摘要
目的:探讨基于数字乳腺断层摄影(digital breast tomosynthesis,DBT)的影像组学对乳腺癌分子分型的预测价值。方法:回顾并分析2019年1月—2020年8月于复旦大学附属肿瘤医院行DBT检查并经病理学检查证实为浸润性乳腺癌的380例患者资料,每例患者DBT影像包含头尾(craniocaudal,CC)位和内外斜(mediolateral oblique,MLO)位。通过提取380例基于DBT的病灶全瘤组学特征,经降维、筛选后,将保留的特征分别放入逻辑回归(logistic regression,LR)、支持向量机(support vector machine,SVM)及随机森林(random forest,RF)3个不同的机器学习模型,以受试者工作特征(receiver operating characteristic,ROC)曲线评价3种模型对乳腺癌4种分子分型的预测效能。结果:经病理学检查证实的380例病灶中,Luminal A型72例,Luminal B型175例,人表皮生长因子受体2(human epidermal growth factor receptor 2,HER2)过表达型54例,三阴性乳腺癌(triple-negative breast cancer,TNBC)79例。3种不同的算法模型均可有效鉴别乳腺癌分子分型,其中RF模型表现效果整体较好,在测试集中通过二分法预测Luminal A型、Luminal B型、HER2过表达型和TNBC的曲线下面积(area under curve,AUC)分别为0.82、0.71、0.70和0.71。DBT组学特征中,熵及与熵相关特征、形态特征与乳腺癌分子分型有关。结论:基于DBT的影像组学模型可较好预测乳腺癌的分子分型,其中表征异质性与形态的影像组学特征有助于乳腺癌分子分型的鉴别。
Objective:To investigate the predictive value of radiomics based on digital breast tomosynthesis(DBT)in molecular subtypes of breast cancer.Methods:The data of 380 patients with invasive breast cancer confirmed by pathology after DBT examination in the Fudan University Shanghai Cancer Center from January 2019 to August 2020 were retrospectively analyzed.The DBT images of each patient included craniocaudal(CC)position and mediolateral oblique(MLO)position.And 380 wholetumor features of lesions based on DBT were extracted,after performing dimensionality reduction and screening,the flnal retained features were put into three different machine learning models,including logistic regression(LR),support vector machine(SVM)and random forest(RF),respectively.Receiver operating characteristic(ROC)curve was used to evaluate the predictive efficacy of three models based on DBT images for the four molecular classiflcation of breast cancer.Results:Of the 380 lesions conflrmed by pathology,72 were Luminal A type,175 were Luminal B type,54 were human epidermal growth factor receptor 2(HER2)overexpression type,and 79 were triple-negative breast cancer(TNBC).The three models all can predict the molecular subtypes of breast cancer efficiently.Among the three different models,RF model had a better performance,and in the test set,AUC values predicted by dichotomy were 0.82,0.71,0.70,and 0.71 for Luminal A type,Luminal B type,HER2 over-expression type,and TNBC respectively.Among DBT radiomics features,the entropy and entropy-related features,as well as the morphological features are related to the molecular subtypes of breast cancer.Conclusion:The radiomics model based on DBT imaging can predict the molecular subtypes of breast cancer,and the radiomics features that represent the heterogeneity and morphology are helpful for the differentiation of breast cancer molecular subtypes.
作者
李佳蔚
姜婷婷
汤振伟
简嘉豪
范明
沈茜刚
厉力华
顾雅佳
彭卫军
尤超
LI Jiawei;JIANG Tingting;TANG Zhenwei;JIAN Jiahao;FAN Ming;SHEN Xigang;LI Lihua;GU Yajia;PENG Weijun;YOU Chao(Department of Radiology,Fudan University Shanghai Cancer Center,Department of Oncology,Shanghai Medical College,Fudan University,Shanghai 200032,China;Institute of Biomedical Engineering and Instrumentation,Hangzhou Dianzi University,Hangzhou 310018,Zhejiang Province,China)
出处
《肿瘤影像学》
2023年第1期12-19,共8页
Oncoradiology
基金
国家癌症中心攀登基金(NCC201909B06)
上海市卫生健康委员会面上科研项目(202240241)。
关键词
数字乳腺断层摄影
影像组学
分子分型
预测
Digital breast tomosynthesis
Radiomics
Molecular subtype
Prediction
