分享:
分享到微信朋友圈
X
临床研究
基于DCE-MRI影像组学特征联合ADC值预测乳腺癌Ki-67表达水平
韩剑剑 马文俊 马培旗 谢玉海

HAN J J, MA W J, MA P Q, et al. Imaging radiomics features based on DCE-MRI combined with ADC in predicting expression level of Ki-67 in breast cancer[J]. Chin J Magn Reson Imaging, 2023, 14(8): 63-67, 85.引用本文:韩剑剑, 马文俊, 马培旗, 等. 基于DCE-MRI影像组学特征联合ADC值预测乳腺癌Ki-67表达水平[J]. 磁共振成像, 2023, 14(8): 63-67, 85. DOI:10.12015/issn.1674-8034.2023.08.010.


[摘要] 目的 探讨动态对比增强MRI(dynamic contrast-enhanced MRI, DCE-MRI)影像组学特征联合表观扩散系数(apparent diffusion coefficient, ADC)值预测乳腺癌Ki-67表达水平的临床价值。材料与方法 回顾性分析2018年12月至2021年12月间经病理证实的234例乳腺癌患者MRI影像资料,依据术后免疫组化结果,将其分为Ki-67高表达组(n=180)和低表达组(n=54),采用半自动分割的方式从DCE-MRI第1期增强图像中提取瘤体1906个组学特征,采用组内相关系数(intra-class correlation coefficient, ICC)、特征间线性相关性分析和最小绝对收缩与选择算子(least absolute shrinkage and selection operator, LASSO)最终筛选出4个最优特征构建影像组学模型,采用受试者工作特征(receiver operating characteristic, ROC)曲线评估影像组学、平均ADC值及二者联合模型的诊断效能。并使用校准曲线及决策曲线评价预测模型的临床实用性。结果 从瘤体提取1906个特征,ICC分析剔除207个、特征间线性相关性分析剔除1626个,剩余73个特征LASSO降维筛选出4个最优组学特征。最终筛选出的4个组学特征,平均ADC值在两组间差异均有统计学意义(P<0.05)。影像组学、平均ADC值及联合模型预测Ki-67高表达的曲线下面积(area under the curve, AUC)分别为0.820、0.676和0.856,三者间的差异均有统计学意义(P<0.05),联合模型对Ki-67高表达的预测效能最佳,其AUC、敏感度和特异度分别为0.856、88.3%和74.1%,校准曲线及决策曲线显示联合模型具有临床应用价值。结论 基于DCE-MRI组学特征联合平均ADC值对乳腺癌Ki-67高表达具有较高的预测效能,联合模型优于影像组学模型及平均ADC值。
[Abstract] Objective To investigate the clinical value of imaging radiomics features based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) combined with apparent diffusion coefficient (ADC) in predicting the expression level of Ki-67 in breast cancer.Materials and Methods MRI images of 234 patients with breast cancer confirmed by pathology from December 2018 to December 2021 were retrospectively analyzed. According to postoperative immunohistochemical results, the tumors were divided into the Ki-67 high expression group (n=180) and low expression group (n=54). 1906 radiomics features were extracted form the first phase of the DCE-MRI by semi-automatic separation method. Using intraclass correlation coefficient (ICC), the linear correlation analysis and the least absolute shrinkage and selection operator (LASSO), four features were selected to construct the radiomics model. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic effectiveness of the radiomics, average ADC values and combined models. Calibration curves and decision curves were used to evaluate the clinical usefulness of the predictive model.Results A total of 1906 features were extracted from the tumor body, 207 features were excluded by ICC analysis, 1626 features were excluded by linear correlation analysis, and the remaining 73 features were selected by LASSO dimensionality reduction to select 4 optimal omics features. Four radiomics features and the average ADC values were significantly different between two groups (P<0.05). Radiomics model, the average ADC value and the combined model predicted that the area under the curve (AUC) of Ki-67 high expression were 0.820, 0.676 and 0.856, respectively, with statistically significant differences each other (P<0.05). The combined model had the best predictive efficiency for Ki-67 expression, and its AUC, sensitivity and specificity were 0.856, 88.3% and 74.1%, calibration curves and decision curves showed that the combined model had clinical application value.Conclusions The combined model which constructed by the images radiomics features based on DCE-MRI and the average ADC values has high efficacy in predicting Ki-67 expression in breast cancer.The combined model is superior to the radiomics model and the average ADC value.
[关键词] 乳腺癌;Ki-67;影像组学;动态对比增强;扩散加权成像;磁共振成像
[Keywords] breast cancer;Ki-67;radiomics;dynamic contrast-enhanced;diffusion weighted imaging;magnetic resonance imaging

韩剑剑 1   马文俊 2   马培旗 3   谢玉海 2*  

1 皖南医学院第一附属医院弋矶山医院放射科,芜湖 241000

2 太和县人民医院/皖南医学院附属太和医院放射科,阜阳 236600

3 阜阳市人民医院放射科,阜阳 236000

通信作者:谢玉海,E-mail:xyhdoctor@163.com

作者贡献声明:谢玉海设计本研究的方案,对稿件重要内容进行了修改;韩剑剑起草和撰写稿件,获取、分析或解释本研究的数据;马文俊、马培旗获取、分析或解释本研究的数据,对稿件重要内容进行了修改;谢玉海获得皖南医学院科研项目资金资助、全体作者都同意发表最后的修改稿,同意对本研究的所有方面负责,确保本研究的准确性和诚信。


基金项目: 皖南医学院科研项目 JXYY202139
收稿日期:2022-09-16
接受日期:2023-07-21
中图分类号:R445.2  R737.9 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2023.08.010
引用本文:韩剑剑, 马文俊, 马培旗, 等. 基于DCE-MRI影像组学特征联合ADC值预测乳腺癌Ki-67表达水平[J]. 磁共振成像, 2023, 14(8): 63-67, 85. DOI:10.12015/issn.1674-8034.2023.08.010.

0 前言

       在我国,女性乳腺癌的发病率和死亡率均居首位,且呈逐年上升的趋势[1, 2]。增殖指数(Ki-67)与肿瘤细胞的增殖活动有关,作为乳腺癌的常规检测指标,与其预后密切相关。裴蓓等[3]研究表明Ki-67增殖指数与腋窝淋巴结转移率呈正相关。宋旗等[4]研究表明,Ki-67的表达水平与乳腺癌患者的预后密切相关,高表达组患者的生存时间明显低于低表达组。刘杰娜等[5]研究证实Ki-67表达水平是乳腺癌患者新辅助化疗后病理学完全缓解的独立预测因素,Ki-67高表达患者病理学完全缓解率为低表达患者的4.282倍。因此,术前准确判断Ki-67的表达水平对乳腺癌患者的预后以及诊疗方案的制订具有重要的临床价值,但是,临床对于Ki-67的诊断多依赖于病理免疫组化。磁共振成像(magnetic resonance imaging, MRI)具有软组织分辨率高、多参数、多方位成像特点,近几年在乳腺疾病中的应用价值越来越得到认可[6, 7, 8]。有研究发现通过扩散加权成像(diffusion weighted imaging, DWI)定量参数分析可以评估乳腺癌的分子亚型与Ki-67增殖指数的相关性[9, 10],明洁等[11]基于动态对比增强MRI(dynamic contrast-enhanced MRI, DCE-MRI)瘤内联合瘤周影像组学模型对乳腺癌Ki-67表达具有较高的预测效能。DWI可通过检测活体组织中水分子扩散程度,从而反映肿瘤内的微观结构。而目前国内外研究者基于影像组学联合平均ADC值预测Ki-67的研究较少。因此,本研究旨在探讨基于DCE-MR第1期增强图像的组学特征联合ADC值预测乳腺癌Ki-67表达水平的预测价值,为术前无创性准确评估乳腺癌Ki-67表达状态提供新方法,从而为临床诊疗方案的制订和预后的评估提供重要的参考依据。

1 材料与方法

1.1 一般资料

       回顾性分析皖南医学院弋矶山医院2018年12月至2021年12月间经术后病理证实的女性乳腺癌患者的影像及临床资料。病例纳入标准:(1)术前有完整的MRI平扫、DWI及多期增强检查;(2)术后有完整的病理资料(包括Ki-67表达水平);(3)无其他恶性肿瘤病史。排除标准:(1)MRI检查前行手术或放化疗史;(2)图像不清晰,难以满足后期图像勾画;(3)肿瘤多发或存在转移史。Ki-67表达水平的高低参照2013年St Gallen国际乳腺癌会议专家共识[12],本研究将肿瘤细胞核着色<20%定义为低表达、≥20%定义为高表达。本研究遵守《赫尔辛基宣言》,经过皖南医学院第一附属医院弋矶山医院医学伦理委员会批准,免除受检者知情同意(批文批号:2019-KY-271)。

1.2 MRI设备及扫描参数

       所有患者均进行了常规及DCE-MRI检查,采用GE Signa HD xt 3.0 T MR扫描仪,8通道乳腺专用相控阵线圈。患者取俯卧位,双侧乳腺自然悬垂于线圈内,扫描范围为腋窝至乳腺下缘。采用轴位和矢状面扫描;LAVA T1WI扫描参数:TR 5.68 ms,TE 2.20 ms,TI 16 ms,层厚2.0 mm,层间距0 mm,FOV 340 mm× 340 mm,矩阵 348×348。增强扫描采用双筒高压注射器静脉注射对比剂钆-二乙烯三胺五乙酸(拜耳制药,德国),注射流速2.5 mL/s,剂量0.1 mmol/kg,轴位平扫后注入对比剂后即行LAVA T1WI扫描,参数同上。每期扫描60 s,扫描8期,共480 s。各序列参数见表1

表1  MRI各序列扫描参数
Tab. 1  MRI scanning parameters of each sequence

1.3 图像分析

       将所有患者MRI图像从PACS工作站以DICOM格式导出后导入深睿医疗多模态科研平台(https://keyan.deepwise.com),参照DWI和多期动态增强图像,在DCE-MRI第1期相上采用半自动分割的方式逐层勾画瘤体感兴趣区(region of interest, ROI)。ROI勾画由两位放射科医生(医师1诊断经验10年,副主任医师;医师2诊断经验6年,主治医师)分别在告知病灶位置的情况下独立完成,医师1进行两次勾画,且两次勾画间隔时间≥1周。使用ICC评估影像组学特征提取的观察者间和观察者内一致性。使用科研平台从ROI中自动提取1906个组学特征,包括一阶特征(396个)、形状特征(14个)、灰度共生矩阵特征(484个)、灰度区域矩阵特征(352个)、灰度游程矩阵特征(352个)、灰度共生矩阵(gray-level co-occurrence matrix, GLCM)特征(308个)。瘤体ADC值测量由医师1(诊断经验10年,副主任医师)在后处理工作站进行,选取肿瘤最大层面勾画ROI(图1~2),测量平均ADC值,每个病灶测量3次,取平均值。

图1  女,39岁,右乳浸润性乳腺癌,Ki-67高表达组(30%)。1A:横断面第1期DCE-MRI图像;1B:肿块ROI勾画图;1C:免疫组化染色,Ki-67高表达(+,30%)。
图2  女,68岁,右乳浸润性乳腺癌,Ki-67低表达组(5%)。2A:横断面第1期DCE-MRI图像;2B:肿块ROI勾画图;2C:免疫组化染色,Ki-67高表达(+,5%)。DCE-MRI:动态对比增强MRI;ROI:感兴趣区。
Fig. 1  39-year-old female with right breast invasive breast cancer, Ki-67 high expression group (30%). 1A: Cross-sectional the first phase of DCE-MRI. 1B: ROI mapping of lumps. 1C: Immunohistochemical staining, Ki-67 high expression (+ , 30%).
Fig. 2  68-year-old female with righr breast cancer, Ki-67 low expression group (5%). 2A: Cross-sectional the first phase of DCE-MRI. 2B: ROI mapping of lumps. 2C: Immunohistochemical staining, Ki-67 low expression (+, 5%). DCE-MRI: dynamic contrast enhanced magnetic resonance imaging; ROI: region of interest.

1.4 最优特征筛选与模型构建

       第一步将所有样本量的特征参数通过ICC筛选出一致性较好的非零组学特征(ICC>0.8)。第二步使用深睿医疗多模态科研平台,采用10折交叉验证的方法,通过特征间线性相关性分析(C=0.75)和最小绝对收缩与选择算子(least absolute shrinkage and selection operator, LASSO)算法筛选最优组学特征构建logistic回归模型。利用影像组学评分联合平均ADC值构建联合模型。

1.5 统计学方法

       特征筛选及预处理采用R软件(Version 3.6.0)进行统计分析。最优特征及平均ADC值采用SPSS 22.0统计软件包进行数据分析。计量资料采用x¯±s表示,符合正态分布的采用独立样本t检验,非正态分布采用Mann-Whitney U检验。诊断价值采用受试者工作特征(receiver operating characteristic, ROC)曲线分析。模型间的曲线下面积(area under the curve, AUC)比较采用DeLong检验对比分析。P<0.05为差异有统计学意义。

2 结果

2.1 两组间一般资料比较

       本研究依据术后病理结果分为Ki-67高表达180例和低表达54例,所有患者术前均行乳腺MRI检查及术后免疫组化检测,年龄23~78(51.50±9.58)岁。纳入本研究的234例患者均为女性,其中浸润性癌219例(Ki-67高表达176例、低表达43例),非浸润性癌15例(Ki-67高表达4例、低表达11例)。术后免疫组化标记Ki-67高表达180例,年龄23~78(50.89±9.19)岁,低表达组54例,年龄26~77(53.52±10.63)岁,两组间年龄差异无统计学意义(P=0.131)(表2)。低表达组平均ADC值为0.997±0.222、高表达组平均ADC值为0.883±0.130,两组间的差异有统计学意义(P<0.01)。

表2  乳腺癌患者临床及病理基线资料
Tab. 2  Clinical and pathological baseline data of breast cancer patients

2.2 影像组学特征筛选及模型构建

       1906个影像组学特征经ICC(剔除207个)、特征间线性相关性分析(剔除1626个)和LASSO降维(剔除69个)后共筛选出4个最优组学特征分别是log-sigma-3-0-mm-3D_firstorder_Skewness、wavelet-LHH_gldm_DependenceEntropy、original_shape_Flatness和wavelet-LLL_firstorder_Skewness(图3),采用logistic回归构建影像组学模型。

图3  影像组学分析最终筛选的4个最优特征及相关权重。
Fig. 3  The four optimal features and associated weights for the final screening by radiomics analysis.

2.3 各模型ROC曲线分析

       影像组学、平均ADC值及二者联合模型诊断乳腺癌Ki-67高表达的AUC分别为0.820、0.676和0.856,三者间的差异有统计学意义(P<0.01)(表2);DeLong检验结果显示平均ADC值与影像组学模型、平均ADC值与联合模型以及影像组学模型与联合模型之间存在显著性差异(P值分别为0.010、<0.001及0.033)。根据约登指数,当组合模型取最佳界值0.654时,其预测乳腺癌Ki-67高表达的敏感度和特异度分别为88.3%和74.1%;校准曲线及决策曲线验证了模型的临床实用性(表3图4, 5, 6)。

图4  乳腺癌Ki-67表达水平平均表观扩散系数(ADC)值、影像组学模型及联合模型的受试者工作特征曲线。
Fig. 4  Receiver operating characteristic curve of radiomics, the average apparent diffusion coefficient (ADC) value and combined model to predict Ki67 expression levels in breast cancer.
图5  乳腺癌Ki-67表达水平联合模型的校准曲线。
Fig. 5  Calibration curve of the combined model to predict Ki-67 expression levels in breast cancer.
图6  乳腺癌Ki-67表达水平的影像组学模型、平均表观扩散系数(ADC)值及联合模型的决策曲线。
Fig. 6  Decision curve of radiomics, the average apparent diffusion coefficient (ADC) value and combined model to predict Ki-67 expression levels in breast cancer.
表3  影像组学及平均ADC值预测Ki-67表达诊断效能
Tab. 3  Radiomics and average ADC values predicted the diagnostic efficacy of Ki-67 expression

3 讨论

       本研究基于动态增强影像组学模型结合平均ADC值构建联合模型预测乳腺癌Ki-67表达水平,通过提取MR T1-DCE第1期增强图像中瘤体影像组学特征联合瘤体平均ADC值构建的logistic回归模型对于乳腺癌Ki-67高表达的AUC、敏感度和特异度分别为0.856、88.3%和74.1%,联合模型的诊断效能优于影像组学模型和平均ADC值,联合模型的构建可以为临床提供一种新型无创的方法预测乳腺癌Ki-67表达水平。

3.1 影像组学模型预测乳腺癌Ki-67表达状态的价值

       影像组学是通过提取肉眼无法观察的高通量特征来预测恶性肿瘤的生物学行为,目前在乳腺癌中的应用已成为研究热点,多项研究表明,基于MRI影像组学对乳腺癌分子标志物的表达状态[13, 14, 15]、腋窝淋巴结转移的预测[16, 17, 18, 19]以及新辅助化疗的敏感性[20, 21]均具有较好的诊断效能。本研究筛选的4个最优组学特征:偏度(Skewness)2个,分别为log-sigma-3-0-mm-3D_firstorder_Skewness和wavelet-LLL_firstorder_Skewness;灰度相关矩阵特征中的依赖熵(DependenceEntropy);形状特征中的平整度(Flatness)(图3)。偏度描述图像中数据分布的不对称性,偏度越低数据分布越均匀。国内外学者研究表明恶性病变的偏度特征值高于良性病变[22, 23]。本研究结果也表明Ki-67高表达组偏度高于低表达组,这说明Ki-67高表达组强化方式多以不均匀强化为主。作者分析认为不均匀强化是由于肿瘤生长速度快,细胞发生缺血缺氧而出现坏死囊变,从而导致强化不均匀。有学者研究表明乳腺癌不均匀强化与Ki-67阳性表达呈正相关[24],闫峰山等[25]研究也表明,Ki-67高表达患者瘤体多呈不均匀强化,占比75.87%,显著高于低表达组的31.48%。依赖熵表示基于灰度相关矩阵的熵值,主要反映纹理异质性大小,值越大说明图像异质性越高[26],本研究结果发现依赖熵与Ki-67的表达水平呈正相关。Ki-67代表肿瘤细胞增殖情况,表达越高,说明增殖越活跃,从而导致肿瘤的异质性越高。

3.2 DWI预测乳腺癌Ki-67表达状态的价值

       ADC值是水分子扩散受限的定量指标,肿瘤细胞增殖越快,细胞越密集,水分子扩散运动越受限,从而导致ADC值越低,它可以敏感地衡量细胞微环境的变化[27],HOTTAT等[28]发现乳腺肿瘤ROI-ADC在DWI的显著增加预示着完全的病理和放射学反应。洪娟等[29]研究表明Ki-67的表达水平与ADC值呈明显负相关。本研究结果也进一步表明,Ki-67高表达组的平均ADC值低于低表达组,这与REN等[30]研究结果相一致。

3.3 影像组学联合ADC值预测乳腺癌Ki-67表达状态的价值

       乳腺癌是一种高度异质性肿瘤,影像组学特征有可能反映肿瘤微观结构的异质性。肿瘤Ki-67的表达水平其分化程度密切相关[31],Ki-67表达水平越高,瘤细胞分化越差,细胞核异型性越高,核/浆比越高,从而导致水分子布朗运动越受限,ADC值越低。本研究结果表明影像组学模型联合ADC值预测乳腺癌Ki-67高表达的诊断效能优于影像组学模型和平均ADC值的单一指标,差异有统计学意义。决策曲线显示联合模型较影像组学模型、ADC值有更大的净收益,因此,可以得出联合模型对乳腺癌Ki-67高表达的预测具有更高的临床应用价值。

3.4 本研究的局限性

       本研究不足之处:(1)本研究采用的单中心数据,样本量相对较少,可能导致结果的偏倚,模型的鲁棒性差,因此,后期希望进行多中心、大样本数据研究进一步改善、提高模型的诊断效能及鲁棒性;(2)本研究由于样本量较小,未纳入验证组进行验证,结果可重复性可能存在一定影响,未来进一步扩大样本量,纳入验证组进行验证;(3)本研究影像组学特征的提取采用的是半自动分割的方式,存在一定人为的误差,后期希望采用深度学习的自动分割方式进行ROI勾画,从而尽可能避免人为误差。

4 结论

       总之,基于DCE-MRI组学特征联合平均ADC值对乳腺癌Ki-67高表达具有较高的预测效能,二者的联合模型优于影像组学及平均ADC值参数,对临床诊疗方案的制订和预后的评估具有一定的参考价值。

[1]
KATSURA C, OGUNMWONYI I, KANKAM H K, et al. Breast cancer: presentation, investigation and management[J]. Br J Hosp Med, 2022, 83(2): 1-7. DOI: 10.12968/hmed.2021.0459.
[2]
DAVEY M G, HYNES S O, KERIN M J, et al. Ki-67 as a prognostic biomarker in invasive breast cancer[J/OL]. Cancers, 2021, 13(17): 4455 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34503265/. DOI: 10.3390/cancers13174455.
[3]
裴蓓, 成琳. 不同分子分型乳腺癌患者预后与淋巴结转移率的相关性分析[J]. 中国肿瘤生物治疗杂志, 2019, 26(7): 776-781. DOI: 10.3872/j.issn.1007-385x.2019.07.009.
PEI B, CHENG L. Correlation between lymph node metastasis ratio and prognosis of breast cancer with different molecular subtypes[J]. Chin J Cancer Biother, 2019, 26(7): 776-781. DOI: 10.3872/j.issn.1007-385x.2019.07.009.
[4]
宋旗, 胡友庭, 杨泳, 等. 乳腺癌组织细胞核增殖抗原的异常表达与病理特征相关性[J]. 中华实验外科杂志, 2020, 37(2): 317-320. DOI: 10.3760/cma.j.issn.1001-9030.2020.02.034.
SONG Q, HU Y T, YANG Y, et al. Correlation between expression of proliferation cell nuclear antigen protein and pathological characteristics in breast cancer[J]. Chin J Exp Surg, 2020, 37(2): 317-320. DOI: 10.3760/cma.j.issn.1001-9030.2020.02.034.
[5]
刘杰娜, 张建国, 郭宝良, 等. 乳腺癌患者Ki-67表达水平对新辅助化疗后病理学完全缓解的预测价值[J]. 中国普通外科杂志, 2018, 27(5): 608-614. DOI: 10.3978/j.issn.1005-6947.2018.05.013.
LIU J N, ZHANG J G, GUO B L, et al. Values of Ki-67 expression level in predicting pathological complete response following neoadjuvant chemotherapy in breast cancer patients[J]. Chin J Gen Surg, 2018, 27(5): 608-614. DOI: 10.3978/j.issn.1005-6947.2018.05.013.
[6]
ZHANG J, HUANG Y B, CHEN J H, et al. Potential of combination of DCE-MRI and DWI with serum CA125 and CA199 in evaluating effectiveness of neoadjuvant chemotherapy in breast cancer[J/OL]. World J Surg Oncol, 2021, 19(1): 284 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34537053/. DOI: 10.1186/s12957-021-02398-w.
[7]
BONELLI L A, CALABRESE M, BELLI P, et al. MRI versus Mammography plus Ultrasound in Women at Intermediate Breast Cancer Risk: study Design and Protocol of the MRIB Multicenter, Randomized, Controlled Trial[J/OL]. Diagnostics, 2021, 11(9): 1635 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34573983/. DOI: 10.3390/diagnostics11091635.
[8]
CHOI B B. Dynamic contrast enhanced-MRI and diffusion-weighted image as predictors of lymphovascular invasion in node-negative invasive breast cancer[J/OL]. World J Surg Oncol, 2021, 19(1): 76 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/33722246/. DOI: 10.1186/s12957-021-02189-3.
[9]
BAYSAL B, BAYSAL H, ESER M B, et al. Radiomics features based on MRI-ADC maps of patients with breast cancer: relationship with lesion size, features stability, and model accuracy[J]. Medeni Med J, 2022, 37(3): 277-288. DOI: 10.4274/MMJ.galenos.2022.70094.
[10]
ZHANG Y, ZHU Y F, ZHANG K, et al. Invasive ductal breast cancer: preoperative predict Ki-67 index based on radiomics of ADC maps[J]. Radiol Med, 2020, 125(2): 109-116. DOI: 10.1007/s11547-019-01100-1.
[11]
明洁, 陈莹, 刘莹, 等. 基于DCE-MRI瘤内联合瘤周影像组学模型术前预测乳腺癌Ki-67表达状态的价值[J]. 磁共振成像, 2022, 13(10): 132-137, 149. DOI: 10.12015/issn.1674-8034.2022.10.020.
MING J, CHEN Y, LIU Y, et al. Value of preoperative prediction of Ki-67 expression in breast cancer based on DCE-MRI intratumoral combined with peritumoral radiomics model[J]. Chin J Magn Reson Imag, 2022, 13(10): 132-137, 149. DOI: 10.12015/issn.1674-8034.2022.10.020.
[12]
GOLDHIRSCH A, WINER E P, COATES A S, et al. Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013[J]. Ann Oncol, 2013, 24(9): 2206-2223. DOI: 10.1093/annonc/mdt303.
[13]
MA M M, GAN L Y, JIANG Y, et al. Radiomics analysis based on automatic image segmentation of DCE-MRI for predicting triple-negative and nontriple-negative breast cancer[J/OL]. Comput Math Methods Med, 2021, 2021: 2140465 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34422088/. DOI: 10.1155/2021/2140465.
[14]
张成孟, 丁治民, 陈鹏, 等. 基于DCE-MRI瘤内及瘤周影像组学联合TIC分型及Ki-67预测乳腺癌患者HER-2表达[J]. 磁共振成像, 2023, 14(4): 68-75. DOI: 10.12015/issn.1674-8034.2023.04.012.
ZHANG C M, DING Z M, CHEN P, et al. Prediction of HER-2 expression in breast cancer patients based on DCE-MRI intratumor and peritumoral imaging combined with TIC typing and Ki-67[J]. Chin J Magn Reson Imag, 2023, 14(4): 68-75. DOI: 10.12015/issn.1674-8034.2023.04.012.
[15]
ZHANG S H, WANG X L, YANG Z, et al. Intra- and peritumoral radiomics model based on early DCE-MRI for preoperative prediction of molecular subtypes in invasive ductal breast carcinoma: a multitask machine learning study[J]. Front Oncol, 2022, 12: 905551 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/35814460/. DOI: 10.3389/fonc.2022.905551.
[16]
朱永琪, 纪华, 朱彦芳, 等. 术前MRI影像组学列线图对乳腺癌腋窝淋巴结转移的预测价值[J]. 磁共振成像, 2022, 13(5: 52-58. DOI: 10.12015/issn.1674-8034.2022.05.010.
ZHU Y Q, JI H, ZHU Y F, et al. Predictive value of preoperative MRI-based nomogram for axillary lymph node metastasis in breast cancer[J]. Chin J Magn Reson Imag, 2022, 13(5: 52-58. DOI: 10.12015/issn.1674-8034.2022.05.010.
[17]
姜原, 马明明, 程元甲, 等. 基于乳腺癌动态增强MRI图像的影像组学特征预测腋窝淋巴结转移的可行性研究[J]. 中华放射学杂志, 2022, 56(6: 631-635. DOI: 10.3760/cma.j.cn112149-20210810-00460.
JIANG Y, MA M M, CHENG Y J, et al. Feasibility study of predicting axillary lymph node metastasis of breast cancer using radiomics analysis based on dynamic contrast-enhanced MRI[J]. Chin J Radiol, 2022, 56(6: 631-635. DOI: 10.3760/cma.j.cn112149-20210810-00460.
[18]
ZHU Y D, YANG L, SHEN H L. Value of the application of CE-MRI radiomics and machine learning in preoperative prediction of sentinel lymph node metastasis in breast cancer[J/OL]. Front Oncol, 2021, 11: 757111 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34868967/. DOI: 10.3389/fonc.2021.757111.
[19]
YU Y F, HE Z F, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study[J/OL]. EBioMedicine, 2021, 69: 103460 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34233259/. DOI: 10.1016/j.ebiom.2021.103460.
[20]
宋德领, 崔书君, 杨飞, 等. 基于动态对比增强MRI影像组学模型预测乳腺癌新辅助化疗后非病理完全缓解[J]. 中国医学影像技术, 2021, 37(4: 547-551. DOI: 10.13929/j.issn.1003-3289.2021.04.016.
SONG D L, CUI S J, YANG F, et al. Radiomics model based on dynamic contrast-enhanced MRI for predicting breast cancer non-pathological complete response after neoadjuvant chemotherapy[J]. Chin J Med Imag Technol, 2021, 37(4: 547-551. DOI: 10.13929/j.issn.1003-3289.2021.04.016.
[21]
姚纯, 杨志企, 杨佳达, 等. 基于动态增强MRI影像组学评分和激素受体的列线图预测乳腺癌新辅助化疗不敏感的价值[J]. 国际医学放射学杂志, 2022, 45(2: 130-134. DOI: 10.19300/j.2022.L19006.
YAO C, YANG Z Q, YANG J D, et al. A nomogram based on DCE-MRI Radscore and hormone receptor status for predicting drug insensitive to neoadjuvant chemotherapy in breast cancer patients[J]. Int J Med Radiol, 2022, 45(2: 130-134. DOI: 10.19300/j.2022.L19006.
[22]
张金梅, 董江宁, 吴瑶媛, 等. 能谱CT定量参数联合纹理分析鉴别甲状腺良恶性结节的价值[J]. 实用放射学杂志, 2022, 38(7: 1069-1073. DOI: 10.3969/j.issn.1002-1671.2022.07.006.
ZHANG J M, DONG J N, WU Y Y, et al. The differential diagnostic performance of spectral CT quantitative parameters combined with texture analysis on benign and malignant thyroid nodules[J]. J Pract Radiol, 2022, 38(7: 1069-1073. DOI: 10.3969/j.issn.1002-1671.2022.07.006.
[23]
KIM D, JENSEN L J, ELGETI T, et al. Radiomics for everyone: a new tool simplifies creating parametric maps for the visualization and quantification of radiomics features[J]. Tomography, 2021, 7(3: 477-487. DOI: 10.3390/tomography7030041.
[24]
王月波, 蒲红. 乳腺癌增强MRI形态学特征及表观扩散系数值与相关分子生物学标记物的关系分析[J]. 实用放射学杂志, 2020, 36(2: 219-222. DOI: 10.3969/j.issn.1002-1671.2020.02.012.
WANG Y B, PU H. Morphological features of breast cancer enhanced MRI, ADC values and their relationships with related molecular biomarkers[J]. J Pract Radiol, 2020, 36(2: 219-222. DOI: 10.3969/j.issn.1002-1671.2020.02.012.
[25]
闫峰山, 周晶, 白岩, 等. 不同Ki-67表达状态乳腺癌患者临床和DCE-MRI特征[J]. 中国医学影像技术, 2019, 35(11: 1657-1662. DOI: 10.13929/j.1003-3289.201902066.
YAN F S, ZHOU J, BAI Y, et al. Clinical and DCE-MRI features of breast cancer in patients with different Ki-67 status[J]. Chin J Med Imag Technol, 2019, 35(11: 1657-1662. DOI: 10.13929/j.1003-3289.201902066.
[26]
王猛, 刘周, 文洁, 等. 基于T2WI-FS的影像组学特征在术前预测乳腺癌腋窝淋巴结转移中的价值[J]. 肿瘤影像学, 2022, 31(1: 28-35. DOI: 10.19732/j.cnki.2096-6210.2022.01.006.
WANG M, LIU Z, WEN J, et al. The value of radiomics features derived from the T2WI-FS assisted preoperative prediction of axillary lymph node metastasis of breast cancer[J]. Oncoradiology, 2022, 31(1: 28-35. DOI: 10.19732/j.cnki.2096-6210.2022.01.006.
[27]
CHOI B B. Effectiveness of ADC difference value on pre-neoadjuvant chemotherapy MRI for response evaluation of breast cancer[J/OL]. Technol Cancer Res Treat, 2021, 20: 15330338211039129 [2022-09-15]. https://pubmed.ncbi.nlm.nih.gov/34519583/. DOI: 10.1177/15330338211039129.
[28]
HOTTAT N A, BADR D A, LECOMTE S, et al. Value of diffusion-weighted MRI in predicting early response to neoadjuvant chemotherapy of breast cancer: comparison between ROI-ADC and whole-lesion-ADC measurements[J]. Eur Radiol, 2022, 32(6: 4067-4078. DOI: 10.1007/s00330-021-08462-z.
[29]
洪娟, 王冬青, 殷瑞根, 等. 乳腺浸润性导管癌磁共振弥散加权成像与Ki-67表达的关系[J]. 江苏大学学报(医学版), 2019, 29(5: 441-443, 455. DOI: 10.13312/j.issn.1671-7783.y190096.
HONG J, WANG D Q, YIN R G, et al. The correlation between diffusion-weighted magnetic resonance imaging and Ki-67 in invasive ductal carcinoma of breast[J]. J Jiangsu Univ Med Ed, 2019, 29(5: 441-443, 455. DOI: 10.13312/j.issn.1671-7783.y190096.
[30]
REN C C, ZOU Y, ZHANG X D, et al. Diagnostic value of diffusion-weighted imaging-derived apparent diffusion coefficient and its association with histological prognostic factors in breast cancer[J]. Oncol Lett, 2019, 18(3: 3295-3303. DOI: 10.3892/ol.2019.10651.
[31]
任爱雄, 卫美辰, 杨玉庆, 等. 血清KI-67抗原(ki67)水平检测及用于浸润性乳腺癌临床诊断的评价[J]. 细胞与分子免疫学杂志, 2020, 36(12: 1124-1128. DOI: 10.13423/j.cnki.cjcmi.009119.
REN A X, WEI M C, YANG Y Q, et al. Detection and value of serum antigen KI-67 (ki67) in clinical diagnosis of breast cancer patients[J]. Chin J Cell Mol Immunol, 2020, 36(12: 1124-1128. DOI: 10.13423/j.cnki.cjcmi.009119.

上一篇 合成MRI全容积直方图特征鉴别乳腺良恶性病变的价值
下一篇 肿块型肝内胆管细胞癌的MRI增强特征与相关病理及预后
  
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