基于深度学习的影像组学在前列腺癌精准诊疗中的研究进展

doi:10.3760/cma.j.cn441417-20250414-21003

摘要/Abstract

摘要： 前列腺癌（prostate cancer，PCa）是男性常见的恶性肿瘤之一，PCa的精准诊疗亟需克服肿瘤异质性及预后差异的挑战。影像组学通过提取医学影像的高通量特征并融合人工智能技术，为病灶检测、Gleason评分预测及治疗反应监测提供了新工具。本文系统综述了影像组学在PCa中的技术流程、诊断效能、预后评估及治疗监测中的最新进展，梳理影像组学在无创分级、转移风险预测及个体化放疗规划中的突破性成果，重点整合了多模态影像技术与深度学习方法；针对当前技术局限性，提出建立多中心协作数据库、多模态组学、多组学融合、开发标准化验证模型的未来发展方向。通过技术创新与临床实践并重，影像组学有望推动PCa诊疗向动态精准医学范式转变，最终实现患者生存获益的全面提升。

关键词: 前列腺癌, 影像组学, MRI, 深度学习, 精准诊疗, 进展

Abstract: Prostate cancer (PCa) is one of the most common malignant tumors in men, and the precise diagnosis and treatment of PCa urgently need to address the challenges of tumor heterogeneity and prognostic variability. Radiomics, by extracting high-throughput features from medical imaging and integrating artificial intelligence technologies, provides new tools for lesion detection, Gleason score prediction, and treatment response monitoring. This article systematically reviews the latest advancements in the technical processes, diagnostic efficacy, prognostic assessment, and treatment monitoring of radiomics in PCa. It highlights breakthrough achievements in non-invasive grading, metastatic risk prediction, and personalized radiotherapy planning, with a focus on integrating multimodal imaging technologies and deep learning methods. Addressing current technical limitations, it proposes future development directions, including the establishment of multicenter collaborative databases, multimodal omics, integrative omics, and the development of standardized validation models. Through a balanced approach of technological innovation and clinical practice, radiomics is expected to drive the transition of PCa diagnosis and treatment towards a paradigm of dynamic precision medicine, ultimately enhancing patient survival benefits.

Key words:

Prostate cancer, Radiomics, MRI, Deep learning, Precision diagnosis and treatment, Progress

秦静王爱杰张亚飞黄冉冉王龙江李忠维张国伟. 基于深度学习的影像组学在前列腺癌精准诊疗中的研究进展[J]. 国际医药卫生导报, 2025, 31(21): 3531-3535.

Qin Jing, Wang Aijie, Zhang Yafei, Huang Ranran, Wang Longjiang, Li Zhongwei, Zhang Guowei. Research progress of imaging omics based on deep learning in the precise diagnosis and treatment of prostate cancer[J]. International Medicine and Health Guidance News, 2025, 31(21): 3531-3535.

参考文献

[1] Filho AM, Laversanne M, Ferlay J, et al. The GLOBOCAN 2022 cancer estimates: data sources, methods, and a snapshot of the cancer burden worldwide[J]. Int J Cancer, 2025, 156(7):1336-1346. DOI: 10.1002/ijc.35278.
[2] 顾秀瑛,郑荣寿,张思维,等. 2000—2014年中国肿瘤登记地区前列腺癌发病趋势及年龄变化分析[J]. 中华预防医学杂志,2018,52(6):586-592.DOI:10.3760/cma.j.issn.0253-9624.2018.06.006.
[3] 赫捷,陈万青,李霓,等. 中国前列腺癌筛查与早诊早治指南(2022,北京)[J]. 中华肿瘤杂志,2022,44(1):29-53.DOI:10.3760/cma.j.cn112152-20211226-00975.
[4] 张亚飞,黄冉冉,张国伟. 磁共振成像在前列腺癌早期筛查中的应用价值[J]. 山东第一医科大学学报,2022,43(12):963-966. DOI:10.3969/j.issn.2097-0005.2022.12.016.
[5] 曾文彦,庄娘妥,李琼华,等. 3.0T多参数磁共振成像诊断外周带慢性前列腺炎的临床价值[J]. 国际医药卫生导报,2022,28(20):2910-2914.DOI:10.3760/cma.j.issn.1007-1245.2022.20.021.
[6] Launer BM, Ellis TA, Scarpato KR. A contemporary review: mpMRI in prostate cancer screening and diagnosis[J]. Urol Oncol, 2025, 43(1):15-22. DOI: 10.1016/j.urolonc.2024.05.012.
[7] Khan A, Moore CM, Minhaj Siddiqui M. Prostate MRI and image quality: the urologist's perspective[J]. Eur J Radiol, 2024,170:111255. DOI: 10.1016/j.ejrad.2023.111255.
[8] Avanzo M, Wei L, Stancanello J, et al. Machine and deep learning methods for radiomics[J]. Med Phys, 2020,47(5):e185-e202. DOI: 10.1002/mp.13678.
[9] Chaddad A, Tan G, Liang X, et al. Advancements in MRI-based radiomics and artificial intelligence for prostate cancer: a comprehensive review and future prospects[J]. Cancers (Basel), 2023, 15(15):3839. DOI: 10.3390/cancers15153839.
[10] Zhu X, Shao L, Liu Z, et al. MRI-derived radiomics models for diagnosis, aggressiveness, and prognosis evaluation in prostate cancer[J]. J Zhejiang Univ Sci B, 2023, 24(8):663-681. DOI: 10.1631/jzus.B2200619.
[11] Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach[J]. Nat Commun, 2014, 5:4006. DOI: 10.1038/ncomms5006.
[12] 赵青,苏桐,代婷,等.基于多参数MRI影像组学联合临床病理变量预测乳腺癌新辅助治疗的敏感性[J].磁共振成像,2024,15(6):79-86.DOI:10.12015/issn.1674-8034.2024.06.012.
[13] 吴春梅, 李思琪, 杨存霞, 等. mpMRI影像组学在前列腺癌诊疗中的研究进展[J]. 磁共振成像, 2023, 14(6): 166-170,191. DOI: 10.12015/issn.1674-8034.2023.06.030.
[14] Stanzione A, Ponsiglione A, Alessandrino F, et al. Beyond diagnosis: is there a role for radiomics in prostate cancer management?[J]. Eur Radiol Exp, 2023, 7(1):13. DOI: 10.1186/s41747-023-00321-4.
[15] Feretzakis G, Juliebø-Jones P, Tsaturyan A, et al. Emerging trends in ai and radiomics for bladder, kidney, and prostate cancer: a critical review[J]. Cancers (Basel), 2024, 16(4):810. DOI: 10.3390/cancers16040810.
[16] Turkbey B, Haider MA. Deep learning-based artificial intelligence applications in prostate MRI: brief summary[J]. Br J Radiol, 2022, 95(1131):20210563. DOI: 10.1259/bjr.20210563.
[17] 乔晓梦,包婕,胡尘翰,等. 基于小视野扩散加权成像的影像组学模型对临床显著性前列腺癌的诊断价值[J]. 磁共振成像,2023,14(8):79-85.DOI:10.12015/issn.1674-8034.2023.08.013.
[18] 席晓霖.基于Bp-MRI及免疫组化表达状态构建影像组学模型在早期前列腺癌识别中的应用[D].郑州:河南大学,2024.DOI:10.27114/d.cnki.ghnau.2024.002246.
[19] Li C, Deng M, Zhong X, et al. Multi-view radiomics and deep learning modeling for prostate cancer detection based on multi-parametric MRI[J]. Front Oncol, 2023,13:1198899. DOI: 10.3389/fonc.2023.1198899.
[20] Zhang Y, Li W, Zhang Z, et al. Differential diagnosis of prostate cancer and benign prostatic hyperplasia based on DCE-MRI using bi-directional CLSTM deep learning and radiomics[J]. Med Biol Eng Comput, 2023, 61(3):757-771. DOI: 10.1007/s11517-022-02759-x.
[21] Zamboglou C, Bettermann AS, Gratzke C, et al. Uncovering the invisible-prevalence, characteristics, and radiomics feature-based detection of visually undetectable intraprostatic tumor lesions in 68GaPSMA-11 PET images of patients with primary prostate cancer[J]. Eur J Nucl Med Mol Imaging, 2021, 48(6):1987-1997. DOI: 10.1007/s00259-020-05111-3.
[22] Chen T, Hu W, Zhang Y, et al. A multimodal deep learning nomogram for the identification of clinically significant prostate cancer in patients with gray-zone PSA levels: comparison with clinical and radiomics models[J]. Acad Radiol, 2025, 32(2):864-876. DOI: 10.1016/j.acra.2024.10.009.
[23] 陈铌,周桥. 国际泌尿病理协会前列腺癌病理分级2019年共识简介[J]. 中华病理学杂志,2021,50(2):167-171. DOI:10.3760/cma.j.cn112151-20201019-00790.
[24] Zhou C, Zhang YF, Guo S, et al. Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study[J]. Discov Oncol, 2023, 14(1):133. DOI: 10.1007/s12672-023-00752-w.
[25] 邱杨.前列腺癌Gleason分级与风险评估:基于肿瘤亚区影像组学的应用研究[D].重庆:重庆医科大学,2024. DOI:10.27674/d.cnki.gcyku.2024.000962.
[26] Delgadillo R, Ford JC, Abramowitz MC, et al. The role of radiomics in prostate cancer radiotherapy[J]. Strahlenther Onkol, 2020, 196(10):900-912. DOI: 10.1007/s00066-020-01679-9.
[27] Feliciani G, Celli M, Ferroni F, et al. Radiomics analysis on [68Ga]Ga-PSMA-11 PET and MRI-ADC for the prediction of prostate cancer ISUP grades: preliminary results of the BIOPSTAGE trial[J]. Cancers (Basel), 2022, 14(8):1888. DOI: 10.3390/cancers14081888.
[28] Gao ZY, Zhang T, Zhang H, et al. Prognostic factors for overall survival in patients with spinal metastasis secondary to prostate cancer: a systematic review and meta-analysis[J]. BMC Musculoskelet Disord, 2020, 21(1):388. DOI: 10.1186/s12891-020-03412-0.
[29] Onal C, Guler OC, Erpolat P, et al. Evaluation of treatment outcomes of prostate cancer patients with lymph node metastasis treated with definitive radiotherapy: comparative analysis of PSMA PET/CT and conventional imaging[J]. Clin Nucl Med, 2024, 49(8):e383-e389. DOI: 10.1097/RLU.0000000000005284.
[30] Woo S, Han S, Kim TH, et al. Prognostic value of pretreatment MRI in patients with prostate cancer treated with radiation therapy: a systematic review and meta-analysis[J]. AJR Am J Roentgenol, 2020, 214(3):597-604. DOI: 10.2214/AJR.19.21836.
[31] Cuocolo R, Stanzione A, Faletti R, et al. MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study[J]. Eur Radiol, 2021, 31(10):7575-7583. DOI: 10.1007/s00330-021-07856-3.
[32] Cornford P, Bellmunt J, Bolla M, et al. EAU-ESTRO-SIOG guidelines on prostate cancer. Part II: treatment of relapsing, metastatic, and castration-resistant prostate cancer[J]. Eur Urol, 2017, 71(4):630-642. DOI: 10.1016/j.eururo.2016.08.002.
[33] Hofman MS, Murphy DG, Williams SG, et al. A prospective randomized multicentre study of the impact of gallium-68 prostate-specific membrane antigen (PSMA) PET/CT imaging for staging high-risk prostate cancer prior to curative-intent surgery or radiotherapy (proPSMA study): clinical trial protocol[J]. BJU Int, 2018, 122(5):783-793. DOI: 10.1111/bju.14374.
[34] Perera M, Jibara G, Tin AL, et al. Outcomes of grade group 2 and 3 prostate cancer on initial versus confirmatory biopsy: implications for active surveillance[J]. Eur Urol Focus, 2023, 9(4):662-668. DOI: 10.1016/j.euf.2022.12.008.
[35] Patra A, Khasawneh H, Suman G, et al. Atypical metastases in the abdomen and pelvis from biochemically recurrent prostate cancer: 11C-Choline PET/CT with multimodality correlation[J]. AJR Am J Roentgenol, 2022, 218(1):141-150. DOI: 10.2214/AJR.21.26426.
[36] Li L, Shiradkar R, Leo P, et al. A novel imaging based Nomogram for predicting post-surgical biochemical recurrence and adverse pathology of prostate cancer from pre-operative bi-parametric MRI[J]. EBioMedicine, 2021, 63:103163. DOI: 10.1016/j.ebiom.2020.103163.
[37] Wang H, Wang K, Zhang Y, et al. Deep learning-based radiomics model from pretreatment ADC to predict biochemical recurrence in advanced prostate cancer[J]. Front Oncol, 2024,14:1342104. DOI: 10.3389/fonc.2024.1342104.
[38] Assadi M, Manafi-Farid R, Jafari E, et al. Predictive and prognostic potential of pretreatment 68Ga-PSMA PET tumor heterogeneity index in patients with metastatic castration-resistant prostate cancer treated with 177Lu-PSMA[J]. Front Oncol, 2022, 12:1066926. DOI: 10.3389/fonc.2022.1066926.
[39] 刘和洋,刘倩,红华,等. 超声影像组学联合模型预测前列腺癌内分泌治疗无进展生存期的价值[J]. 中华超声影像学杂志,2024,33(11):992-999. DOI:10.3760/cma.j.cn131148-20240507-00266.
[40] Tran VT, Tu SJ, Tseng JR. 68Ga-PSMA-11 PET/CT features extracted from different radiomic zones predict response to androgen deprivation therapy in patients with advanced prostate cancer[J]. Cancers (Basel), 2022,14(19):4838. DOI: 10.3390/cancers14194838.