基于多参数MRI影像组学评估前列腺癌侵袭性

杨静; 黄豆豆; 陈峻帆; 罗银灯; 刘玥希

doi:10.16016/j.2097-0927.202307044

您当前的位置：

首页 >

文章列表页 >

基于多参数MRI影像组学评估前列腺癌侵袭性

临床医学 | 更新时间：2026-01-09

- 基于多参数MRI影像组学评估前列腺癌侵袭性
- Assessment of invasion of prostate cancer with multiparametric MRI-based radiomics
- 陆军军医大学学报 2024年46卷第2期页码：170-180
- 作者机构：
  
  400010 重庆，重庆医科大学附属第二医院放射科
- 作者简介：
  
  [罗银灯，E-mail: 300757@hospital.cqmu.edu.cnLUO Yindeng, E-mail: 300757@hospital.cqmu.edu.cn
- 基金信息：
  
  重庆市科技局技术创新与应用发展专项(cstc2019jscx-msxmX0253);利益冲突声明全体作者声明无利益冲突
- DOI：10.16016/j.2097-0927.202307044
  中图分类号： R445.2;R73-37;R737.25
- 收稿：2023-07-08，
  
  修回：2023-09-04，
  
  纸质出版：2024-01-30
- 稿件说明：
移动端阅览
杨静, 黄豆豆, 陈峻帆, 等. 基于多参数MRI影像组学评估前列腺癌侵袭性[J]. 陆军军医大学学报, 2024,46(2):170-180.

Jing YANG, Doudou HUANG, Junfan CHEN, et al. Assessment of invasion of prostate cancer with multiparametric MRI-based radiomics[J]. Journal of Army Medical University, 2024, 46(2): 170-180.
杨静, 黄豆豆, 陈峻帆, 等. 基于多参数MRI影像组学评估前列腺癌侵袭性[J]. 陆军军医大学学报, 2024,46(2):170-180. DOI： 10.16016/j.2097-0927.202307044.

Jing YANG, Doudou HUANG, Junfan CHEN, et al. Assessment of invasion of prostate cancer with multiparametric MRI-based radiomics[J]. Journal of Army Medical University, 2024, 46(2): 170-180. DOI： 10.16016/j.2097-0927.202307044.

摘要

目的

探讨多参数MRI上不同感兴趣区的影像组学模型和结合影像组学、PI-RADS 2.1评分、临床变量的综合模型在评估前列腺癌侵袭性方面的价值。

方法

收集本院2018年5月至2022年9月2个医疗中心经病理确诊为前列腺癌患者245例：渝中院区176例，其中低侵袭性组[Gleason评分≤7(3+4)

]

77例，高侵袭性组[Gleason评分≥7(4+3)

]

99例；江南院区69例(低侵袭性组33例，高侵袭性组36例)。所有患者行多参数MRI检查后，在多参数MRI图像上分割2种ROI：肿瘤病变区域(tumor region，TR)和前列腺区域(prostate gland，PG)。评估与前列腺癌侵袭性相关的临床变量，并记录每位患者的PI-RADS 2.1评分。使用逻辑回归算法作为机器学习算法，建立多个前列腺癌侵袭性分层模型：影像组学模型(Model

、Model

PG+TR

)、影像组学-临床联合模型、影像组学-PIRADS联合模型、临床-PIRADS联合模型和影像组学-临床-PIRADS综合模型。分别采用受试者工作特性(ROC)曲线、曲线下面积(AUC)和决策曲线分析(DCA)比较各模型的诊断价值和临床收益。结合影像组学评分、独立临床变量和PI-RADS2.1评分构建影像组学列线图。通过校准度、区分度和临床应用评价列线图性能。

结果

在3种影像组学模型中，Model

PG+TR

的AUC值为0.919，高于Model

(AUC=0.874)和Model

(AUC=0.887)。在联合模型中，影像组学-PIRADS-临床综合模型的AUC为0.954，优于影像组学模型(AUC=0.919)、影像组学-临床联合模型(AUC=0.919)、影像组学-PIRADS联合模型(AUC=0.921)和临床-PIRADS联合模型(AUC=0.769)。列线图在评估前列腺癌侵袭性方面显示出良好的风险分层性能(AUC=0.919)和校准效能。决策曲线分析显示，影像组学模型Model

PG+TR

和影像组学-临床-PIRADS综合模型获得了较高的临床净收益。

结论

结合前列腺和肿瘤区域特征的影像组学模型可准确评估前列腺癌的侵袭性；结合影像组学、PI-RADS 2.1评分和临床变量的综合模型能进一步提高对前列腺癌侵袭性的评估性能。

Abstract

Objective

To investigate the value of a radiomic model of multiparametric MRI different regions of interest (ROI) in assessment of the invasion of prostate cancer (PCa)

and explore the evaluation value of an integrated model based on above radiomic model combined with radiomics

PI-RADS 2.1 score

and clinical variables.

Methods

A total of 245 patients with pathologically-confirmed PCa admitted to 2 medical centers in our hospital from May 2018 to September 2022 were collected in this retrospective study. Among them

176 cases were collected in Yuzhong Medical Center

including 77 cases in the low invasive group [Gleason score ≤7 (3+4)

]

and 99 cases in the high invasive group [Gleason score ≥7 (4+3)

]

; 69 cases were collected in Jiangnan Medical Center

including 33 cases in the low invasive group and 36 cases in the high invasive group. All patients underwent multiparametric MRI

and then 2 types of ROI

the tumor region (TR) and the prostate gland (PG)

were segmented on the multiparametric MRI images. Clinical variables related with PCa invasion were assessed

and PI-RADS 2.1 score was recorded for each patient. Logistic regression algorithm was employed as a machine learning method to develop following invasive stratification models for PCa: radiomics models (Model

Model

and Model

PG+TR

)

Radiomics-Clinical model

Radiomics-PIRADS model

PIRADS-Clinical model and Radiomics-PIRADS-Clinical combined model. Receiver operating characteristic (ROC) curve

area under ROC curve (AUC) and decision curve analysis (DCA) were applied to compare the diagnostic efficacy and clinical benefit of each model. A nomogram was constructed by combining Radiomics score (Radscore)

PI-RADS 2.1 score and independent clinical variables

and its performance was evaluated by calibration

differentiation and clinical application.

Results

the above 3 radiomics models

the AUC value was 0.919 for Model

PG+TR

which was higher than that of Model

(0.874) and of Model

(0.887). And the AUC value of the Radiomics-PIRADS-Clinical combined model was 0.954

superior to that of the radiomics model (0.919)

Radiomics-PIRADS model (0.921)

Radiomics-Clinical model (0.919)

and PIRADS-Clinical model (0.769) respectively

The nomogram model showed good performance (AUC=0.919) and calibration efficacy in risk stratification. DSA revealed that both the Model

PG+TR

model and Radiomics-PIRADS-Clinical combined models achieved a higher net clinical benefit.

Conclusion

Our radiomic model of combining features of the prostate and tumor regions can more accurately assess the invasion of PCa

and our integrated model of combining radiomics

PI-RADS 2.1 score and clinical variables can further improve the assessment.

关键词

Keywords

references

REBELLO R J, OING C, KNUDSEN K E, et al . Prostate cancer[J ] . Nat Rev Dis Primers, 2021, 7(1): 1-27. DOI: 10.1038/s41572-020-00243-0.

HURWITZ L M, AGALLIU I, ALBANES D, et al . Recommended definitions of aggressive prostate cancer for etiologic epidemiologic research[J ] . J Natl Cancer Inst, 2021, 113(6): 727-734. DOI: 10.1093/jnci/djaa154.

SCHAEFFER E, SRINIVAS S, ANTONARAKIS E S, et al . NCCN guidelines insights: prostate cancer, version 1.2021[J ] . J Natl Compr Canc Netw, 2021, 19(2): 134-143. DOI: 10.6004/jnccn.2021.0008.

TURKBEY B, XU S, KRUECKER J, et al . Documenting the location of systematic transrectal ultrasound-guided prostate biopsies: correlation with multi-parametric MRI[J ] . Cancer Imaging, 2011, 11(1): 31-36. DOI: 10.1102/1470-7330.2011.0007.

WOO S, SUH C H, KIM S Y, et al . Diagnostic performance of prostate imaging reporting and data system version 2 for detection of prostate cancer: a systematic review and diagnostic meta-analysis[J ] . Eur Urol, 2017, 72(2): 177-188. DOI: 10.1016/j.eururo.2017.01.042.

SONN G A, FAN R E, GHANOUNI P, et al . Prostate magnetic resonance imaging interpretation varies substantially across radiologists[J ] . Eur Urol Focus, 2019, 5(4): 592-599. DOI: 10.1016/j.euf.2017.11.010.

GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.

KRAFFT S P, RAO A, STINGO F, et al . The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis[J ] . Med Phys, 2018, 45(11): 5317-5324. DOI: 10.1002/mp.13150.

HOMAYOUNIEH F, EBRAHIMIAN S, BABAEI R, et al . CT radiomics, radiologists, and clinical information in predicting outcome of patients with COVID-19 pneumonia[J ] . Radiol Cardiothorac Imaging, 2020, 2(4): e200322. DOI: 10.1148/ryct.2020200322.

HAN C, MA S, LIU X, et al . Radiomics models based on apparent diffusion coefficient maps for the prediction of high-grade prostate cancer at radical prostatectomy: comparison with preoperative biopsy[J ] . J Magn Reson Imaging, 2021, 54(6): 1892-1901. DOI: 10.1002/jmri.27565.

JING G D, XING P Y, LI Z H, et al . Prediction of clinically significant prostate cancer with a multimodal MRI-based radiomics nomogram[J ] . Front Oncol, 2022, 12: 918830. DOI: 10.3389/fonc.2022.918830.

BERNATZ S, ACKERMANN J, MANDEL P, et al . Comparison of machine learning algorithms to predict clinically significant prostate cancer of the peripheral zone with multiparametric MRI using clinical assessment categ ories and radiomic features[J ] . Eur Radiol, 2020, 30(12): 6757-6769. DOI: 10.1007/s00330-020-07064-5.

EGEVAD L, DELAHUNT B, SRIGLEY J R, et al . International Society of Urological Pathology (ISUP) grading of prostate cancer: An ISUP consensus on contemporary grading[J ] . APMIS, 2016, 124(6): 433-435. DOI: 10.1111/apm.12533.

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.

YANG L, LI M, ZHANG M N, et al . Association of prostate zonal volume with location and aggressiveness of clinically significant prostate cancer: A multiparametric MRI study according to PI-RADS version 2.1[J ] . Eur J Radiol, 2022, 150: 110268. DOI: 10.1016/j.ejrad.2022.110268.

ZHANG G M Y, HAN Y Q, WEI J W, et al . Radiomics based on MRI as a biomarker to guide therapy by predicting upgrading of prostate cancer from biopsy to radical prostatectomy[J ] . J Magn Reson Imaging, 2020, 52(4): 1239-1248. DOI: 10.1002/jmri.27138.

BLEKER J, KWEE T C, DIERCKX R A J O, et al . Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer[J ] . Eur Radiol, 2020, 30(3): 1313-1324. DOI: 10.1007/s00330-019-06488-y.

GONG L X, XU M, FANG M J, et al . The potential of prostate gland radiomic features in identifying the Gleason score[J ] . Comput Biol Med, 2022, 144: 105318. DOI: 10.1016/j.compbiomed.2022.105318.

CHENG X Q, CHEN Y T, XU H, et al . Avoiding unnecessary systematic biopsy in clinically significant prostate cancer: comparison between MRI-based radiomics model and PI-RADS category[J ] . J Magn Reson Imaging, 2023, 57(2): 578-586. DOI: 10.1002/jmri.28333.

YE C H, BYUN S S, HONG S K, et al . mp74-13 evaluation of the tumor volume from surgical specimens after radical prostatectomy and its clinical impact on the prognosis of patients with localized prostate cancer[J ] . J Urol, 2020, 203(Supplement 4): e1136-e1137. DOI: 10.1097/ju.0000000000000960.013.

WU M, KRISHNA S, THORNHILL R E, et al . Transition zone prostate cancer: Logistic regression and machine-learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis[J ] . J Magn Reson Imaging, 2019, 50(3): 940-950. doi: 10.1002/jmri.26674.

NKETIAH G, ELSCHOT M, KIM E, et al . T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results[J ] . Eur Radiol, 2017, 27(7): 3050-3059. DOI: 10.1007/s00330-016-4663-1.

HUMPHREY P A. Tumor amount in prostatic tissues in relation to patient outcome and management[J]. Am J Clin Pathol, 2009, 131(1): 7-10. DOI: 10.1309/AJCPAU2KQURY6COY.

EPSTEIN J I. Prognostic significance of tumor volume in radical prostatectomy and needle biopsy specimens[J]. J Urol, 2011, 186(3): 790-797. DOI: 10.1016/j.juro.2011.02.2695.

KILIC M, MADENDERE S, VURAL M, et al . The role of the size and number of index lesion in the diagnosis of clinically significant prostate cancer in patients with PI-RADS 4 lesions who underwent in-bore MRI-guided prostate biopsy[J ] . World J Urol, 2023, 41(2): 449-454. DOI: 10.1007/s00345-022-04274-y.

FREEDLAND S J, ISAACS W B, PLATZ E A, et al. Prostate size and risk of high-grade, advanced prostate cancer and biochemical progression aft er radical prostatectomy: a search database study[J ] . J Clin Oncol, 2005, 23(30): 7546-7554. DOI: 10.1200/JCO.2005.05.525.

NEWTON M R, PHILLIPS S, CHANG S S, et al . Smaller prostate size predicts high grade prostate cancer at final pathology[J ] . J Urol, 2010, 184(3): 930-937. DOI: 10.1016/j.juro.2010.04.082.

BRIGANTI A, CHUN F K H, SUARDI N, et al . Prostatevolume and adverse prostate cancer features: fact not artifact[J ] . Eur J Cancer, 2007, 43(18): 2669-2677. DOI: 10.1016/j.ejca.2007.09.022.

KIM K H, LIM S K, SHIN T Y, et al . Upgrading of Gleason score and prostate volume: a clinicopathological analysis[J ] . BJU Int, 2013, 111(8): 1310-1316. DOI: 10.1111/j.1464-410x.2013.11799.x.

WOŹNICKI P, WESTHOFF N, HUBER T, et al . Multiparametric MRI for prostate cancer characterization: combined use of radiomics model with PI-RADS and clinical parameters[J ] . Cancers, 2020, 12(7): 1767. DOI: 10.3390/cancers12071767.

CHEN T, ZHANG Z Y, TAN S, et al . MRI based radiomics compared with the PI-RADS V 2.1 in the prediction of clinically sign ificant prostate cancer: biparametric vs multiparametric MRI[J ] . Front Oncol, 2022, 11: 792456. DOI: 10.3389/fonc.2021.792456..

KIM M J, PARK S Y. Biparametric magnetic resonance imaging-derived nomogram to detect clinically significant prostate cancer by targeted biopsy for index lesion[J]. J Magn Reson Imaging, 2022, 55(4): 1226-1233. DOI: 10.1002/jmri.27841.

HIREMATH A, SHIRADKAR R, FU P F, et al . An integrated nomogram combining deep learning, Prostate Imaging-Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametricMRI: a retrospective multicentre study[J ] . Lancet Digit Health, 2021, 3(7): e445-e454. DOI: 10.1016/S2589-7500(21)00082-0.

LIU B, CHENG J, GUO D J, et al . Prediction of prostate cancer aggressiveness with a combination of radiomics and machine learning-based analysis of dynamic contrast-enhanced MRI[J ] . Clin Radiol, 2019, 74(11): 896. e1-896. e8. DOI: 10.1016/j.crad.2019.07.011.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合深度学习、临床与影像组学特征的综合模型提升非小细胞肺癌EGFR突变预测效能

CT影像组学联合临床特征对胰腺导管腺癌患者生存预测的应用研究

联合瘤内及瘤周异质性的MRI影像组学预测高级别胶质瘤原位复发空间模式的价值

基于增强静脉期CT放射组学的甲状腺乳头状癌中央区淋巴结转移预测模型构建与验证

基于CT影像组学特征联合临床特征预测非小细胞肺癌EGFR突变状态