切换至 "中华医学电子期刊资源库"

中华乳腺病杂志(电子版) ›› 2022, Vol. 16 ›› Issue (03) : 147 -154. doi: 10.3877/cma.j.issn.1674-0807.2022.03.003

论著

增强MRI影像组学在构建乳腺癌腋窝淋巴结转移预测模型中的应用研究
叶钉利1, 张涵1, 刘伊佳1, 李健轩1, 白美玉1, 赵继红1, 赵敏2, 孙双燕1,()   
  1. 1. 130021 长春,吉林省肿瘤医院放射科
    2. 201203 上海,通用电气药业(上海)有限公司
  • 收稿日期:2021-07-14 出版日期:2022-06-01
  • 通信作者: 孙双燕
  • 基金资助:
    吉林省科技厅科技发展计划项目(20190201246JC)

Enhanced MRI radiomics in predictive model for axillary lymph node metastasis of breast cancer

Dingli Ye1, Han Zhang1, Yijia Liu1, Jianxuan Li1, Meiyu Bai1, Jihong Zhao1, Min Zhao2, Shuangyan Sun1,()   

  1. 1. Department of Radiology, Jilin Cancer Hospital, Changchun 130021, China
    2. General Electric Healthcare Co., Ltd, Shanghai 201203, China
  • Received:2021-07-14 Published:2022-06-01
  • Corresponding author: Shuangyan Sun
引用本文:

叶钉利, 张涵, 刘伊佳, 李健轩, 白美玉, 赵继红, 赵敏, 孙双燕. 增强MRI影像组学在构建乳腺癌腋窝淋巴结转移预测模型中的应用研究[J/OL]. 中华乳腺病杂志(电子版), 2022, 16(03): 147-154.

Dingli Ye, Han Zhang, Yijia Liu, Jianxuan Li, Meiyu Bai, Jihong Zhao, Min Zhao, Shuangyan Sun. Enhanced MRI radiomics in predictive model for axillary lymph node metastasis of breast cancer[J/OL]. Chinese Journal of Breast Disease(Electronic Edition), 2022, 16(03): 147-154.

目的

探讨基于增强MRI影像组学构建的预测模型对乳腺癌腋窝淋巴结转移的诊断效能。

方法

根据纳入及排除标准,回顾性分析2016年1月至2020年6月在吉林省肿瘤医院接受手术治疗的376例女性乳腺癌患者的临床、病理及影像资料。患者术前接受乳腺增强MRI检查。用随机数字表法从所有患者中选择20例,由2名放射科医师对其影像独立分割病灶,勾画感兴趣区域(ROI)。采用组内相关系数(ICC)检验对2名医师勾画的ROI进行一致性分析。采用A.K.(Version 3.3.0)软件提取病灶区域的三维纹理特征参数,通过IPMs(Version 2.0.2)软件及最小绝对收缩和选择算子(LASSO)筛选出最佳影像组学特征,用于构建乳腺癌淋巴结转移预测模型。按7∶3的比例将患者随机分为训练组(n=263)和验证组(n=113)。采用6种机器学习模型,包括Logistic回归、随机森林(RF)、贝叶斯算法(NB)、决策树(DT)、邻近算法(KNN)和支持向量机(SVM)模型,对2组数据进行处理,采用受试者操作特征(ROC)曲线分析各机器学习模型对乳腺癌腋窝淋巴结转移的诊断效能,根据训练组ROC曲线下面积(AUC)大小,选择最佳模型。用决策曲线分析(DCA)评价最佳模型的临床获益。

结果

共有腋窝淋巴结阳性患者114例,腋窝淋巴结阴性患者262例。操作者一致性检验结果显示:2名医师具有很强的操作者一致性(ICC=0.915,95%CI: 0.894~0.932, P<0.001)。每个病灶提取得到396个三维纹理特征参数,筛选保留7个淋巴结阳性组与淋巴结阴性组间差异明显的影像组学特征,并将其与2个临床指标(年龄和绝经状态)和5个影像学指标(病灶位置、有无钙化、病灶数量、病灶长径和造影剂时间-信号曲线类型)一起,共14个参数,构建预测模型。6种机器学习模型中,Logistic回归模型在训练组中诊断乳腺癌腋窝淋巴结转移的AUC最高(0.798),准确率为73.0%(192/263)、特异度为75.4%(138/183)、敏感度为67.5%(54/80),在验证组的AUC为0.767、准确率为73.5%(83/113)、特异度为77.2%(61/79)、敏感度为64.7%(22/34),为最佳机器学习模型。基于Logistic回归模型的决策曲线分析结果显示:训练组中阈值为0.15~1.00,验证组中阈值为0.10~0.60,有临床获益。

结论

基于增强MRI影像组学结合机器学习模型建立的预测模型能够鉴别乳腺癌淋巴结转移,其中以Logistic回归模型的诊断效能更优。

Objective

To investigate diagnosis efficiency of the predictive model based on enhanced MRI radiomics for axillary lymph node metastasis of breast cancer.

Methods

According to the inclusion and exclusion criteria, the clinical, pathological and imaging data of 376 female breast cancer patients who received surgical treatment in the Jilin Cancer Hospital from January 2016 to June 2020 were retrospectively analyzed. The patient underwent enhanced MRI of the breast before surgery. Twenty patients were selected from all patients by random number table method, and 2 radiologists independently segmented the lesions on their images and delineated the region of interest (ROI). The intraclass correlation coeficient (ICC) was used to analyze the consistency of the ROI delineated by the two radiologists. The A. K. (Version 3.3.0) software was used to extract the three-dimensional imaging parameters of the lesion area, and the optimal radiomic parameters were screened out using the IPMs (Version 2.0.2) software and the least absolute shrinkage and selection operator (LASSO) to construct a predictive model for lymph node metastasis in breast cancer. Patients were randomly divided into the training group (n=263) and validation group (n=113) at a ratio of 7∶3. Six machine learning algorithms including the Logistic regression, random forest (RF), Bayesian algorithm (NB), decision tree (DT), K-neighborhood algorithm (KNN) and support vector machine (SVM) were used to process the data of the training group and validation group. The receiver operating characteristic (ROC) curve was used to investigate the diagnosis efficiency of the above-mentioned 6 models for axillary lymph node metastasis of breast cancer, and the optimal model was selected based on AUC of the training group. The clinical benefit of the optimal model was evaluated by the decision curve analysis (DCA).

Results

There were 114 patients with positive axillary lymph nodes and 262 patients with negative axillary lymph nodes. The ICC was 0.915, indicating high consistency between the two radiologists (95%CI: 0.894-0.932, P<0.001). Totally 396 three-dimensional imaging parameters were extracted from each lesion. Among them, 7 radiomic parameters with significant differences between the lymph node-positive group and the lymph node-negative group were screened out. The 7 radiomic parameters, 2 clinical parameters (age and menopausal status) and 5 imaging parameters (lesion location, calcification, number of lesions, long diameter of lesions, and time-signal curve type of contrast agent) were employed to construct a predictive model. Among six machine learning algorithms, the Logistic regression model had the highest AUC (0.798) in the diagnosis of axillary lymph node metastasis in breast cancer patients of training group, with the accuracy of 73.0%(192/263), specificity 75.4%(138/183) and sensitivity 67.5%(54/80). In the validation group, the Logistic regression model had the AUC of 0.767, accuracy 73.5%(83/113), specificity 77.2%(61/79) and sensitivity 64.7%(22/34), indicating that the Logistic regression model was the optimal. The decision curve analysis of the Logistic regression model showed that the threshold was 0.15-1.00 in the training group, and 0.10-0.60 in the validation group, indicating obvious clinical benefit.

Conclusion

The predictive models based on enhanced MRI radiomics combined with machine learning algorithm can diagnose lymph node metastasis of breast cancer, and among them the Logistic regression model shows the optimal diagnostic efficiency.

图1 放射科医师在乳腺癌患者的核磁共振图上勾画ROI a图所示1例28岁乳腺癌患者的病灶最大层面对比增强90 s轴位T1压脂图像;b图所示在轴位T1压脂图像上显示ROI;c图所示在矢状位T1压脂图像上显示ROI;d图所示分割后ROI的三维图像 注:ROI是感兴趣区域
表1 376例乳腺癌患者的分子亚型分布(例)
表2 用于构建机器学习模型的14个参数
图2 6种机器学习模型在263例训练组乳腺癌患者中的受试者操作特征曲线 注:NB是贝叶斯算法;KNN是邻近算法;RF是随机森林;DT是决策树;SVM是支持向量机
图3 6种机器学习模型在113例验证组乳腺癌患者中的受试者操作特征曲线 注:NB是贝叶斯算法;KNN是邻近算法;RF是随机森林;DT是决策树;SVM是支持向量机
表3 6种机器学习模型对376例乳腺癌患者腋窝淋巴结转移的诊断效能比较
表4 Logistic回归机器学习模型中各特征参数信息
图4 Logistic回归模型预测乳腺癌淋巴结转移风险的决策曲线和诺莫图 a图所示训练组的决策曲线;b图所示验证组的决策曲线;c图为诺莫图 注:DCA是决策曲线;Treat none是指所有样本都是阴性,即所有患者均不接受干预,净获益为0;Treat all是指所有样本都是阳性,即所有患者均接受干预,净获益是斜率为负值的反斜线;决策曲线越远离这两条极端曲线,表明该模型越具有应用价值;病灶数量和造影剂时间-信号曲线类型2个变量在取值范围内对应的分值均为0,在c图中未显示
[1]
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.
[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[J]. Chin Med J (Engl), 2021, 134(7):783-791.
[3]
庄琰,张进,杜森,等.MR间质淋巴造影在诊断乳腺癌腋窝淋巴结转移中的临床意义表达[J].医药论坛杂志201940(2):78-79.
[4]
Giuliano AE, Edge SB, Hortobagyi GN. Eighth edition of the AJCC cancer staging manual: breast cancer[J]. Ann Surg Oncol, 2018, 25(7):1783-1785.
[5]
吴佩琪.影像组学在乳腺癌淋巴结转移中的研究进展[J].分子影像学杂志202043(1):31-35.
[6]
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.
[7]
Gherghe M, Bordea C, Blidaru A. Sentinel lymph node biopsy (SLNB) vs. axillary lymph node dissection (ALND) in the current surgical treatment of early stage breast cancer[J]. J Med Life, 2015, 8(2):176-180.
[8]
Liu J, Sun D, Chen L, et al. Radiomics analysis of dynamic contrast-enhanced magnetic resonance imaging for the prediction of sentinel lymph node metastasis in breast cancer[J]. Front Oncol, 2019, 9:980.
[9]
张强,牛连杰,黄涛,等.早期乳腺癌520例前哨淋巴结转移关联性分析及预测研究[J].中华肿瘤防治杂志202027(22):1850-1854.
[10]
Zhu Y, Zhou W, Jia XH, et al. Preoperative axillary ultrasound in the selection of patients with a heavy axillary tumor burden in early-stage breast cancer: what leads to false-positive results[J]. J Ultrasound Med, 2018, 37(6):1357-1365.
[11]
李玉欣,王嬴煊,程流泉,等.MRI、乳腺X线摄影和超声对乳腺导管原位癌检出的效能[J].中华放射学杂志202054(6):557-562.
[12]
Harnan SE, Cooper KL, Meng Y, et al. Magnetic resonance for assessment of axillary lymph node status in early breast cancer: a systematic review and meta-analysis[J]. Eur J Surg Oncol, 2011, 37(11):928-936.
[13]
Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4):488-495.
[14]
周嘉音,尤超,顾雅佳.影像组学在乳腺癌的应用研究进展[J].国际医学放射学杂志202245(2):174-179.
[15]
陈基明,朱浩雨,高静,等.基于临床病理及常规和功能MRI影像组学模型预测乳腺癌腋窝淋巴结转移[J].中国医学影像技术202137(6):885-890.
[16]
刘梅婕,毛宁,马恒,等.基于影像组学构建乳腺癌前哨淋巴结转移预测模型的研究[J].中国中西医结合影像学杂志202018(3):227-231.
[17]
罗红兵,刘圆圆,青浩渺,等.乳腺癌腋窝淋巴结的DCE-MRI影像组学特征对诊断其转移状态价值的初步研究[J].临床放射学杂志202140(3):442-447.
[18]
Kang SR, Kim HW, Kim HS. Evaluating the relationship between dynamic contrast-enhanced MRI (DCE-MRI) parameters and pathological characteristics in breast cancer[J]. J Magn Reson Imaging, 2020, 52(5):1360-1373.
[19]
Wang QQ, Yu SC, Qi X, et al. Overview of logistic regression model analysis and application[J]. Zhonghua Yu Fang Yi Xue Za Zhi, 2019, 53(9):955-960.
[20]
Ishwaran H, Lu M. Standard errors and confidence intervals for variable importance in random forest regression, classification, and survival[J]. Stat Med, 2019, 38(4):558-582.
[21]
Sugahara S, Ueno M. Exact learning augmented Naive Bayes Classifier[J]. Entropy (Basel), 2021, 23(12):1703.
[22]
Che D, Liu Q, Rasheed K, et al. Decision tree and ensemble learning algorithms with their applications in bioinformatics[J]. Adv Exp Med Biol, 2011, 696:191-199.
[23]
Zhang Z. Introduction to machine learning: k-nearest neighbors[J]. Ann Transl Med, 2016, 4(11):218-224.
[24]
Huang S, Cai N, Pacheco PP, et al. Applications of support vector machine (SVM) learning in cancer genomics[J]. Cancer Genomics Proteomics, 2018, 15(1):41-51.
[25]
Downs-Canner SM, Gaber CE, Louie RJ, et al. Nodal positivity decreases with age in women with early-stage, hormone receptor-positive breast cancer[J]. Cancer, 2020, 126(6):1193-1201.
[1] 王佳佳, 詹韵韵, 姜凡, 孙碧云, 毕玉, 李如冰, 彭梅. Peyton四步教学法在超声住院医师规范化培训颈部淋巴结分区中的应用[J/OL]. 中华医学超声杂志(电子版), 2024, 21(08): 814-818.
[2] 李乐平, 张荣华, 商亮. 腹腔镜食管胃结合部腺癌根治淋巴结清扫策略[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 9-12.
[3] 吴晖, 佴永军, 施雪松, 魏晓为. 两种解剖入路下行直肠癌侧方淋巴结清扫的效果比较[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 40-43.
[4] 周世振, 朱兴亚, 袁庆港, 刘理想, 王凯, 缪骥, 丁超, 汪灏, 管文贤. 吲哚菁绿荧光成像技术在腹腔镜直肠癌侧方淋巴结清扫中的应用效果分析[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 44-47.
[5] 奚玲, 仝瀚文, 缪骥, 毛永欢, 沈晓菲, 杜峻峰, 刘晔. 基于肌少症构建的造口旁疝危险因素预测模型[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 48-51.
[6] 高杰红, 黎平平, 齐婧, 代引海. ETFA和CD34在乳腺癌中的表达及与临床病理参数和预后的关系研究[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 64-67.
[7] 李代勤, 刘佩杰. 动态增强磁共振评估中晚期低位直肠癌同步放化疗后疗效及预后的价值[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 100-103.
[8] 韩萌萌, 冯雪园, 马宁. 乳腺癌改良根治术后桡神经损伤1例[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 117-118.
[9] 屈勤芳, 束方莲. 盆腔器官脱垂患者盆底重建手术后压力性尿失禁发生的影响因素及列线图预测模型构建[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 606-612.
[10] 公宇, 廖媛, 尚梅. 肝细胞癌TACE术后复发影响因素及预测模型建立[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 818-824.
[11] 陆镜明, 韩大为, 任耀星, 黄天笑, 向俊西, 张谞丰, 吕毅, 王傅民. 基于术前影像组学的肝内胆管细胞癌淋巴结转移预测的系统性分析[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 852-858.
[12] 王景明, 王磊, 许小多, 邢文强, 张兆岩, 黄伟敏. 腰椎椎旁肌的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(09): 846-852.
[13] 韦巧玲, 黄妍, 赵昌, 宋庆峰, 陈祖毅, 黄莹, 蒙嫦, 黄靖. 肝癌微波消融术后中重度疼痛风险预测列线图模型构建及验证[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 715-721.
[14] 蔡晓雯, 李慧景, 丘婕, 杨翼帆, 吴素贤, 林玉彤, 何秋娜. 肝癌患者肝动脉化疗栓塞术后疼痛风险预测模型的构建及验证[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 722-728.
[15] 崔军威, 蔡华丽, 胡艺冰, 胡慧. 亚甲蓝联合金属定位夹及定位钩针标记在乳腺癌辅助化疗后评估腋窝转移淋巴结的临床应用价值探究[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 625-632.
阅读次数
全文


摘要