基于经直肠多模态超声技术和临床信息的前列腺癌风险预测模型构建与验证

Development and validation of a risk prediction model for prostate cancer based on transrectal multi-modal ultrasound features and clinical variables

摘要

目的 基于前列腺病灶经直肠多模态超声图像特征及临床信息构建前列腺癌风险预测列线图模型，以期在前列腺穿刺活检术前预测患者前列腺癌发生风险。方法 回顾性收集2021年8月-2023年12月于新疆医科大学第一附属医院行经直肠前列腺多模态超声检查并给予前列腺穿刺活检的400例患者的临床资料，按7∶3比例随机分为训练集（n=280）和测试集（n=120）。采用LASSO算法和单因素、多因素logistic回归分析筛选前列腺癌发生风险的独立影响因素，并构建列线图预测模型。采用受试者工作特征（ROC）曲线、校准曲线、曲线下面积（AUC）和临床决策曲线（DCA）评估与验证该列线图模型的预测效能。结果 本研究纳入的400例患者中，有185例经病理诊断为前列腺癌。经LASSO算法及单因素、多因素逐步logistic回归分析显示，年龄、前列腺特异性抗原的对数（ln PSA）、游离前列腺特异性抗原/总前列腺特异性抗原（f/t PSA）、病灶有无结节感、边界清晰与否、血流阻力指数（RI）、病灶与内腺峰值强度（PI）差值、应变率比值是前列腺癌发生风险的独立影响因素（均P＜0.01）。基于多因素logistic回归分析结果构建前列腺癌风险预测列线图模型。在验证集中，该列线图模型的AUC为0.902（95%CI：0.851～0.954），显示出较高的诊断性能。结论 基于经直肠多模态超声技术与临床信息构建的列线图模型能够在术前有效评估前列腺病灶的良恶性概率，可作为前列腺癌风险预测的重要工具。

Abstract

Objective To construct a nomogram model for predicting the risks of prostate cancer (PCa) based on transrectal multi-modal ultrasound features of prostatic lesions and clinical data, aiming to predict the malignant risk in patients prior to prostate needle biopsy. Methods A total of 400 patients who underwent transrectal multi-modal prostate ultrasound and subsequent prostate needle biopsy at our hospital during Aug. 2021 and Dec. 2023 were retrospectively enrolled. The patients were randomly divided into a training set (n=280) and a validation set (n=120) at a ratio of 7∶3. The least absolute shrinkage and selection operator (LASSO) algorithm, univariate and multivariate logistic regression analyses were applied to screen independent risk factors, and a predictive nomogram model was established. The predictive performance of the nomogram was evaluated and validated using receiver operating characteristic (ROC) curve, calibration curve, area under the ROC curve (AUC) and decision curve analysis (DCA). Results Of the 400 cases, 185 were pathologically confirmed as PCa. Age, natural logarithm of prostate-specific antigen (ln PSA), free-to-total prostate-specific antigen ratio (f/t PSA), presence of nodular sensation in lesions, lesion margin, resistance index (RI), peak intensity (PI) difference between the lesion and the prostatic inner gland, and strain rate ratio were identified as independent risk factors for PCa (all P<0.01). A PCa risk prediction nomogram was constructed based on the results of multivariate logistic regression analyses. In the validation set, the model yielded an AUC of 0.902 (95%CI: 0.851-0.954), demonstrating favorable diagnostic efficacy. Conclusion The nomogram established on the basis of transrectal multi-modal ultrasound and clinical information can effectively evaluate the benign and malignant probability of prostatic lesions preoperatively. It can be used as a quantitative tool and critical reference for clinical decision-making in patients with suspected prostate cancer.

关键词

前列腺癌 / 超声检查 / 多模态超声 / 列线图 / 预测模型

Key words

prostate cancer / ultrasonic examination / multi-modal ultrasound / nomogram / prediction model

参考文献

[1] SIEGEL RL, MILLER KD, FUCHS HE, et al. Cancer statistics, 2021[J]. Cancer J Clin, 2021, 71(1): 7-33.

[2] SUNG H, FERLAY J, SIEGEL RL, 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.

[3] SINDHWANI P, WILSON CM. Prostatitis and serum prostate-specific antigen[J]. Curr Urol Rep, 2005, 6(4): 307-312.

[4] GAO P, SHI C, ZHAO L, et al. Differential diagnosis of prostate cancer and noncancerous tissue in the peripheral zone and central gland using the quantitative parameters of DCE-MRI: a meta-analysis[J]. Medicine, 2016, 95(52): e5715.

[5] 熊飞, 王红, 李峰, 等. 经直肠超声造影微血管成像、弹性成像及常规超声靶向引导前列腺癌穿刺活检在前列腺病变诊断中的应用[J]. 现代泌尿外科杂志, 2024, 29(1): 18-22.

[6] SUN MH, XU L, ZHANG XY, et al. PI-RADS v2.1 evaluation of prostate "nodule in nodule" variants: clinical, imaging, and patholnical features[J]. Insights Imaging, 2024, 15(1): 79.

[7] 赵云歆, 江怡, 姚敏, 等. 前列腺癌超声造影低增强结节的病理学基础探索[J]. 肿瘤影像学, 2018, 27(5): 382-386.

[8] HUANG ST, HSIEH ML. Evaluation of resistance index in patients with prostate cancer[J]. Anticancer Res, 2008, 28(4A): 1985-1988.

[9] XU G, FENG L, YAO M, et al. A new 5-grading score in the diagnosis of prostate cancer with real-time elastography[J]. Int J Clin Exp Pathol, 2014, 7(7): 4128-4135.

[10] WOO S, SUH CH, KIM SY, et al. Shear-wave elastography for detection of prostate cancer: a systematic review and diagnostic meta-analysis[J]. AJR Am J Roentgenol, 2017, 209(4): 806-814.

[11] ZHENG X, JI P, MAO H, et al. A comparison of virtual touch tissue quantification and digital rectal examination for discrimination between prostate cancer and benign prostatic hyperplasia[J]. Radiol Oncol, 2012, 46(1): 69-74.

[12] ANBARASAN T, WEI C, BAMBER JC, et al. Characterisation of prostate lesions using transrectal shear wave elastography (SWE) ultrasound imaging: a systematic review[J]. Cancers (Basel), 2021, 13(1): 122.

[13] STRAZDINA A, KRUMINA G, SPERGA M. The value and limitations of contrast-enhanced ultrasound in detection of prostate cancer[J]. Anticancer Res, 2011, 31(4): 1421-1426.

[14] 吴猛, 吴蓉, 吴剑, 等. 超声造影和经直肠实时组织超声弹性成像及磁共振成像对前列腺癌诊断价值研究[J]. 中国全科医学, 2015, 18(18): 2228-2232, 2236.

[15] FOLEY SJ, BAILEY DM. Microvessel density in prostatic hyperplasia[J]. BJU Int, 2000, 85(1): 70-73.

[16] SRIVASTAVA S, KOAY EJ, BOROWSKY AD, et al. Cancer overdiagnosis: a biolnical challenge and clinical dilemma[J]. Nat Rev Cancer, 2019, 19(6): 349-358.

基金资助

自治区区域协同创新专项（科技援疆计划）(2024E02054)

省部共建中亚高发病成因与防治国家重点实验室开放课题(SKL-HIDCA-2024-BC5)