Department of Radiology, Duke University School of Medicine, Durham, NC, 22705, USA.
Department of Electrical and Computer Engineering, Duke University, Durham, NC, 22705, USA.
Br J Cancer. 2018 Aug;119(4):508-516. doi: 10.1038/s41416-018-0185-8. Epub 2018 Jul 23.
Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship.
We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients.
Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647-0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589-0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591-0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569-0.674, p < .0001). Associations between individual features and subtypes we also found.
There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.
最近的研究显示了基于 MRI 的乳腺癌成像表型与乳腺癌分子、基因组和相关特征之间关联的初步数据。在这项研究中，我们对这种关系进行了全面分析。
我们分析了一组 922 名患有浸润性乳腺癌和术前 MRI 的患者。通过计算机算法对 MRI 进行分析，以提取肿瘤和周围组织的 529 个特征。使用部分数据（461 名患者）基于成像特征训练基于机器学习的模型，以预测以下分子、基因组和增殖特征：肿瘤替代分子亚型、雌激素受体、孕激素受体和人表皮生长因子状态，以及肿瘤增殖标志物（Ki-67）。在其余的 461 名患者中评估训练模型。
多变量模型可预测 Luminal A 亚型，AUC=0.697（95%CI：0.647-0.746，p<0.0001），三阴性乳腺癌，AUC=0.654（95%CI：0.589-0.727，p<0.0001），ER 状态，AUC=0.649（95%CI：0.591-0.705，p<0.001）和 PR 状态，AUC=0.622（95%CI：0.569-0.674，p<0.0001）。我们还发现了个体特征与亚型之间的关联。
肿瘤分子生物标志物与算法评估的成像特征之间存在中度关联。
