[1]朱学华 邵立智① 颜野 刘泽南 何继德 马潞林 卢剑**.前列腺癌根治术后生化复发相关MRI影像组学特征的研究[J].中国微创外科杂志,2023,01(5):359-366.
　Zhu Xuehua*,Shao Lizhi,Yan Ye*,et al.MRIbased Radiomics Features Associated With Biochemical Recurrence of Prostate Cancer After Radical Prostatectomy[J].Chinese Journal of Minimally Invasive Surgery,2023,01(5):359-366.
点击复制

前列腺癌根治术后生化复发相关MRI影像组学特征的研究()
分享到：

《中国微创外科杂志》[ISSN:1009-6604/CN:11-4526/R]

卷:
01
期数:
2023年5期
页码:
359-366
栏目:
影像学研究
出版日期:
2023-05-25

文章信息/Info

Title:
MRIbased Radiomics Features Associated With Biochemical Recurrence of Prostate Cancer After Radical Prostatectomy
作者:
朱学华 邵立智① 颜野 刘泽南 何继德 马潞林 卢剑**
(北京大学第三医院泌尿外科，北京100191)
Author(s):
Zhu Xuehua*;  Shao Lizhi;  Yan Ye*;  et al.
*Department of Urology, Peking University Third Hospital, Beijing 100191, China
关键词:
前列腺癌; 影像组学; 前列腺癌根治术; 生化复发
Keywords:
Prostate cancer; Radiomics; Radical prostatectomy; Biochemical recurrence
文献标志码:
A
摘要:
目的基于双参数磁共振成像(biparametric magnetic resonance imaging, bpMRI)探讨影响前列腺癌根治术(radical prostatectomy, RP)后生化复发(biochemical recurrence, BCR)的影像组学特征。方法回顾性分析我科2010年1月~2016年6月278例RP患者的临床资料，术后至少随访3年，86例(30.9%)发生BCR。以患者术后病理切片为参考，采用认知融合的方式在术前mpMRI相应层面的T2WI和表观弥散系数（apparent diffusion coefficient,ADC)图片上勾画前列腺癌灶轮廓，获得感兴趣区(region of interest，ROI)，对MRI片ROI内的影像组学特征进行提取。最小绝对选择与收缩算子(least absolute shrinkage and selection operator，LASSO)回归联合Cox回归模型用于影像组学特征降维、筛选及影像组学标签构建。单因素和多因素Cox回归分析影响BCR的预后因素。结果由T2WI和ADC图中各获取444个影像组学特征，共888个影像组学特征。通过LASSO回归进行特征降维及筛选，最终获得6个非零参数的影像组学特征。基于上述特征，结合Cox回归模型构建影像组学标签。多因素Cox回归分析显示影像组学标签(HR=2.404，95%CI:1.543~3.747，P=0.000)与国际泌尿病理协会(International Society of Urological Pathology，ISUP)分级(HR=1.235，95%CI：1.027~1.486，P=0.025)是BCR的独立预后因素。结论共获得6个非零系数的bpMRI影像组学特征，以此构建的影像组学标签与RP后BCR显著相关。该标签可能有助于辅助识别RP 治疗后BCR高风险的前列腺癌患者。
Abstract:
ObjectiveTo evaluate the biparametric magnetic resonance imaging (bpMRI) based radiomics features associated with the biochemical recurrence (BCR) after radical prostatectomy (RP).MethodsA total of 278 patients with prostate cancer who underwent RP in our department from January 2010 to June 2016 with a minimum of 3year followups were retrospectively investigated. The preoperative bpMRI images of T2WI and apparent diffusion coefficient (ADC) at the corresponding level were identified by cognitive fusion with the reference of a pathological section to outline the tumor, and subsequently the region of interest (ROI) was acquired. Radiomic features in the ROI were extracted. The least absolute shrinkage and selection operator (LASSO) regression algorithm combined with the Cox regression model was used for feature dimensionality reduction, selection, and signature construction. Univariate and multivariate Cox regression were used to identify the prognostic factors of BCR.ResultsA total of 888 radiomics features were acquired from T2WI and ADC images (444 features for each). Through the LASSO regression for feature dimensionality reduction and selection, 6 radiomics features with nonzero coefficients were identified. Based on the above features, the Cox regression model was utilized to construct a radiomics signature. In the multivariate analysis, the radiomics signature (HR=2404, 95% CI: 1.543-3.747,P=0.000) and International Society of Urological Pathology (ISUP) grade (HR=1.235, 95% CI: 1.027-1.486,P=0.025) were independent prognostic factors of BCR.ConclusionsSix imaging features with nonzero coefficients and the radiomics signature built from them are significantly correlated with BCR after RP. This signature may help identify prostate cancer patients with high risk of BCR following RP.

参考文献/References:

[1]Siegel RL, Miller KD, Fuchs HE, et al. Cancer statistics, 2022. CA Cancer J Clin,2022,72(1):7-33.
[2]Cao W, Chen HD, Yu YW, et al. Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020. Chin Med J (Engl),2021,134(7):783-791.
[3]Rebello RJ, Oing C, Knudsen KE, et al. Prostate cancer. Nat Rev Dis Primers,2021,7(1):9.
[4]Van den Broeck T, van den Bergh RCN, Arfi N, et al. Prognostic value of biochemical recurrence following treatment with curative intent for prostate cancer: A systematic review. Eur Urol,2019,75(6):967-987.
[5]Devos G, Devlies W, De Meerleer G, et al. Neoadjuvant hormonal therapy before radical prostatectomy in highrisk prostate cancer. Nature Rev Urol,2021,18(12):739-762.
[6]Roach M, 3rd. Current trends for the use of androgen deprivation therapy in conjunction with radiotherapy for patients with unfavorable intermediaterisk, highrisk, localized, and locally advanced prostate cancer. Cancer,2014,120(11):1620-1629.
[7]Brajtbord JS, Leapman MS, Cooperberg MR. The CAPRA score at 10 years: Contemporary perspectives and analysis of supporting studies. Eur Urol,2017,71(5):705-709.
[8]Kattan MW, Eastham JA, Stapleton AM, et al. A preoperative nomogram for disease recurrence following radical prostatectomy for prostate cancer. J Natl Cancer Inst,1998,90(10):766-771.
[9]Zelic R, Garmo H, Zugna D, et al. Predicting prostate cancer death with different pretreatment risk stratification tools: A headtohead comparison in a nationwide cohort study. Eur Urol,2020,78(1):E45-E47.
[10]Yeung VH, Chiu Y, Yu SS, et al. Are preoperative Kattan and Stephenson nomograms predicting biochemical recurrence after radical prostatectomy applicable in the Chinese population? Sci World J,2013,2013:506062.
[11]王海峰,高旭,王燕,等.Kattan列线图和CAPRA评分预测中国前列腺癌患者根治术后生化复发的效能验证.中华泌尿外科杂志,2015,36(4):285-289.
[12]Liesenfeld L, Kron M, Gschwend JE, et al. Prognostic factors for biochemical recurrence more than 10 years after radical prostatectomy. J Urol,2017,197(1):143-148.
[13]Ploussard G, Agamy MA, Alenda O, et al. Impact of positive surgical margins on prostatespecific antigen failure after radical prostatectomy in adjuvant treatmentnave patients. BJU Int,2011,107(11):1748-1754.
[14]Limkin EJ, Sun R, Dercle L, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology. Ann Oncol,2017,28(6):1191-1206.
[15]Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics. J Nucl Med,2020,61(4):488-495.
[16]Stabile A, Giganti F, Rosenkrantz AB, et al. Multiparametric MRI for prostate cancer diagnosis: current status and future directions. Nat Rev Urol,2020,17(1):41-61.
[17]Cookson MS, Aus G, Burnett AL, et al. Variation in the definition of biochemical recurrence in patients treated for localized prostate cancer: the American Urological Association prostate guidelines for localized prostate cancer update panel report and recommendations for a standard in the reporting of surgical outcomes. J Urol,2007,177(2):540-545.
[18]Turkbey B, Rosenkrantz AB, Haider MA, et al. Prostate imaging reporting and data system version 21: 2019 Update of prostate imaging reporting and data system version 2. Eur Urol,2019,76(3):340-351.
[19]Shao L, Yan Y, Liu Z, et al. Radiologistlike artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy. Theranostics,2020,10(22):10200-10212.
[20]Yu Y, Tan Y, Xie C, et al. Development and validation of a preoperative magnetic resonance imaging radiomics-based signature to predict axillary lymph node metastasis and diseasefree survival in patients with earlystage breast cancer. JAMA New Open,2020,3(12):e2028086.
[21]Wu Q, Wang S, Li L, et al. Radiomics analysis of computed tomography helps predict poor prognostic outcome in COVID19. Theranostics,2020,10(16):7231-7244.
[22]Midiri F, Vernuccio F, Purpura P, et al. Multiparametric MRI and radiomics in prostate cancer: A review of the current literature. Diagnostics (Basel),2021,11(10):1829.
[23]Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics. J Nucl Med,2020,61(4):488-495.
[24]Gnep K, Fargeas A, GutierrezCarvajal RE, et al. Haralick textural features on T2weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer. J Magn Reson Imaging,2017,45(1):103-117.
[25]Shiradkar R, Ghose S, Jambor I, et al. Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings. J Magn Reson Imaging,2018,48(6):1626-1636.
[26]Bourbonne V, Vallieres M, Lucia F, et al. MRIderived radiomics to guide postoperative management for highrisk prostate cancer. Front Oncol,2019,9:807.
[27]Bourbonne V, Fournier G, Vallieres M, et al. External validation of an MRIderived radiomics model to predict biochemical recurrence after surgery for highrisk prostate cancer. Cancers,2020,12(4):814.
[28]Yan Y, Shao LZ, Liu ZY, et al. Deep learning with quantitative features of magnetic resonance images to predict biochemical recurrence of radical prostatectomy: A multicenter study. Cancers,2021,13(12):3098.

备注/Memo

备注/Memo:
基金项目：北京市自然科学基金（Z200027、L212051）；北京大学第三医院-院队列建设项目B类（BYSYDL2021012）**通讯作者，Email：lujian@bjmu.edu.cn ①（中国科学院自动化研究所分子影像重点实验室，北京100190）
更新日期/Last Update: 2023-08-10