabolic response of pancreatic cancer[J].World J Gastroenterol,2014,20(42):15580-15589.
[13] LEE W,OH M,KIM J S,et al.Metabolic activity by FDG-PET/CT after neoadjuvant chemotherapy in borderline resectable and locally advanced pancreatic cancer and association with survival[J].Br J Surg,2021,109(1):61-70.
[14] KITTAKA H,TAKAHASHI H,OHIGASHI H,et al.Role of(18)F-fluorodeoxyglucose positron emission tomography/computed tomography in predicting the pathologic response to preoperative chemoradiation therapy in patients with resectable T3 pancreatic cancer[J].World J Surg,2013,37(1):169-178.
[15] HU X,LI X,WANG P,et al.The role of FAPI PET imaging in pancreatic cancer:a meta-analysis compared with(18)F-FDG PET[J].Acad Radiol,2025,32(1):191-200.
[16] YOKOSE T,KITAGO M,MATSUSAKA Y,et al.Usefulness of(18)F-fluorodeoxyglucose positron emission tomography/computed tomography for predicting the prognosis and treatment response of neoadjuvant therapy for pancreatic ductal adenocarcinoma[J].Cancer Med,2020,9(12):4059-4068.
[17] SHEIKHBAHAEI S,WRAY R,YOUNG B,et al.18F-FDG-PET/CT therapy assessment of locally advanced pancreatic adenocarcinoma:impact on management and utilization of quantitative parameters for patient survival prediction[J].Nucl Med Commun,2016,37(3):231-238.
[18] WEI M,GU B,SONG S,et al.A novel validated recurrence stratification system based on(18)F-FDG PET/CT radiomics to guide surveillance after resection of pancreatic cancer[J].Front Oncol,2021,11:650266.
[19] 李艳霞,蒋圣哲,陈强,等.CT平扫及增强影像组学在急性胰腺炎严重程度评估中的应用研究[J].现代医学,2025,53(3):356-361.
[20] 曾钰瀧,葛昭,崇维霞,等.基于深度学习及Delta影像组学的唾液腺显像在甲状腺癌术后及¹³¹I治疗后唾液腺损伤评估中的价值[J].中华核医学与分子影像杂志,2024,44(2):68-73.
[21] COUSIN F,LOUIS T,DHEUR S,et al.Radiomics and delta-radiomics signatures to predict response and survival in patients with non-small-cell lung cancer treated with immune checkpoint inhibitors[J].Cancers(Basel),2023,15(7):1968.
[22] NARDONE V,REGINELLI A,RUBINI D,et al.Delta radiomics:an updated systematic review[J].Radiol Med,2024,129(8):1197-1214.
[23] NASIEF H,HALL W,ZHENG C,et al.Improving treatment response prediction for chemoradiation therapy of pancreatic cancer using a combination of delta-radiomics and the clinical biomarker CA19-9[J].Front Oncol,2019,9:1464.
[24] SIMPSON G,JIN W,SPIELER B,et al.Predictive value of delta-radiomics texture features in 0.35 tesla magnetic resonance setup images acquired during stereotactic ablative radiotherapy of pancreatic cancer[J].Front Oncol,2022,12:807725.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录