Share：
Share this content in WeChat
X
[Chinese][PDF]1182
• Review •
Research progress of radiomics and deep learning in prostate cancer
LIU Jiarui  WU Hui  LIU Na  GAO Kaihua  YANG Jiao 

Cite this article as LIU J R, WU H, LIU N, et al. Research progress of radiomics and deep learning in prostate cancer[J]. Chin J Magn Reson Imaging, 2024, 15(5): 222-226, 234. DOI:10.12015/issn.1674-8034.2024.05.036.


[Abstract] Prostate cancer (Pca) is one of the most common malignant tumors of male genitourinary system, and its incidence rate is increasing year by year. Therefore, early diagnosis, pathological classification, risk stratification and prognosis evaluation of Pca are crucial to the formulation of patient diagnosis and treatment plans. Radiomics and deep learning (DL) have made significant progress in Pca research, providing important tools for the realization of precision medicine in recent years. This article systematically reviews the applications and potential of these two techniques in Pca image segmentation, diagnosis, Gleason grading, prediction of extracapsular extension and metastasis, prognosis evaluation, and treatment decision-making. It also summarizes the achievements, limitations, and future improvement measures and development directions of current research, aiming to provide more precise and personalized diagnosis and treatment plans for Pca patients, thereby improving treatment effectiveness and quality of life.
[Keywords] prostate cancer；radiomics；deep learning；magnetic resonance imaging；diagnosis；prognostic evaluation

LIU Jiarui   WU Hui*   LIU Na   GAO Kaihua   YANG Jiao  

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  2024-01-30
Accepted  2024-04-17
DOI: 10.12015/issn.1674-8034.2024.05.036
Cite this article as LIU J R, WU H, LIU N, et al. Research progress of radiomics and deep learning in prostate cancer[J]. Chin J Magn Reson Imaging, 2024, 15(5): 222-226, 234. DOI:10.12015/issn.1674-8034.2024.05.036.

[1]
HE J, CHEN W Q, LI N, et al. China guideline for the screening and early detection of prostate cancer (2022, Beijing) [J]. Chin J Oncol, 2022, 44(1): 29-53. DOI: 10.3760/cma.j.cn112152-20211226-00975.
[2]
CAI H L, YUAN W G, LIU S Q, et al. Study on disease burden and risk factors of prostate cancer in China in 1990 and 2019[J]. J Clin Urol, 2022, 37(10): 749-752. DOI: 10.13201/j.issn.1001-1420.2022.10.005.
[3]
XIA C F, DONG X S, LI H, et al. Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J]. Chin Med J, 2022, 135(5): 584-590. DOI: 10.1097/CM9.0000000000002108.
[4]
GU X Y, ZHENG R S, ZHANG S W, et al. Analysis on the trend of prostate cancer incidence and age change in cancer registration areas of China, 2000 to 2014[J]. Chin J Prev Med, 2018, 52(6): 586-592. DOI: 10.3760/cma.j.issn.0253-9624.2018.06.006.
[5]
ZIGLIOLI F, PATERA A, ISGRÒ G, et al. Impact of modifiable lifestyle risk factors for prostate cancer prevention: a review of the literature[J/OL]. Front Oncol, 2023, 13: 1203791 [2023-06-08]. https://doi.org/10.3389/fonc.2023.1203791. DOI: 10.3389/fonc.2023.1203791.
[6]
ZHANG S L. Research on intelligent screening method for prostate cancer ultrasound images based on deep learning[D].Guangzhou: Guangdong Polytechnic Normal University, 2023. DOI: 10.27729/d.cnki.ggdjs.2023.000232.
[7]
WANG W H, ZHANG T H, XIE Z Z, et al. Visual analysis of research hotspots and trends of radiomics in prostate cancer[J]. Guangdong Med J, 2024, 45(1): 121-130. DOI: 10.13820/j.cnki.gdyx.20233784.
[8]
ACS B, RANTALAINEN M, HARTMAN J. Artificial intelligence as the next step towards precision pathology[J]. J Intern Med, 2020, 288(1): 62-81. DOI: 10.1111/joim.13030.
[9]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[10]
ZHAO S Y, LIU X B, GUO Y, et al. Application progress of imaging in prostate cancer[J]. Chin J Med Imag, 2021, 29(4): 411-414. DOI: 10.3969/j.issn.1005-5185.2021.04.030.
[11]
WANG Y. Research on artificial intelligence and multimodal imaging in some disease analysis[D].Shenyang: Northeastern University, 2019. DOI: 10.27007/d.cnki.gdbeu.2019.000179.
[12]
YANG J, HUANG D D, CHEN J F, et al. Application of multiparametric MRI imaging based on different regions of interest in the assessment of prostate cancer aggressiveness[J]. J Clin Radiol, 2023, 42(9): 1465-1470. DOI: 10.13437/j.cnki.jcr.2023.09.011.
[13]
ZOVÁTHI B H, MOHÁCSI R, SZÁSZ A M, et al. Breast tumor tissue segmentation with area-based annotation using convolutional neural network[J/OL]. Diagnostics, 2022, 12(9): 2161 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/36140562/. DOI: 10.3390/diagnostics12092161.
[14]
KOSTYSZYN D, FECHTER T, BARTL N, et al. Intraprostatic tumor segmentation on PSMA PET images in patients with primary prostate cancer with a convolutional neural network[J]. J Nucl Med, 2021, 62(6): 823-828. DOI: 10.2967/jnumed.120.254623.
[15]
GHEZZO S, MONGARDI S, BEZZI C, et al. External validation of a convolutional neural network for the automatic segmentation of intraprostatic tumor lesions on 68Ga-PSMA PET images[J/OL]. Front Med, 2023, 10: 1133269 [2023-06-08]. https://doi.org/10.3389/fmed.2023.1133269. DOI: 10.3389/fmed.2023.1133269.
[16]
SUNOQROT M R S, SELNÆS K M, SANDSMARK E, et al. A quality control system for automated prostate segmentation on T2-weighted MRI[J/OL]. Diagnostics, 2020, 10(9): 714 [2023-06-08]. https://doi.org/10.3390/diagnostics10090714. DOI: 10.3390/diagnostics10090714.
[17]
DAI Z Z, CARVER E, LIU C, et al. Segmentation of the prostatic gland and the intraprostatic lesions on multiparametic magnetic resonance imaging using mask region-based convolutional neural networks[J]. Adv Radiat Oncol, 2020, 5(3): 473-481. DOI: 10.1016/j.adro.2020.01.005.
[18]
DURAN A, DUSSERT G, ROUVIÈRE O, et al. ProstAttention-Net: a deep attention model for prostate cancer segmentation by aggressiveness in MRI scans[J/OL]. Med Image Anal, 2022, 77: 102347 [2023-06-08]. https://doi.org/10.1016/j.media.2021.102347. DOI: 10.1016/j.media.2021.102347.
[19]
CHEN M L. Automatic differentiation of prostate cancer based on magnetic resonance and histopathology images[D].Shanghai: East China Normal University, 2020. DOI: 10.27149/d.cnki.ghdsu.2020.001627.
[20]
ZHANG Y, LI W K, 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]
LI C Y, DENG M, ZHONG X L, et al. Multi-view radiomics and deep learning modeling for prostate cancer detection based on multi-parametric MRI[J/OL]. Front Oncol, 2023, 13: 1198899 [2023-06-08]. https://doi.org/10.3389/fonc.2023.1198899. DOI: 10.3389/fonc.2023.1198899.
[22]
LEUNG K H, ROWE S P, LEAL J P, et al. Deep learning and radiomics framework for PSMA-RADS classification of prostate cancer on PSMA PET[J/OL]. EJNMMI Res, 2022, 12(1): 76 [2023-06-08]. https://doi.org/10.1186/s13550-022-00948-1. DOI: 10.1186/s13550-022-00948-1.
[23]
LI D Y, HAN X W, GAO J, et al. Deep learning in prostate cancer diagnosis using multiparametric magnetic resonance imaging with whole-mount histopathology referenced delineations[J/OL]. Front Med, 2022, 8: 810995 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/35096899. DOI: 10.3389/fmed.2021.810995.
[24]
YU R Q. Prostate cancer detection and PI-RADS scoring based on radiomics and deep learning[D].Shanghai: East China Normal University, 2022. DOI: 10.27149/d.cnki.ghdsu.2022.002138.
[25]
ZHOU C, ZHANG Y F, GUO S, et al. Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study[J/OL]. Discov Oncol, 2023, 14(1): 133 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/37470865. DOI: 10.1007/s12672-023-00752-w.
[26]
SUN Y Y, ZHANG J T, SU Y T, et al. Application of radiomics machine learning in differentiating gleason grade group for prostate cancer based on biparametric magnetic resonance imaging[J]. Chin J CT MRI, 2023, 21(8): 118-120. DOI: 10.3969/j.issn.1672-5131.2023.08.038.
[27]
QIU Y, LIU Y F, SHU X, et al. Peritumoral radiomics strategy based on ensemble learning for the prediction of gleason grade group of prostate cancer[J]. Acad Radiol, 2023, 30(Suppl 1): S1-S13. DOI: 10.1016/j.acra.2023.06.011.
[28]
MAKOWSKI M R, BRESSEM K K, FRANZ L, et al. De novo radiomics approach using image augmentation and features from T1 mapping to predict gleason scores in prostate cancer[J]. Invest Radiol, 2021, 56(10): 661-668. DOI: 10.1097/RLI.0000000000000788.
[29]
LIU J T, SHAN W L, KONG D, et al. Value of radiomics based on Bi-parametric MRI combined PSA in predicting gleason score of protaste cancer[J]. J Clin Radiol, 2023, 42(4): 634-639. DOI: 10.13437/j.cnki.jcr.2023.04.020.
[30]
CAO R M, MOHAMMADIAN BAJGIRAN A, AFSHARI MIRAK S, et al. Joint prostate cancer detection and gleason score prediction in mp-MRI via FocalNet[J]. IEEE Trans Med Imaging, 2019, 38(11): 2496-2506. DOI: 10.1109/TMI.2019.2901928.
[31]
BRUNESE L, MERCALDO F, REGINELLI A, et al. Radiomics for gleason score detection through deep learning[J/OL]. Sensors, 2020, 20(18): 5411 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/32967291. DOI: 10.3390/s20185411.
[32]
ZLOTTA A R, EGAWA S, PUSHKAR D, et al. Prevalence of prostate cancer on autopsy: cross-sectional study on unscreened Caucasian and Asian men[J]. J Natl Cancer Inst, 2013, 105(14): 1050-1058. DOI: 10.1093/jnci/djt151.
[33]
SAKR W A, GRIGNON D J, CRISSMAN J D, et al. High grade prostatic intraepithelial neoplasia (HGPIN) and prostatic adenocarcinoma between the ages of 20-69: an autopsy study of 249 cases[J]. In Vivo, 1994, 8(3): 439-443.
[34]
LIN X J, ZHU G B, ZHANG C R, et al. Differential diagnosis of clinically significant prostate cancer using a machine learning model based on magnetic resonance apparent diffusion coefficient imaging[J]. J Mod Oncol, 2023, 31(22): 4202-4206. DOI: 10.3969/j.issn.1672-4992.2023.22.019.
[35]
BRANCATO V, AIELLO M, BASSO L, et al. Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions[J/OL]. Sci Rep, 2021, 11(1): 643 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/33436929. DOI: 10.1038/s41598-020-80749-5.
[36]
BHATTACHARYA I, SEETHARAMAN A, KUNDER C, et al. Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework[J/OL]. Med Image Anal, 2022, 75: 102288 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/34784540. DOI: 10.1016/j.media.2021.102288.
[37]
MEHTA P, ANTONELLI M, AHMED H U, et al. Computer-aided diagnosis of prostate cancer using multiparametric MRI and clinical features: a patient-level classification framework[J/OL]. Med Image Anal, 2021, 73: 102153 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/34246848. DOI: 10.1016/j.media.2021.102153.
[38]
FALAGARIO U G, JAMBOR I, RATNANI P, et al. Performance of prostate multiparametric MRI for prediction of prostate cancer extra-prostatic extension according to NCCN risk categories: implication for surgical planning[J]. Ital J Urol Nephrol, 2020, 72(6): 746-754. DOI: 10.23736/S0393-2249.20.03688-7.
[39]
ROOIJ M D, HAMOEN E H, WITJES J A, et al. Accuracy of magnetic resonance imaging for local staging of prostate cancer: a diagnostic meta-analysis[J]. Eur Urol, 2016, 70(2): 233-245. DOI: 10.1016/j.eururo.2015.07.029.
[40]
YANG L Q, JIN P F, BAO J, et al. MRI-based radiomics for the prediction of extra-capsular extension with prostate cancer[J]. J Clin Radiol, 2023, 42(5): 789-795. DOI: 10.13437/j.cnki.jcr.2023.05.029.
[41]
MOROIANU Ş L, BHATTACHARYA I, SEETHARAMAN A, et al. Computational detection of extraprostatic extension of prostate cancer on multiparametric MRI using deep learning[J/OL]. Cancers, 2022, 14(12): 2821 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/35740487. DOI: 10.3390/cancers14122821.
[42]
HOU Y, ZHANG Y H, BAO J, et al. Artificial intelligence is a promising prospect for the detection of prostate cancer extracapsular extension with mpMRI: a two-center comparative study[J]. Eur J Nucl Med Mol Imaging, 2021, 48(12): 3805-3816. DOI: 10.1007/s00259-021-05381-5.
[43]
DUAN X J, CUI Y G. Advances in the diagnosis and treatment of bone metastases in prostate cancer[J]. Chin J Med, 2023, 58(6): 594-596.
[44]
LI K J, ZHANG J T, REN K X, et al. The value of machine learning model for predicting prostate cancer bone metastases based on MRI radiomics[J]. Chin J Magn Reson Imag, 2023, 14(1): 100-104, 115. DOI: 10.12015/issn.1674-8034.2023.01.018.
[45]
JI J Z, ZHANG Q, NIU M, et al. Nomogram based on clinical, MR T2WI and apparent diffusion coefficient map radiomics features for predicting bone metastasis of incipient prostate cancer[J]. Chin J Med Imag Technol, 2022, 38(7): 1050-1055. DOI: 10.13929/j.issn.1003-3289.2022.07.020.
[46]
SONG X Y, ZHANG T, WANG Y Y, et al. Clinic, MRI radiomics and deep learning combined model for predicting bone metastases of initial prostate cancer[J]. Chin J Interv Imag Ther, 2023, 20(4): 212-217. DOI: 10.13929/j.issn.1672-8475.2023.04.006.
[47]
LIU X, CUI Y P, HAN C, et al. The value of DWI radiomics model in predicting pelvic bone metastasis of prostate cancer based on deep learning segmentation model[J]. Radiol Pract, 2021, 36(12): 1563-1570. DOI: 10.13609/j.cnki.1000-0313.2021.12.020.
[48]
WU C M, LI S Q, YANG C X, et al. Advances in multiparametric magnetic resonance imaging radiomics in the management of prostate cancer[J]. Chin J Magn Reson Imag, 2023, 14(6): 166-170, 191. DOI: 10.12015/issn.1674-8034.2023.06.030.
[49]
SUMITOMO M, TERAMOTO A, TODA R, et al. Deep learning using preoperative magnetic resonance imaging information to predict early recovery of urinary continence after robot-assisted radical prostatectomy[J]. Int J Urol, 2020, 27(10): 922-928. DOI: 10.1111/iju.14325.
[50]
ZHU Q Q. Value of MRI radiomics in predicting progression to castration-resistant prostate cancer after endocrine therapy for prostate cancer[D].Kaifeng: Henan University, 2023. DOI: 10.27114/d.cnki.ghnau.2023.000712.
[51]
WANG Y R. MRI-based Texture Analysis of the Primary Tumor for the Prediction of Bone Metastases, therapeutic Evaluation of Androgen Deprivation Therapy in Prostate Cancer[D].Shenyang: China Medical University, 2020. DOI: 10.27652/d.cnki.gzyku.2020.000040.
[52]
JIA Y S, QUAN S, REN J L, et al. MRI radiomics predicts progression-free survival in prostate cancer[J/OL]. Front Oncol, 2022, 12: 974257 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/36110963. DOI: 10.3389/fonc.2022.974257.
[53]
LEE H W, KIM E, NA I, et al. Novel multiparametric magnetic resonance imaging-based deep learning and clinical parameter integration for the prediction of long-term biochemical recurrence-free survival in prostate cancer after radical prostatectomy[J/OL]. Cancers, 2023, 15(13): 3416 [2023-06-08]. https://pubmed.ncbi.nlm.nih.gov/37444526. DOI: 10.3390/cancers15133416.

PREV Research progress of magnetic resonance elastography in abdominal and pelvic cancer
NEXT Research progress of radiomics in common gynecologic malignancies
  


LINK


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