分享:
分享到微信朋友圈
X
综述
基于多参数磁共振成像的影像组学在膀胱癌精准诊疗中的研究进展
白晶晶 张璐 王效春 杨国强

Cite this article as: Bai JJ, Zhang L, Wang XC, et al. Research progress on precise diagnosis and treatment of bladder cancer based on multiparameter MRI radiomics[J]. Chin J Magn Reson Imaging, 2022, 13(11): 157-160.本文引用格式:白晶晶, 张璐, 王效春, 等. 基于多参数磁共振成像的影像组学在膀胱癌精准诊疗中的研究进展[J]. 磁共振成像, 2022, 13(11): 157-160. DOI:10.12015/issn.1674-8034.2022.11.032.


[摘要] 膀胱癌(bladder cancer, BCa)发病率居全球泌尿系统恶性肿瘤前列,具有高复发率和高死亡率等特点,早期精准诊断BCa病理分级、淋巴结转移、肌层浸润对于治疗决策制订和疗效及预后评估具有重要作用。多参数磁共振成像(multiparameter magnetic resonance imaging, mpMRI)以其较高的软组织分辨率和结构功能多层次信息呈现,为BCa早期精准诊断提供了关键成像手段。近年来,随着影像组学智能诊断技术的发展,磁共振影像组学挖掘隐藏在多序列图像中的微观尺度信息,在肿瘤诊断、疗效评估、预后预测方面具有重要的临床应用价值。本文系统综述了mpMRI影像组学在BCa术前分级预测、淋巴结转移、肌层浸润和疗效及预后评估等方面的研究进展。
[Abstract] The incidence of bladder cancer (BCa) ranks among the forefront of urinary system malignancies in the world, with high recurrence rate and high mortality rate. Early and accurate diagnosis of pathological grade, lymph node metastasis and myometrial invasion of bladder cancer plays an important role in treatment decision making and prognosis evaluation of efficacy. Multiparameter magnetic resonance imaging (mpMRI) provides a key imaging method for early and accurate diagnosis of bladder cancer due to its high soft tissue resolution and multi-level information of structure and function.In recent years, with the development of intelligent diagnostic technology of radiomics, MRI radiomics has important clinical application value in tumor diagnosis, efficacy evaluation and prognosis prediction by mining micro-scale information hidden in multi-sequence images. This article provides a systematic review of the progress of mpMRI radiomics in preoperative grade prediction of bladder cancer, lymph node metastasis, myometrial invasion and prognosis evaluation of efficacy.
[关键词] 膀胱癌;病理分级;淋巴结转移;肌层浸润;疗效评估;预后;多参数磁共振成像;影像组学;磁共振成像
[Keywords] bladder cancer;pathological grading;lymph node metastasis;myometrial invasion;curative effect evaluation;prognosis;multiparameter magnetic resonance imaging;radiomics;magnetic resonance imaging

白晶晶 1, 2   张璐 1, 2   王效春 1, 2   杨国强 1, 2*  

1 山西医科大学第一医院磁共振影像科,太原 030001

2 山西医科大学医学影像学院,太原 030001

杨国强,E-mail:doctor_ygq@163.com

作者利益冲突声明:全体作者均声明无利益冲突。


基金项目: 国家自然科学基金 81971592
收稿日期:2022-06-08
接受日期:2022-10-12
中图分类号:R445.2  R737.14 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2022.11.032
本文引用格式:白晶晶, 张璐, 王效春, 等. 基于多参数磁共振成像的影像组学在膀胱癌精准诊疗中的研究进展[J]. 磁共振成像, 2022, 13(11): 157-160. DOI:10.12015/issn.1674-8034.2022.11.032.

       膀胱癌(bladder cancer, BCa)是发生在膀胱黏膜上的恶性肿瘤,占我国泌尿生殖系肿瘤发病率第一位,是老年男性泌尿系统最常见的恶性肿瘤[1, 2, 3]。大多数BCa是尿路上皮细胞癌,在组织学上可分为低级别和高级别肿瘤;根据肿瘤是否存在肌层浸润可以分为非肌层浸润性膀胱癌(non-muscle-invasive bladder cancer, NMIBC)和肌层浸润性膀胱癌(muscle-invasive bladder cancer, MIBC)[4]。目前光学膀胱镜[5]和经尿道活检是确定BCa的临床金标准,然而由于肿瘤的时空异质性,经尿道活检技术的差异可能导致误诊[6],因此临床迫切需要一种具有较高敏感性和特异性的无创诊断工具来实现BCa的精准诊断。

       MRI具有多序列成像、软组织分辨率高、结构和功能多层次信息呈现等优点[7, 8, 9]。研究发现多参数磁共振成像(multiparameter magnetic resonance imaging, mpMRI)相比单序列成像在鉴别高、低级别肿瘤中更有优势[10]。结合T2加权成像(T2 weighted imaging, T2WI)、扩散加权成像(diffusion-weighted imaging, DWI)、表观扩散系数(apparent diffusion coefficient, ADC)和动态对比增强(dynamic contrast enhancement, DCE),mpMRI已被证实可以改善肿瘤检测和局部分期[11]、监测肿瘤治疗反应等[12, 13, 14]。2018年,膀胱成像报告和数据系统(Vesical Imaging Reporting and Data System, VI-RADS)发布,用以标准化mpMRI诊断报告[15]。VI-RADS 可以改善经尿道膀胱肿瘤切除术(transurethral rescetion of bladder tumor, TURBT)候选患者的选择[16, 17],在准确鉴别肌层浸润和分级诊断方面具有良好的敏感性和特异性[18, 19]。影像组学(radiomics)通过提取肿瘤高维影像特征来描述肿瘤表型和异质性等深层信息,是指导BCa临床决策的一种智能影像新方法[20, 21, 22]。mpMRI影像组学挖掘隐藏在多序列图像中的微观尺度信息,如体素强度变化、病变形状特征、纹理模式以及高维滤波特征,在肿瘤诊断、疗效评估、预后预测方面具有重要的应用。目前,已有多项研究表明mpMRI影像组学方法可以精准地对BCa进行术前分级预测和肌层浸润评估,进而指导临床治疗及评估患者预后[23, 24, 25]。然而,mpMRI图像信息的深度挖掘组合以及模型的有效性和可重复性仍需要进一步研究探讨。本文系统介绍了mpMRI影像组学方法流程及其在BCa术前分级、淋巴结转移、肌层浸润、疗效及预后预测方面的研究进展。

1 mpMRI影像组学概念及方法流程

       影像组学概念于2012年由荷兰学者Lambin等[26]首次提出,概念提出基于以下假说:微观基因或蛋白的改变会在宏观影像上有所表达,进而可以通过影像组学特征进行定量刻画。经过近十年的发展,影像组学研究领域不断拓展,利用计算机图像处理和大数据挖掘手段获取医学图像中无法被人眼直接识别的影像特征,挖掘影像中蕴含的肿瘤分级、肌层浸润、疗效及预后等信息,指导精准的诊疗决策。

       影像组学的工作流程包括:(1)图像采集,影像组学可以分析CT、MRI、超声、正电子发射体层成像(positron emission tomography, PET)等多种模态的医学影像数据,图像采集方案的一致性和标准化将直接影响影像组学特征和模型的稳定性和可重复性。(2)病灶分割,分为手动分割、计算机自动分割和半自动分割,目的是从每位患者的医学图像中勾画出肿瘤或其他典型病灶的感兴趣区(region of interest, ROI)。(3)特征提取,针对图像的ROI进行影像组学特征提取,包括刻画病灶区域形态的形状特征组、量化信号非均质性的强度特征组、反映组织微观异质性的纹理特征组及人眼无法直接识别的高维滤波特征组。(4)特征筛选,采用最小绝对收缩和选择算子(least absolute shrinkage and selection operator, LASSO)和最大相关和最小冗余(max-relevance and min-redundancy, mRMR)等多种特征降维算法筛选与预测目标高度相关、稳定性高和重复性好的最优特征子集。(5)模型构建及验证,基于筛选后的影像组学特征,采用支持向量机(support vector machine, SVM)、logistic回归、随机森林(random forest, RF)等多种机器学习分类器构建预测模型,采用受试者工作特征曲线下面积(area under the curve, AUC)、准确率、敏感度、特异度、一致性系数等指标评估模型的诊断预测效能。影像组学方法流程的标准化将直接影响预测模型的稳定性、可重复性和临床适用性,是目前亟待解决的关键问题。

2 mpMRI影像组学在BCa精准诊疗中的应用现状

       根据欧洲泌尿外科协会(the European Association of Urology, EAU)指南[27, 28],病理分级、肌层浸润状态以及淋巴结有无转移是BCa临床诊疗的重要因素。基于mpMRI的影像组学技术通过深度挖掘图像背后隐藏的疾病特征和肿瘤异质性信息,在BCa术前精准诊断、术后疗效及预后评估和复发风险监测方面显示出巨大的潜力。

2.1 病理分级预测

       BCa精准分级对患者治疗决策制订和疗效及预后评估起着重要作用[29],多项研究表明基于MRI影像组学分析在BCa病理分级预测方面具有潜在价值。Zhang等[10]提出一种基于影像组学纹理分析进行BCa分级的策略,从61例患者术前DWI和ADC图像中提取102个纹理特征,基于筛选后的最优特征子集采用SVM算法构建BCa病理分级预测模型,AUC和准确率分别为0.861和82.9%。表明MRI图像的纹理特征,特别是ADC图像的直方图特征和灰度共生矩阵(gray-level co-occurrence matrix, GLCM)特征可以反映高、低级别BCa的差异,在BCa病理分级预测中获得了较好效能。Wang等[30]从70例BCa患者术前T2WI、DWI和ADC图像的肿瘤实质区提取影像组学特征,采用多变量logistic回归建立影像组学模型。结果显示多参数模型显著优于单一序列模型,获得了更高的分级预测效能(AUC达到0.923)。表明基于mpMRI影像组学方法相比单序列成像更有潜力作为BCa术前精准分级的无创评估工具,但仍需多中心验证才能获得其临床应用的高水平证据。为了进一步研究影像组学在BCa术前分级预测中的价值,Zheng等[31]提出一种整合mpMRI影像组学特征和VI-RADS评分进行BCa术前分级预测的策略,从185例BCa患者的术前DCE和T2WI图像的肿瘤ROI中提取影像组学特征,发现整合VI-RADS评分建立的影像组学-临床列线图在训练集(AUC=0.956)和验证集(AUC=0.958)中均获得了最佳预测效能,表明VI-RADS评分和影像组学相结合更有助于提高术前精准分级能力。

       上述研究均表明mpMRI影像组学方法可以对BCa进行术前精准病理分级预测,且多序列的影像组学特征相比单序列影像组学特征在BCa精准分级中更具有优势,但现有研究样本量较小,未来仍需扩大样本量来进一步验证模型的有效性。

2.2 淋巴结转移预测

       淋巴结有无转移是BCa患者的另一项关键预后指标。在接受外科治疗的BCa患者中,淋巴结转移的发生率约为27%[32],发生淋巴结转移患者的五年总生存率(15%~31%)远低于未发生淋巴结转移患者(>60%)。近年来,影像组学方法已被证实能够更好地术前预测BCa淋巴结转移状态。Wu等[22]基于BCa患者的动脉期CT图像进行影像组学分析,发现包含影像组学特征和CT报告的影像组学列线图在训练集(AUC=0.9262)和验证集(AUC=0.8986)中对BCa患者淋巴结转移预测具有较高的准确性。其随后的另一项研究[33]证实了MRI影像组学特征在BCa淋巴结转移预测中的价值。从103例BCa患者T2WI图像的肿瘤ROI提取718个影像组学特征,运用LASSO算法筛选特征并构建影像组学标签,整合临床风险因素和影像组学标签构建影像组学列线图,结果显示列线图在训练集和验证集中均显示出良好的淋巴结转移预测能力(AUC分别为0.9118和0.8902)。表明影像组学有望成为术前预测BCa淋巴结转移的一种无创工具。

       尽管目前MRI影像组学在BCa淋巴结转移预测中的研究很少,且仅采用了T2WI序列进行影像组学分析,但初步结果表明影像组学特征结合临床风险因素构建的模型可以有效预测BCa淋巴结转移状态。未来基于多序列MRI图像的深入挖掘及组合有望进一步提升模型的预测效能。

2.3 肌层浸润预测

       BCa分为肌层浸润性和非肌层浸润性,术前肌层浸润的准确诊断是患者诊疗过程中的关键环节[34]。近年来,较多研究通过联合mpMRI影像组学方法预测BCa肌层浸润状态。Xu等[35]回顾性研究54例BCa患者数据,从T2WI、DWI和ADC图像的肿瘤ROI提取1104个影像组学特征,发现采用递归特征消除和合成少数过采样技术的SVM算法构建的肌层浸润预测模型的分类性能最好,敏感度、特异度、准确率和AUC分别为92.60%、100.00%、96.30%和0.9857,优于影像专家诊断。并得出mpMRI最优特征子集比单一T2WI特征子集构建的模型在识别肌层浸润方面具有更好的性能。Zheng等[36]从T2WI图像的膀胱肿瘤和病变基底区域提取影像组学特征,发现结合影像组学特征和临床风险因素开发的影像组学列线图在训练集和验证集中均显示出良好的校准和鉴别能力(AUC分别为0.922和0.876),表明基于肿瘤和基底区域的影像组学分析结合临床风险因素后可以提高术前鉴别MIBC和NMIBC的准确性。徐肖攀等[4]研究发现基于T2WI、DWI和ADC的影像组学分析在术前定量表征BCa肌层浸润方面具有潜能,且基于DWI和ADC序列构建的预测模型对肌层浸润的预测效能明显优于基于T2WI序列构建的模型,更能有效反映NMIBC与MIBC的差异。董琪等[23]基于106例BCa患者的T2WI、DWI和ADC图像,对肿瘤区域提取5类影像组学特征,结果显示利用logistic回归方法对筛选后的36个影像组学特征构建的预测模型在鉴别肌层浸润方面效能良好(准确率=84.7%,AUC=0.880)。

       目前,VI-RADS评分系统也可以有效评估BCa的肌层浸润状态,是BCa影像学研究领域的热点。Barchetti等[37]采用VI-RADS对78例BCa患者mpMRI的每个病变进行评分,发现结合VI-RADS评分的mpMRI在鉴别MIBC和NMIBC方面具有更高的敏感性和特异性。Zheng等[38]采用LASSO、SVM和RF三种机器学习算法分别基于T2WI特征子集构建肌层浸润预测模型,发现三种算法中LASSO回归算法在训练集(准确率=90.7%,AUC=0.934)和验证集(准确率=87.5%,AUC=0.906)中均具有最好的预测效能。同时,整合VI-RADS评分和影像组学评分的列线图提高了术前鉴别BCa肌层浸润的准确性,该列线图的预测效能优于基于MRI图像和临床风险因素的列线图[6, 36]。目前已有大量研究[39, 40, 41]通过不同方式利用VI-RADS评分进行肌层浸润的评估和预测,将基于影像医师诊断的VI-RADS评分与基于计算机图像处理的影像组学方法相结合将促进BCa肌层浸润的术前精准诊断。

       上述多项研究均证实mpMRI影像组学在BCa肌层浸润预测中具有重要的临床应用价值,且平扫、增强、DWI等多序列MRI图像信息的深入挖掘是模型诊断效能取得不断提升的关键,未来将影像组学与VI-RADS评分相结合的人机交互式联合诊断将有望全面提升BCa肌层浸润的术前精准诊断水平。

2.4 疗效及预后预测

       BCa患者术后复发率较高,MIBC患者2年内复发率高达5%~50%,NMIBC患者经TURBT术后2年内复发率可达61%[21,42, 43]。因此,亟须一种更精准的复发风险预测模型辅助临床决策。杜鹏等[44]基于mpMRI影像组学特征,采用SVM算法构建预测模型进行复发预测,结果发现从DWI和ADC序列中提取的影像组学特征对BCa复发的预测效能优于T2WI序列。Xu等[21]基于SVM的递归特征消除方法和逻辑回归方法建立了影像组学模型用于术后个体化预测BCa复发风险,结果显示由两个独立预测因子即肌层浸润状态和影像组学评分Radscore构成的列线图在训练集(准确率=88%,AUC=0.915)和验证集(准确率=80.95%,AUC=0.838)中均显示出良好效能,基于mpMRI的影像组学列线图在术前预测BCa复发方面具有巨大潜能。Zhang等[45]开发了一种基于DWI的影像组学预测模型来评估MIBC患者的无进展生存期(progression-free survival, PFS),通过分析210例MIBC患者术前DWI图像,利用LASSO回归算法构建影像组学列线图,发现影像组学特征与PFS显著相关(P=0.0073),与临床及病理风险因素独立相关(P=0.0004)。决策曲线分析表明,影像组学列线图在个体化预测PFS方面具有更好的临床实用性。

       多参数联合建立的影像组学模型在BCa疗效及预后评估中获得了较好的预测效果。然而,疗效及预后的精准评估需要临床、影像、病理甚至基因等多维度的信息挖掘,未来基于上述信息的多组学研究将有望进一步全面精准评估患者疗效及预后。

3 局限性与展望

       影像组学作为一种集计算机图像处理与机器学习为一体的辅助诊断技术,为BCa精准诊断和疗效及预后评估提供了无创可行的新方法。但是,目前MRI影像组学尚处于验证性研究阶段,并未广泛应用于实际临床工作中。主要考虑存在以下几点限制:(1)目前研究多为小样本、单中心,且存在不平衡数据,其预测价值尚有待进一步研究证实,未来应增大样本数据,进行多中心、前瞻性验证,并发展更好的数据均衡化处理方法。(2)目前基于mpMRI成像特点,扫描参数、图像后处理方法、多序列图像配准等仍缺乏标准化,已有研究提出了影像生物标志物标准化倡议(image bio-marker standardization initiative, IBSI),验证了一套基于共识的影像组学特征参考值,提出了采集协议和数据分析标准化流程建议[46]。未来研究应进一步加强图像采集和处理的标准化,促进国际相应标准规范共识。(3)BCa的分子分型[47, 48]比传统组织病理学分型更能反映肿瘤内在特征和发展机制,并为临床早期诊断和个体化治疗方案的选择提供理论依据,是目前BCa临床和基础研究领域的热点话题。然而,目前基于MRI影像组学方法预测BCa分子分型的研究甚少,以无创的影像学方法术前早期评估BCa基因和蛋白的表达水平,促进其精准诊疗将是未来发展趋势。

       综上所述,随着影像组学技术的发展,MRI打破常规技术局限性,深入挖掘隐藏在图像中的BCa病理分级、肌层浸润、淋巴结转移以及疗效及预后等关键诊疗信息,不仅可用于患者分层的治疗计划制订和疾病进展监测,也为BCa的术前评估和精准诊疗提供了显著的潜在好处。相信未来随着深度学习[49]和人工智能[50]研究的深入,一定会有更准确的、自动化的影像组学模型为BCa患者做出更精准的诊断预测,从而更好地指导临床决策。

[1]
Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2018, 68(6): 394-424. DOI: 10.3322/caac.21492.
[2]
Siegel R, Miller K, Fuchs HE, et al. Cancer statistics, 2021[J]. CA A Cancer J Clin, 2021, 71: 7-33. DOI: 10.3322/caac.21654.
[3]
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. DOI: 10.3322/caac.21660.
[4]
徐肖攀, 杜鹏, 徐桓, 等. 基于多模态MRI影像组学策略构建膀胱癌肌层浸润预测模型研究[J]. 中国医学装备, 2020, 17(9): 5-9.
Xu XP, Du P, Xu H, et al. Study on constructing prediction model of muscle-invasive status of bladder cancer based on multimodal MRI radiomics strategy[J]. China Med Equip, 2020, 17(9): 5-9.
[5]
Alfred Witjes J, Lebret T, Compérat EM, et al. Updated 2016 EAU guidelines on muscle-invasive and metastatic bladder cancer[J]. Eur Urol, 2017, 71(3): 462-475. DOI: 10.1016/j.eururo.2016.06.020.
[6]
Wang HJ, Xu XP, Zhang X, et al. Elaboration of a multisequence MRI-based radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer: a double-center study[J]. Eur Radiol, 2020, 30(9): 4816-4827. DOI: 10.1007/s00330-020-06796-8.
[7]
Yuan LH, Li DY, Mu D, et al. Combined T2 SPAIR, Dynamic Enhancement and DW Imaging Reliably Detect T Staging and Grading of Bladder Cancer With 3.0T MRI[J/OL]. Front Oncol, 2020, 10 [2022-09-21]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7683786/pdf/fonc-10-582532.pdf. DOI: 10.3389/fonc.2020.582532.
[8]
Wang XY, Tu N, Sun F, et al. Detecting muscle invasion of bladder cancer using a proposed magnetic resonance imaging strategy[J]. J Magn Reson Imaging, 2021, 54(4): 1212-1221. DOI: 10.1002/jmri.27676.
[9]
Hammouda K, Khalifa F, Soliman A, et al. A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging[J/OL]. Comput Med Imaging Graph, 2021, 90 [2022-09-21]. https://www.sciencedirect.com/science/article/abs/pii/S0895611121000604. DOI: 10.1016/j.compmedimag.2021.101911.
[10]
Zhang X, Xu XP, Tian Q, et al. Radiomics assessment of bladder cancer grade using texture features from diffusion-weighted imaging[J]. J Magn Reson Imaging, 2017, 46(5): 1281-1288. DOI: 10.1002/jmri.25669.
[11]
Cornelissen SWE, Veenboer PW, Wessels FJ, et al. Diagnostic Accuracy of Multiparametric MRI for Local Staging of Bladder Cancer: A Systematic Review and Meta-Analysis[J/OL]. Urology, 2020, 145 [2022-09-21]. https://www.sciencedirect.com/science/article/pii/S0090429520308827. DOI: 10.1016/j.urology.2020.07.021.
[12]
van der Pol CB, Sahni VA, Eberhardt SC, et al. ACR appropriateness criteria® pretreatment staging of muscle-invasive bladder cancer[J]. J Am Coll Radiol, 2018, 15(5): S150-S159. DOI: 10.1016/j.jacr.2018.03.020.
[13]
de Haas RJ, Steyvers MJ, Fütterer JJ. Multiparametric MRI of the bladder: ready for clinical routine?[J]. AJR Am J Roentgenol, 2014, 202(6): 1187-1195. DOI: 10.2214/AJR.13.12294.
[14]
Akcay A, Yagci AB, Celen S, et al. VI-RADS score and tumor contact length in MRI: A potential method for the detection of muscle invasion in bladder cancer[J/OL]. Clin Imaging, 2021, 77 [2022-09-21]. https://www.clinicalimaging.org/article/S0899-7071(21)00083-8. DOI: 10.1016/j.clinimag.2021.02.026.
[15]
Panebianco V, Narumi Y, Altun E, et al. Multiparametric magnetic resonance imaging for bladder cancer: development of VI-RADS (vesical imaging-reporting and data system)[J]. Eur Urol, 2018, 74(3): 294-306. DOI: 10.1016/j.eururo.2018.04.029.
[16]
del Giudice F, Barchetti G, de Berardinis E, et al. Prospective assessment of vesical imaging reporting and data system (VI-RADS) and its clinical impact on the management of high-risk non-muscle-invasive bladder cancer patients candidate for repeated transurethral resection[J]. Eur Urol, 2020, 77(1): 101-109. DOI: 10.1016/j.eururo.2019.09.029.
[17]
Taguchi S, Watanabe M, Tambo M, et al. Proposal for a New Vesical Imaging-Reporting and Data System (VI-RADS)-Based Algorithm for the Management of Bladder Cancer: A Paradigm Shift From the Current Transurethral Resection of Bladder Tumor (TURBT)-Dependent Practice[J/OL]. Clin Genitourin Cancer, 2022, 22 [2022-09-21]. https://linkinghub.elsevier.com/retrieve/pii/S1558-7673(22)00047-7. DOI: 10.1016/j.clgc.2022.03.002.
[18]
Panebianco V, Pecoraro M, del Giudice F, et al. VI-RADS for bladder cancer: current applications and future developments[J]. J Magn Reson Imaging, 2022, 55(1): 23-36. DOI: 10.1002/jmri.27361.
[19]
Pizzi AD, Mastrodicasa D, Marchioni M, et al. Bladder cancer: do we need contrast injection for MRI assessment of muscle invasion? A prospective multi-reader VI-RADS approach[J]. Eur Radiol, 2021, 31(6): 3874-3883. DOI: 10.1007/s00330-020-07473-6.
[20]
Park KJ, Lee JL, Yoon SK, et al. Radiomics-based prediction model for outcomes of PD-1/PD-L1 immunotherapy in metastatic urothelial carcinoma[J]. Eur Radiol, 2020, 30(10): 5392-5403. DOI: 10.1007/s00330-020-06847-0.
[21]
Xu XP, Wang HJ, Du P, et al. A predictive nomogram for individualized recurrence stratification of bladder cancer using multiparametric MRI and clinical risk factors[J]. J Magn Reson Imaging, 2019, 50(6): 1893-1904. DOI: 10.1002/jmri.26749.
[22]
Wu SX, Zheng JJ, Li Y, et al. A radiomics nomogram for the preoperative prediction of lymph node metastasis in bladder cancer[J]. Clin Cancer Res, 2017, 23(22): 6904-6911. DOI: 10.1158/1078-0432.CCR-17-1510.
[23]
董琪, 张静, 王焕军, 等. 基于术前多模态磁共振影像组学Radscore的膀胱癌肌层浸润性预测[J]. 中国医学装备, 2021, 18(6): 17-21. DOI: 10.3969/J.ISSN.1672-8270.2021.06.006.
Dong Q, Zhang J, Wang HJ, et al. Prediction on muscle-invasive status of bladder cancer based on the preoperative multimodal MRI omics Radscore[J]. China Med Equip, 2021, 18(6): 17-21. DOI: 10.3969/J.ISSN.1672-8270.2021.06.006.
[24]
Wang HJ, Pui MH, Guan J, et al. Comparison of early submucosal enhancement and tumor stalk in staging bladder urothelial carcinoma[J]. AJR Am J Roentgenol, 2016, 207(4): 797-803. DOI: 10.2214/AJR.16.16283.
[25]
Luo C, Huang B, Wu YK, et al. Use of Vesical Imaging-Reporting and Data System (VI-RADS) for detecting the muscle invasion of bladder cancer: a diagnostic meta-analysis[J]. Eur Radiol, 2020, 30(8): 4606-4614. DOI: 10.1007/s00330-020-06802-z.
[26]
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.
[27]
Babjuk M, Böhle A, Burger M, et al. EAU guidelines on non-muscle-invasive urothelial carcinoma of the bladder: update 2016[J]. Eur Urol, 2017, 71(3): 447-461. DOI: 10.1016/j.eururo.2016.05.041.
[28]
Witjes JA, Bruins HM, Cathomas R, et al. European association of urology guidelines on muscle-invasive and metastatic bladder cancer: summary of the 2020 guidelines[J]. Eur Urol, 2021, 79(1): 82-104. DOI: 10.1016/j.eururo.2020.03.055.
[29]
Cai Q, Wen ZH, Huang YP, et al. Investigation of synthetic magnetic resonance imaging applied in the evaluation of the tumor grade of bladder cancer[J]. J Magn Reson Imaging, 2021, 54(6): 1989-1997. DOI: 10.1002/jmri.27770.
[30]
Wang HJ, Hu DK, Yao HH, et al. Radiomics analysis of multiparametric MRI for the preoperative evaluation of pathological grade in bladder cancer tumors[J]. Eur Radiol, 2019, 29(11): 6182-6190. DOI: 10.1007/s00330-019-06222-8.
[31]
Zheng ZT, Xu FJ, Gu ZR, et al. Integrating multiparametric MRI radiomics features and the Vesical Imaging-Reporting and Data System (VI-RADS) for bladder cancer grading[J]. Abdom Radiol (NY), 2021, 46(9): 4311-4323. DOI: 10.1007/s00261-021-03108-6.
[32]
Gschwend JE, Heck MM, Lehmann J, et al. Extended versus limited lymph node dissection in bladder cancer patients undergoing radical cystectomy: survival results from a prospective, randomized trial[J]. Eur Urol, 2019, 75(4): 604-611. DOI: 10.1016/j.eururo.2018.09.047.
[33]
Wu SX, Zheng JJ, Li Y, et al. Development and Validation of an MRI-Based Radiomics Signature for the Preoperative Prediction of Lymph Node Metastasis in Bladder Cancer[J/OL]. EBio Medicine, 2018, 34 [2022-09-21]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6116473. DOI: 10.1016/j.ebiom.2018.07.029.
[34]
Wang HJ, Luo C, Zhang F, et al. Multiparametric MRI for bladder cancer: validation of VI-RADS for the detection of detrusor muscle invasion[J]. Radiology, 2019, 291(3): 668-674. DOI: 10.1148/radiol.2019182506.
[35]
Xu XP, Zhang X, Tian Q, et al. Quantitative identification of nonmuscle-invasive and muscle-invasive bladder carcinomas: a multiparametric MRI radiomics analysis[J]. J Magn Reson Imaging, 2019, 49(5): 1489-1498. DOI: 10.1002/jmri.26327.
[36]
Zheng JJ, Kong JQ, Wu SX, et al. Development of a noninvasive tool to preoperatively evaluate the muscular invasiveness of bladder cancer using a radiomics approach[J]. Cancer, 2019, 125(24): 4388-4398. DOI: 10.1002/cncr.32490.
[37]
Barchetti G, Simone G, Ceravolo I, et al. Multiparametric MRI of the bladder: inter-observer agreement and accuracy with the Vesical Imaging-Reporting and Data System (VI-RADS) at a single reference center[J]. Eur Radiol, 2019, 29(10): 5498-5506. DOI: 10.1007/s00330-019-06117-8.
[38]
Zheng ZT, Xu FJ, Gu ZR, et al. Combining Multiparametric MRI Radiomics Signature With the Vesical Imaging-Reporting and Data System (VI-RADS) Score to Preoperatively Differentiate Muscle Invasion of Bladder Cancer[J/OL]. Front Oncol, 2021, 11 [2022-09-21]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8155615. DOI: 10.3389/fonc.2021.619893.
[39]
Delli Pizzi A, Mastrodicasa D, Taraschi A, et al. Conspicuity and muscle-invasiveness assessment for bladder cancer using VI-RADS: a multi-reader, contrast-free MRI study to determine optimal b-values for diffusion-weighted imaging[J]. Abdom Radiol (NY), 2022, 47(5): 1862-1872. DOI: 10.1007/s00261-022-03490-9.
[40]
Jazayeri SB, Dehghanbanadaki H, Hosseini M, et al. Diagnostic accuracy of vesical imaging-reporting and data system (VI-RADS) in suspected muscle invasive bladder cancer: a systematic review and diagnostic meta-analysis[J]. Urol Oncol, 2022, 40(2): 45-55. DOI: 10.1016/j.urolonc.2021.11.008.
[41]
Hong SB, Lee NK, Kim S, et al. Vesical imaging-reporting and data system for multiparametric MRI to predict the presence of muscle invasion for bladder cancer[J]. J Magn Reson Imaging, 2020, 52(4): 1249-1256. DOI: 10.1002/jmri.27141.
[42]
Soukup V, Čapoun O, Cohen D, et al. Risk stratification tools and prognostic models in non-muscle-invasive bladder cancer: a critical assessment from the European association of urology non-muscle-invasive bladder cancer guidelines panel[J]. Eur Urol Focus, 2020, 6(3): 479-489. DOI: 10.1016/j.euf.2018.11.005.
[43]
Cambier S, Sylvester RJ, Collette L, et al. EORTC Nomograms and Risk Groups for Predicting Recurrence, Progression, and Disease-specific and Overall Survival in Non-Muscle-invasive Stage Ta-T1 Urothelial Bladder Cancer Patients Treated with 1-3 Years of Maintenance Bacillus Calmette-Guérin[J/OL]. Eur Urol, 2016, 69(1) [2022-09-21]. https://www.sciencedirect.com/science/article/abs/pii/S0302283815005564. DOI: 10.1016/j.eururo.2015.06.045.
[44]
杜鹏, 王焕军, 石宇强, 等. 基于多参数磁共振成像影像组学特征的膀胱癌复发预测[J]. 中国医学装备, 2018, 15(11): 39-43. DOI: 10.3969/J.ISSN.1672-8270.2018.11.011.
Du P, Wang HJ, Shi YQ, et al. Prediction on the relapse of BC based on radiomics approach with multi-parametric MRI[J]. China Med Equip, 2018, 15(11): 39-43. DOI: 10.3969/J.ISSN.1672-8270.2018.11.011.
[45]
Zhang SH, Song MF, Zhao YS, et al. Radiomics nomogram for preoperative prediction of progression-free survival using diffusion-weighted imaging in patients with muscle-invasive bladder cancer[J/OL]. Eur J Radiol, 2020, 131 [2022-09-21]. https://www.ejradiology.com/article/S0720-048X(20)30408-3. DOI: 10.1016/j.ejrad.2020.109219.
[46]
Zwanenburg A, Vallières M, Abdalah MA, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping[J]. Radiology, 2020, 295(2): 328-338. DOI: 10.1148/radiol.2020191145.
[47]
张国文. 膀胱癌分子分型的研究进展[J]. 临床与病理杂志, 2021, 41(5): 1151-1156. DOI: 10.3978/j.issn.2095-6959.2021.05.027.
Zhang GW. Research progress on molecular subtypings of bladder cancer[J]. J Clin Pathol Res, 2021, 41(5): 1151-1156. DOI: 10.3978/j.issn.2095-6959.2021.05.027.
[48]
Zhu HL, Jia XC, Wang YP, et al. M6A Classification Combined With Tumor Microenvironment Immune Characteristics Analysis of Bladder Cancer[J/OL]. Front Oncol, 2021, 11 [2022-09-21]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8479184. DOI: 10.3389/fonc.2021.714267.
[49]
Velmahos CS, Badgeley M, Lo YC. Using deep learning to identify bladder cancers with FGFR-activating mutations from histology images[J]. Cancer Med, 2021, 10(14): 4805-4813. DOI: 10.1002/cam4.4044.
[50]
Loeffler CML, Ortiz Bruechle N, Jung M, et al. Artificial intelligence-based detection of FGFR3 mutational status directly from routine histology in bladder cancer: a possible preselection for molecular testing?[J]. Eur Urol Focus, 2022, 8(2): 472-479. DOI: 10.1016/j.euf.2021.04.007.

上一篇 影像组学在胰腺导管内乳头状黏液性肿瘤中的应用及研究进展
下一篇 中医康复疗法干预膝骨关节炎的脑网络机制研究进展
  
诚聘英才 | 广告合作 | 免责声明 | 版权声明
联系电话:010-67113815
京ICP备19028836号-2