Intratumoural and peritumoural mpMRI-based Delta-radiomics model for the prediction of the response to androgen deprivation therapy in prostate cancerLI Rong1, WANG Ting1, LÜ Hong2, LIU Xiaohang1, ZHOU Liangping1, GU Yajia1, ZHOU　Bingni1

李榕; 王婷; 吕泓; 刘晓航; 周良平; 顾雅佳; 周冰妮

doi:10.19732/j.cnki.2096-6210.2026.02.005

您当前的位置：

首页 >

文章列表页 >

Intratumoural and peritumoural mpMRI-based Delta-radiomics model for the prediction of the response to androgen deprivation therapy in prostate cancerLI Rong¹, WANG Ting¹, LÜ Hong², LIU Xiaohang¹, ZHOU Liangping¹, GU Yajia¹, ZHOU　Bingni¹

Article | 更新时间：2026-05-07

- Intratumoural and peritumoural mpMRI-based Delta-radiomics model for the prediction of the response to androgen deprivation therapy in prostate cancerLI Rong¹, WANG Ting¹, LÜ Hong², LIU Xiaohang¹, ZHOU Liangping¹, GU Yajia¹, ZHOU　Bingni¹
- Oncoradiology Vol. 35, Issue 2, Pages: 251-263(2026)
- 作者机构：
  
  1.复旦大学附属肿瘤医院放射诊断科，复旦大学上海医学院肿瘤学系，上海 200032
  2.复旦大学附属肿瘤医院病理科，复旦大学上海医学院肿瘤学系，上海 200032
- 作者简介：
- 基金信息：
  
  Shanghai Anticancer Association EYAS PROJECT(SACA-CY24C03)
- DOI：10.19732/j.cnki.2096-6210.2026.02.005
  CLC： R737.25;R445.2
- Received：22 October 2025，
  
  Revised：2025-01-08，
  
  Published：28 April 2026
- 稿件说明：
移动端阅览
李　榕, 王　婷, 吕　泓, 等. 基于治疗前后瘤内及瘤周mpMRI的Delta影像组学预测前列腺癌雄激素剥夺治疗效果的价值研究［J］. 肿瘤影像学, 2026, 35(2): 251-263.

LI R, WANG T, LÜ H, et al.Citation: Intratumoural and peritumoural mpMRI-based Delta-radiomics model for the prediction of the response to androgen deprivation therapy in prostate cancer［J］. Oncoradiology, 2026, 35(2): 251-263.
李　榕, 王　婷, 吕　泓, 等. 基于治疗前后瘤内及瘤周mpMRI的Delta影像组学预测前列腺癌雄激素剥夺治疗效果的价值研究［J］. 肿瘤影像学, 2026, 35(2): 251-263. DOI： 10.19732/j.cnki.2096-6210.2026.02.005.

LI R, WANG T, LÜ H, et al.Citation: Intratumoural and peritumoural mpMRI-based Delta-radiomics model for the prediction of the response to androgen deprivation therapy in prostate cancer［J］. Oncoradiology, 2026, 35(2): 251-263. DOI： 10.19732/j.cnki.2096-6210.2026.02.005.

摘要

目的

雄激素剥夺治疗（androgen deprivation therapy，ADT）是目前前列腺癌（prostate cancer，PCa）患者常用的治疗方法之一，然而ADT后前列腺腺体及病灶的形态及病理学特征均发生明显改变，使得常规影像学参数及评价标准在ADT效果评估方面价值有限。本研究拟探索基于多参数磁共振成像（multiparametric magnetic resonance imaging，mpMRI）的肿瘤内部区域（瘤内）、肿瘤周围区域（瘤周）的Delta影像组学是否有助于预测疗效，分析有效瘤周范围，研究瘤内、瘤周、临床信息联合分析的恰当方式。

方法

回顾并分析2013年1月—2020年12月复旦大学附属肿瘤医院经病理学检查证实的PCa患者资料，所有患者于ADT治疗前后均行mpMRI检查。根据治疗后病理学检查结果将患者分为显著残留（significant residual，SR）组与完全缓解（complete response，CR）/微量残留病灶（minimal residual disease，MRD）两组。在治疗前后的mpMRI图像上分别勾画全瘤感兴趣区（volume of interest，VOI），而后采用膨胀算法将VOI分别外扩3 mm和6 mm，提取影像组学特征并计算其变化率，构建特征数据集（训练集∶验证集为7∶3）。使用逻辑回归构建影像组学模型、临床特征模型，并构建两者融合模型。采用受试者工作特征曲线的曲线下面积（area under curve，AUC）、DeLong检验评估模型效能。

结果

共纳入109例PCa患者，经病理学检查证实SR组69例，CR/MRD组40例。影像组学模型中瘤内模型、瘤内+3 mm瘤周模型、瘤内+6 mm瘤周模型的AUC（验证集）分别为0.78、0.84、0.79。临床模型验证集AUC为0.80。验证集中融合模型AUC分别为融合模型1（瘤内-临床）0.89，融合模型2（瘤内+3 mm瘤周-临床）0.92，融合模型3（瘤内+6 mm瘤周-临床）0.90。融合模型2与临床模型相比，其差异有统计学意义（

0.05）。

结论

瘤内、瘤内结合瘤周的Delta影像组学均能有效预测ADT效果，其中瘤内+3 mm瘤周影像组学模型的诊断效能最佳。与临床模型相比，基于mpMRI的瘤内+3 mm瘤周影像组学-临床融合模型可以显著提高ADT效果预测的准确度。

Abstract

Objective

Androgen deprivation therapy (ADT) is one of the primary treatments for prostate cancer (PCa) patients. However

morphology and pathological characteristics of prostate glands and PCa lesions will significantly change after ADT

which limit the value of conventional multiparametric magnetic resonance imaging (mpMRI) parameters and evaluation criteria in the evaluation of ADT response. This study aimed to explore the value of the Delta-radiomics of the intratumoural area (IA) and peritumoural area (PA) based on mpMRI to predict the response to ADT in PCa.

Methods

Patients with pathologically confirmed PCa who underwent mpMRI examinations both before and after ADT at Fudan University Shanghai Cancer Center between January 2013 and December 2020 were analyzed retrospectively. The patients were divided into a significant residual (SR) group and complete response and minimum residual disease (CR/MRD) group according to pathological results after ADT. Three types of volumes of interest (VOIs) were obtained for each lesion: IA VOI

IA+3 mm PA VOI

and IA + 6 mm PA VOI. Radiomics features were extracted

and Delta-radiomics data were calculated. The Delta-radiomics model

clinical model

and combined model were developed by logistic regression methods. Model performance was evaluated by receiver operating characteristic curve and the area under the curve (AUC). The DeLong test was used to compare the AUC values among the different models.

Results

A total of 109 patients were included

and 69 patients in the SR group and 40 patients in the CR/MRD group were included. The AUCs of the IA

IA+3 mm PA and IA+6 mm PA Delta-radiomics models were 0.78

0.84 and 0.79

respectively. The AUC of the clinical model was 0.80. The AUCs of the combined models of IA

IA+3 mm PA

and IA+6 mm PA were 0.89

0.92

and 0.90

respectively. The DeLong test demonstrated significant differences (

0.05) in the predictive performance between the combined model (IA+3 mm PA) and the clinical model.

Conclusion

Delta-radiomics can effectively predict the response to ADT

with the IA+3 mm PA radiomics model achieving the best diagnostic performance. Compared with the clinical model

the combined model (IA+3 mm PA) can significantly improve the accuracy of predicting the response to ADT.

关键词

Keywords

references

TEOH J Y C , HIRAI H W , HO J M W , et al . Global incidence of prostate cancer in developing and developed countries with changing age structures ［J］. PLoS One , 2019 , 14 ( 10 ): e0221775 .

ZHU Y , WANG H K , QU Y Y , et al . Prostate cancer in East Asia: evolving trend over the last decade ［J］. Asian J Androl , 2015 , 17 ( 1 ): 48 - 57 .

LI J , SIEGEL D A , KING J B . Stage-specific incidence rates and trends of prostate cancer by age, race, and ethnicity, United States, 2004-2014 ［J］. Ann Epidemiol , 2018 , 28 ( 5 ): 328 - 330 .

MCKAY R R , MONTGOMERY B , XIE W L , et al . Post prostatectomy outcomes of patients with high-risk prostate cancer treated with neoadjuvant androgen blockade ［J］. Prostate Cancer Prostatic Dis , 2018 , 21 ( 3 ): 364 - 372 .

SAINI S . PSA and beyond: alternative prostate cancer biomarkers ［J］. Cell Oncol , 2016 , 39 ( 2 ): 97 - 106 .

PUCA L , VLACHOSTERGIOS P J , BELTRAN H . Neuroendocrine differentiation in prostate cancer: emerging biology, models, and therapies ［J］. Cold Spring Harb Perspect Med , 2019 , 9 ( 2 ): a030593 .

MURPHY W M , SOLOWAY M S , BARROWS G H . Pathologic changes associated with androgen deprivation therapy for prostate cancer ［J］. Cancer , 1991 , 68 ( 4 ): 821 - 828 .

PADHANI A R , MACVICAR A D , GAPINSKI C J , et al . Effects of androgen deprivation on prostatic morphology and vascular permeability evaluated with MR imaging ［J］. Radiology , 2001 , 218 ( 2 ): 365 - 374 .

RØE K , SEIERSTAD T , KRISTIAN A , et al . Longitudinal magnetic resonance imaging-based assessment of vascular changes and radiation response in androgen-sensitive prostate carcinoma xenografts under androgen-exposed and androgen-deprived conditions ［J］. Neoplasia , 2010 , 12 ( 10 ): 818 - 825 .

BARRETT T , GILL A B , KATAOKA M Y , et al . DCE and DW MRI in monitoring response to androgen deprivation therapy in patients with prostate cancer: a feasibility study ［J］. Magn Reson Med , 2012 , 67 ( 3 ): 778 - 785 .

COAKLEY F V , TEH H S , QAYYUM A , et al . Endorectal MR imaging and MR spectroscopic imaging for locally recurrent prostate cancer after external beam radiation therapy: preliminary experience ［J］. Radiology , 2004 , 233 ( 2 ): 441 - 448 .

RØE K , KAKAR M , SEIERSTAD T , et al . Early prediction of response to radiotherapy and androgen-deprivation therapy in prostate cancer by repeated functional MRI: a preclinical study ［J］. Radiat Oncol , 2011 , 6 : 65 .

CHEN Z Z , GU W J , ZHOU B N , et al . Radiomics based on biparametric MRI for the detection of significant residual prostate cancer after androgen deprivation therapy: using whole-mount histopathology as reference standard ［J］. Asian J Androl , 2023 , 25 ( 1 ): 86 - 92 .

PETRAKI C D , SFIKAS C P . Histopathological changes induced by therapies in the benign prostate and prostate adenocarcinoma ［J］. Histol Histopathol , 2007 , 22 ( 1 ): 107 - 118 .

ZHANG H , LI X L , ZHANG Y X , et al . Diagnostic nomogram based on intralesional and perilesional radiomics features and clinical factors of clinically significant prostate cancer ［J］. J Magn Reson Imaging , 2021 , 53 ( 5 ): 1550 - 1558 .

ALGOHARY A , SHIRADKAR R , PAHWA S , et al . Combination of peri-tumoral and intra-tumoral radiomic features on bi-parametric MRI accurately stratifies prostate cancer risk: a multi-site study ［J］. Cancers , 2020 , 12 ( 8 ): 2200 .

BAI H L , XIA W , JI X F , et al . Multiparametric magnetic resonance imaging-based peritumoral radiomics for preoperative prediction of the presence of extracapsular extension with prostate cancer ［J］. J Magn Reson Imaging , 2021 , 54 ( 4 ): 1222 - 1230 .

张　涵 , 毛　宁 , 黄　程 , 等 . 基于前列腺病变周围区域的MRI影像组学特征对临床显著性前列腺癌的诊断价值［J］. 临床放射学杂志 , 2021 , 40 ( 2 ): 377 - 381 .

ZHANG H , MAO N , HUANG C , et al . The value of prostate perilesional MRI radiomics features for diagnosis of clinically significant prostate cancer ［J］. J Clin Radiol , 2021 , 40 ( 2 ): 377 - 381 .

ZHAI T S , HU L T , MA W G , et al . Peri-prostatic adipose tissue measurements using MRI predict prostate cancer aggressiveness in men undergoing radical prostatectomy ［J］. J Endocrinol Invest , 2021 , 44 ( 2 ): 287 - 296 .

MALLAT S G . A theory for multiresolution signal decomposition: the wavelet representation ［J］. IEEE Trans Pattern Anal Mach Intell , 1989 , 11 ( 7 ): 674 - 693 .

TIBSHIRANI R . Regression shrinkage and selection via the lasso ［J］. J R Stat Soc Ser B Stat Methodol , 1996 , 58 ( 1 ): 267 - 288 .

VICKERS A J , CRONIN A M , ELKIN E B , et al . Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers ［J］. BMC Med Inform Decis Mak , 2008 , 8 : 53 .

BHOWMICK N A , NEILSON E G , MOSES H L . Stromal fibroblasts in cancer initiation and progression ［J］. Nature , 2004 , 432 ( 7015 ): 332 - 337 .

OCAÑA A , DIEZ-GÓNZÁLEZ L , ADROVER E , et al . Tumor-infiltrating lymphocytes in breast cancer: ready for prime time? ［J］. J Clin Oncol , 2015 , 33 ( 11 ): 1298 - 1299 .

ACERBI I , CASSEREAU L , DEAN I , et al . Human breast cancer invasion and aggression correlates with ECM stiffening and immune cell infiltration ［J］. Integr Biol , 2015 , 7 ( 10 ): 1120 - 1134 .

UEMATSU T . Focal breast edema associated with malignancy on T2-weighted images of breast MRI: peritumoral edema, prepectoral edema, and subcutaneous edema ［J］. Breast Cancer , 2015 , 22 ( 1 ): 66 - 70 .

LU P F , WEAVER V M , WERB Z . The extracellular matrix: a dynamic niche in cancer progression ［J］. J Cell Biol , 2012 , 196 ( 4 ): 395 - 406 .

BRAMAN N , PRASANNA P , WHITNEY J , et al . Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2 (ERBB2)-positive breast cancer ［J］. JAMA Netw Open , 2019 , 2 ( 4 ): e192561 .

SALJI M , HENDRY J , PATEL A , et al . Peri-prostatic fat volume measurement as a predictive tool for castration resistance in advanced prostate cancer ［J］. Eur Urol Focus , 2018 , 4 ( 6 ): 858 - 866 .

SHAYESTEH S , NAZARI M , SALAHSHOUR A , et al . Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer ［J］. Med Phys , 2021 , 48 ( 7 ): 3691 - 3701 .

SUSHENTSEV N , RUNDO L , BLYUSS O , et al . Comparative performance of MRI-derived PRECISE scores and delta-radiomics models for the prediction of prostate cancer progression in patients on active surveillance ［J］. Eur Radiol , 2022 , 32 ( 1 ): 680 - 689 .

SUDARSHAN V K , MOOKIAH M R K , ACHARYA U R , et al . Application of wavelet techniques for cancer diagnosis using ultrasound images: a review ［J］. Comput Biol Med , 2016 , 69 : 97 - 111 .

程梓轩 . 小波分解对结直肠癌CT影像组学特征稳定性和诊断效能影响的研究［D］. 广州 : 华南理工大学 , 2019 .

YU Y F , HE Z F , OUYANG J , et al . Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study ［J］. EBioMedicine , 2021 , 69 : 103460 .

ZHOU J L , LU J H , GAO C , et al . Predicting the response to neoadjuvant chemotherapy for breast cancer: wavelet transforming radiomics in MRI ［J］. BMC Cancer , 2020 , 20 ( 1 ): 100 .

PANEBIANCO V , VILLEIRS G , WEINREB J C , et al . Prostate magnetic resonance imaging for local recurrence reporting (PI-RR): international consensus-based guidelines on multiparametric magnetic resonance imaging for prostate cancer recurrence after radiation therapy and radical prostatectomy ［J］. Eur Urol Oncol , 2021 , 4 ( 6 ): 868 - 876 .

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

The application value of multimodal radiomics models in Gleason score of prostate cancer

Diagnostic efficiency and inter-observer agreement among readers with variable experience of PI-RR system: using whole-mount histology after androgen deprivation therapy as reference

A study on the diagnostic performance and consistency of clinically significant prostate cancer based on PI-RADS v2.1

Comparison of ¹⁸ F-PSMA-1007 PET/CT and mpMRI in the detection and intraprostatic localization of primary prostate cancer

Values and limitations of artificial intelligence aided diagnosis in prostate MRI: a systemic review of multicenter studies

Related Author

YANG Xin

YANG Hongkai

QI Xuan

ZHAI Chengfeng

HE Yongsheng nbsp

CHEN Zhangzhe

ZHOU Bingni

LIU Wei

Related Institution

Department of Imaging, Ma’anshan People’s Hospital, Ma’anshan

Department of Radiology, Shanghai Geriatric Medical Center

Department of Radiology, People&rsquo

Department of Radiology, Beijing Friendship Hospital Affiliated to Capital Medical University

Department of Medical Imaging, The First Hospital of Qinhuangdao City

AI脑图

AI问答

⁰