Share：
Share this content in WeChat
X
[Chinese] [PDF] 12 1
• Clinical Article •
Habitat analysis and peritumoral radiomics for predicting castration resistance in prostate cancer patients
GAO Hongyan  WU Hui  WANG Wenjia  YANG Zeting  LIU Jiarui  LIU Na 

Cite this article as: GAO H Y, WU H, WANG W J, et al. Habitat analysis and peritumoral radiomics for predicting castration resistance in prostate cancer patients[J]. Chin J Magn Reson Imaging, 2025, 16(10): 68-75. DOI:10.12015/issn.1674-8034.2025.10.011.


[Abstract] Objective This study aimed to predict the development of castration-resistant prostate cancer (CRPC) in prostate cancer (PCa) patients following androgen deprivation therapy (ADT) by establishing habitat imaging analysis and intra/peri-tumor radiomics models.Materials and Methods Clinical and multiparametric magnetic resonance imaging (mpMRI) data from 195 pathologically confirmed PCa patients treated with ADT were retrospectively analyzed. Patients were randomized into training (n = 138) and validation (n = 57) sets at a 7∶3 ratio. Tumor regions were segmented using habitat imaging, and habitat-specific features representing distinct subregions were extracted. K-means clustering algorithm partitioned tumors into two subclusters based on habitat heterogeneity. Radiomic features were selected from four regions: habitat subregions (17 features), intra-tumor (16 features), peri-tumor (15 features), and combined intra-tumor + 3 mm peri-tumor (ROIintra + 3 mm, 19 features). A logistic regression classifier was trained to construct radiomics models. The optimal habitat model was integrated with clinical features to establish a combined habitat-clinical (H + C) model. A radiomics nomogram (RN) was developed for individualized prediction. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).Results The habitat model demonstrated superior predictive performance (AUC = 0.821) compared to conventional radiomics models. The ROIintra + 3 mm model (AUC = 0.752) outperformed intra-tumor (AUC = 0.697) models and peri-tumor (AUC = 0.725) models. The H + C model achieved the highest predictive efficacy (AUC = 0.828). Calibration curves indicated excellent agreement between predicted and observed outcomes, while DCA curves confirmed greater clinical net benefit for the combined model.Conclusions Habitat imaging analysis significantly enhances CRPC prediction accuracy in PCa patients by resolving intratumoral heterogeneity. Peri-tumor radiomics provides independent prognostic value for CRPC progression, and integration of peri-tumor features improves model performance.
[Keywords] habitat analysis；radiomics；prostate cancer；castration resistance；peri-tumor region；magnetic resonance imaging

GAO Hongyan   WU Hui*   WANG Wenjia   YANG Zeting   LIU Jiarui   LIU Na  

Department of Radiology, Affiliated Hospital of Inner Mongolia Medical University, Hohhot 010050, China

Corresponding author: WU H, E-mail: terrywuhui@sina.com

Conflicts of interest   None.

Received  2025-06-19
Accepted  2025-09-10
DOI: 10.12015/issn.1674-8034.2025.10.011
Cite this article as: GAO H Y, WU H, WANG W J, et al. Habitat analysis and peritumoral radiomics for predicting castration resistance in prostate cancer patients[J]. Chin J Magn Reson Imaging, 2025, 16(10): 68-75. DOI:10.12015/issn.1674-8034.2025.10.011.

[1]
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[2]
JAMES N D, TANNOCK I, N'DOW J, et al. The lancet commission on prostate cancer: planning for the surge in cases[J]. Lancet, 2024, 403(10437): 1683-1722. DOI: 10.1016/S0140-6736(24)00651-2.
[3]
ZHENG R S, CHEN R, HAN B F, et al. Cancer incidence and mortality in China, 2022[J]. Chin J Oncol, 2024, 46(3): 221-231. DOI: 10.3760/cma.j.cn112152-20240119-00035.
[4]
YU E M, ARAGON-CHING J B. Advances with androgen deprivation therapy for prostate cancer[J]. Expert Opin Pharmacother, 2022, 23(9): 1015-1033. DOI: 10.1080/14656566.2022.2033210.
[5]
LOWRANCE W, DREICER R, JARRARD D F, et al. Updates to advanced prostate cancer: AUA/SUO guideline (2023)[J]. J Urol, 2023, 209(6): 1082-1090. DOI: 10.1097/JU.0000000000003452.
[6]
TILKI D, VAN DEN BERGH R C N, BRIERS E, et al. EAU-EANM-ESTRO-ESUR-ISUP-SIOG guidelines on prostate cancer. part Ⅱ-2024 update: treatment of relapsing and metastatic prostate cancer[J]. Eur Urol, 2024, 86(2): 164-182. DOI: 10.1016/j.eururo.2024.04.010.
[7]
DASKIVICH T J, STOCK S R, CUMMINGS S, et al. Risks of progression after early androgen deprivation therapy for biochemical recurrence after radical prostatectomy[J/OL]. J Urol, 2025: 101097JU0000000000004648 [2025-04-25]. https://pubmed.ncbi.nlm.nih.gov/40532189/. DOI: 10.1097/JU.0000000000004648.
[8]
WANG H L, LI N, LIU Q L, et al. Antiandrogen treatment induces stromal cell reprogramming to promote castration resistance in prostate cancer[J/OL]. Cancer Cell, 2023, 41(7): 1345-1362.e9 [2025-04-25]. https://pubmed.ncbi.nlm.nih.gov/37352863/. DOI: 10.1016/j.ccell.2023.05.016.
[9]
PARKER C, CASTRO E, FIZAZI K, et al. Prostate cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up[J]. Ann Oncol, 2020, 31(9): 1119-1134. DOI: 10.1016/j.annonc.2020.06.011.
[10]
LOMER N B, ASHOOBI M A, AHMADZADEH A M, et al. MRI-based radiomics for predicting prostate cancer grade groups: a systematic review and meta-analysis of diagnostic test accuracy studies[J]. Acad Radiol, 2025, 32(6): 3429-3452. DOI: 10.1016/j.acra.2024.12.006.
[11]
CHANG R S, QI S L, WU Y N, et al. Nomograms integrating CT radiomic and deep learning signatures to predict overall survival and progression-free survival in NSCLC patients treated with chemotherapy[J/OL]. Cancer Imaging, 2023, 23(1): 101 [2025-06-12]. https://pubmed.ncbi.nlm.nih.gov/37867196/. DOI: 10.1186/s40644-023-00620-4.
[12]
ABDOLLAHI H, CHIN E, CLARK H, et al. Radiomics-guided radiation therapy: opportunities and challenges[J/OL]. Phys Med Biol, 2022, 67(12): 12TR02 [2025-07-21]. https://pubmed.ncbi.nlm.nih.gov/35561699/. DOI: 10.1088/1361-6560/ac6fab.
[13]
O'CONNOR J P B, ROSE C J, WATERTON J C, et al. Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome[J]. Clin Cancer Res, 2015, 21(2): 249-257. DOI: 10.1158/1078-0432.CCR-14-0990.
[14]
WANG S X, LIU X W, WU Y, et al. Habitat-based radiomics enhances the ability to predict lymphovascular space invasion in cervical cancer: a multi-center study[J/OL]. Front Oncol, 2023, 13: 1252074 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/37954078/. DOI: 10.3389/fonc.2023.1252074.
[15]
LEE D H, PARK J E, KIM N, et al. Tumor habitat analysis using longitudinal physiological MRI to predict tumor recurrence after stereotactic radiosurgery for brain metastasis[J]. Korean J Radiol, 2023, 24(3): 235-246. DOI: 10.3348/kjr.2022.0492.
[16]
MOON H H, PARK J E, KIM N, et al. Prospective longitudinal analysis of imaging-based spatiotemporal tumor habitats in glioblastoma, IDH-wild type: implication in patient outcome using multiparametric physiologic MRI[J/OL]. BMC Cancer, 2024, 24(1): 1197 [2025-08-04]. https://pubmed.ncbi.nlm.nih.gov/39334005/. DOI: 10.1186/s12885-024-12939-7.
[17]
YUAN J L, WU M X, QIU L, et al. Tumor habitat-based MRI features assessing early response in locally advanced nasopharyngeal carcinoma[J/OL]. Oral Oncol, 2024, 158: 106980 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/39151333/. DOI: 10.1016/j.oraloncology.2024.106980.
[18]
YU Y X, FAN Y F, WANG X M, et al. Gd-EOB-DTPA-enhanced MRI radiomics to predict vessels encapsulating tumor clusters (VETC) and patient prognosis in hepatocellular carcinoma[J]. Eur Radiol, 2022, 32(2): 959-970. DOI: 10.1007/s00330-021-08250-9.
[19]
WANG X Y, WEI M X, CHEN Y, et al. Intratumoral and peritumoral MRI-based radiomics for predicting extrapelvic peritoneal metastasis in epithelial ovarian cancer[J/OL]. Insights Imaging, 2024, 15(1): 281 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/39576435/. DOI: 10.1186/s13244-024-01855-w.
[20]
China Prostate Cancer Research Collaboration Group, ZHU Y, YE D W. Chinese expert consensus on the follow-up management of patients with prostate cancer receiving medical castration therapy(2024 edition)[J]. Chin J Oncol, 2024, 46(4): 285-295. DOI: 10.3760/cma.j.cn112152-20240206-00067.
[21]
ZHOU C, ZHANG Y F, GUO S, et al. Multimodal data integration for predicting progression risk in castration-resistant prostate cancer using deep learning: a multicenter retrospective study[J/OL]. Front Oncol, 2024, 14: 1287995 [2025-08-05]. https://pubmed.ncbi.nlm.nih.gov/38549937/. DOI: 10.3389/fonc.2024.1287995.
[22]
TURKBEY B, ROSENKRANTZ A B, HAIDER M A, et al. Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2[J]. Eur Urol, 2019, 76(3): 340-351. DOI: 10.1016/j.eururo.2019.02.033.
[23]
KOHLBRENNER R, WU X, NGUYEN H G, et al. Pharmacokinetic comparison of selective prostatic arterial and intravenous PSMA PET/CT radioligand infusions in primary prostatic adenocarcinoma[J/OL]. Radiology, 2024, 312(2): e232544 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/39136560/. DOI: 10.1148/radiol.232544.
[24]
VAN GRIETHUYSEN J J M, FEDOROV A, PARMAR C, et al. Computational radiomics system to decode the radiographic phenotype[J/OL]. Cancer Res, 2017, 77(21): e104-e107 [2025-08-05]. https://pubmed.ncbi.nlm.nih.gov/29092951/. DOI: 10.1158/0008-5472.can-17-0339.
[25]
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. DOI: 10.1002/jmri.27678.
[26]
QIU Y. Gleason grade groupand risk assessment of prostate cancer: an applied study based on tumor subregions radiomics[D]. Chongqing: Chongqing Medical University, 2024. DOI: 10.27674/d.cnki.gcyku.2024.000962.
[27]
KOISTINEN H, KOVANEN R M, HOLLENBERG M D, et al. The roles of proteases in prostate cancer[J]. IUBMB Life, 2023, 75(6): 493-513. DOI: 10.1002/iub.2700.
[28]
PENG H, YANG M, FENG K, et al. Semaphorin 3C (Sema3C) reshapes stromal microenvironment to promote hepatocellular carcinoma progression[J/OL]. Signal Transduct Target Ther, 2024, 9(1): 169 [2025-06-23]. https://pubmed.ncbi.nlm.nih.gov/38956074/. DOI: 10.1038/s41392-024-01887-0.
[29]
WANG H, WANG T, YAN S X, et al. Crosstalk of pyroptosis and cytokine in the tumor microenvironment: from mechanisms to clinical implication[J/OL]. Mol Cancer, 2024, 23(1): 268 [2025-06-23]. https://pubmed.ncbi.nlm.nih.gov/39614288/. DOI: 10.1186/s12943-024-02183-9.
[30]
HUANG F Y, HUANG Q, LIAO X H, et al. Prediction of high-risk prostate cancer based on the habitat features of biparametric magnetic resonance and the omics features of contrast-enhanced ultrasound[J/OL]. Heliyon, 2024, 10(18): e37955 [2025-06-22]. https://pubmed.ncbi.nlm.nih.gov/39323806/. DOI: 10.1016/j.heliyon.2024.e37955.
[31]
JIN P F, SHEN J K, YANG L Q, et al. Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions: a retrospective multi-center study[J/OL]. BMC Med Imaging, 2023, 23(1): 47 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/36991347/. DOI: 10.1186/s12880-023-01002-9.
[32]
DE PALMA M, BIZIATO D, PETROVA T V. Microenvironmental regulation of tumour angiogenesis[J]. Nat Rev Cancer, 2017, 17(8): 457-474. DOI: 10.1038/nrc.2017.51.
[33]
XIANG X N, WANG J G, LU D, et al. Targeting tumor-associated macrophages to synergize tumor immunotherapy[J/OL]. Signal Transduct Target Ther, 2021, 6(1): 75 [2025-06-24]. https://pubmed.ncbi.nlm.nih.gov/33619259/. DOI: 10.1038/s41392-021-00484-9.
[34]
EIRO N, FERNÁNDEZ-GÓMEZ J M, DE LEÓN C G, et al. Gene expression profile of stromal factors in cancer-associated fibroblasts from prostate cancer[J/OL]. Diagnostics (Basel), 2022, 12(7): 1605 [2025-07-31]. https://pubmed.ncbi.nlm.nih.gov/35885510/. DOI: 10.3390/diagnostics12071605.

PREV Prediction of regional lymph node status in rectal cancer with radiomics features based on deep learning segmented tumor area
NEXT Evaluation of the value of diffusion tensor imaging in assessing the early efficacy of high-intensity focused ultrasound in adenomyosis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn