Romeo Valeria, Cuocolo Renato, Sanduzzi Luca, Carpentiero Vincenzo, Caruso Martina, Lama Beatrice, Garifalos Dimitri, Stanzione Arnaldo, Maurea Simone, Brunetti Arturo
Department of Advanced Biomedical Sciences, University of Naples "Federico II", 80131 Naples, Italy.
Department of Medicine, Surgery, and Dentistry, University of Salerno, 84084 Baronissi, Italy.
Cancers (Basel). 2023 Mar 18;15(6):1840. doi: 10.3390/cancers15061840.
To non-invasively predict Oncotype DX recurrence scores (ODXRS) in patients with + - invasive breast cancer (IBC) using dynamic contrast-enhanced (DCE) MRI-derived radiomics features extracted from primary tumor lesions and a ML algorithm.
Pre-operative DCE-MRI of patients with IBC, no history of neoadjuvant therapy prior to MRI, and for which the ODXRS was available, were retrospectively selected from a public dataset. ODXRS was obtained on histological tumor samples and considered as positive if greater than 16 and 26 in patients aged under and over 50 years, respectively. Tumor lesions were manually annotated by three independent operators on DCE-MRI images through 3D ROIs positioning. Radiomic features were therefore extracted and selected using multistep feature selection process. A logistic regression ML classifier was then employed for the prediction of ODXRS.
248 patients were included, of which 87 with positive ODXRS. 166 (66%) patients were grouped in the training set, while 82 (33%) in the test set. A total of 1288 features was extracted. Of these, 1244 were excluded as 771, 82 and 391 were excluded as not stable ( = 771), not variant ( = 82), and highly intercorrelated ( = 391), respectively. After the use of recursive feature elimination with logistic regression estimator and polynomial transformation, 92 features were finally selected. In the training set, the logistic regression classifier obtained an overall mean accuracy of 60%. In the test set, the accuracy of the ML classifier was 63%, with a sensitivity of 80%, specificity of 43%, and AUC of 66%.
Radiomics and ML applied to pre-operative DCE-MRI in patients with IBC showed promises for the non-invasive prediction of ODXRS, aiding in selecting patients who will benefit from NAC.
利用从原发性肿瘤病变中提取的动态对比增强（DCE）MRI衍生的放射组学特征和机器学习（ML）算法，对浸润性乳腺癌（IBC）患者的Oncotype DX复发评分（ODXRS）进行无创预测。
从一个公共数据集中回顾性选择IBC患者的术前DCE-MRI，这些患者在MRI之前没有新辅助治疗史且有可用的ODXRS。ODXRS是在组织学肿瘤样本上获得的，如果50岁以下和50岁以上患者的ODXRS分别大于16和26，则认为是阳性。通过3D感兴趣区（ROI）定位，由三名独立操作人员在DCE-MRI图像上手动标注肿瘤病变。因此，使用多步骤特征选择过程提取并选择放射组学特征。然后采用逻辑回归ML分类器预测ODXRS。
纳入248例患者，其中87例ODXRS为阳性。166例（66%）患者被纳入训练集，82例（33%）患者被纳入测试集。共提取了1288个特征。其中，1244个特征被排除，因为分别有771个、82个和391个特征因不稳定（n = 771）、无变化（n = 82）和高度相关（n = 391）而被排除。在使用逻辑回归估计器和多项式变换进行递归特征消除后，最终选择了92个特征。在训练集中，逻辑回归分类器的总体平均准确率为60%。在测试集中，ML分类器的准确率为63%，灵敏度为80%，特异性为43%，曲线下面积（AUC）为66%。
将放射组学和ML应用于IBC患者的术前DCE-MRI，显示出无创预测ODXRS的前景，有助于选择将从新辅助化疗（NAC）中获益的患者。
