Radiology Division, Istituto Nazionale Tumori-IRCCS-Fondazione G. Pascale, 80131, Naples, Italy.
Medical Oncology Division, Igea SpA, 80013, Naples, Italy.
Radiol Med. 2024 Jun;129(6):864-878. doi: 10.1007/s11547-024-01817-8. Epub 2024 May 17.
To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 - ; (3) HR + vs. HR - ; and (4) non-luminal vs. luminal A or HR + /HER2- and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.
评估对比增强乳腺摄影图像的放射组学分析在识别不同乳腺癌组织学类型方面的性能，主要目的是预测分级、识别激素受体、区分人表皮生长因子受体 2（HER2）和识别乳腺癌的管腔型。
从四个意大利中心招募了 180 例恶性病变和 68 例良性病变。然而，仅对恶性病变进行了分析。所有患者均在颅尾（CC）和中侧斜（MLO）位进行对比增强乳腺摄影检查。以组织学发现为金标准，考虑了四种结果：（1）G1+G2 与 G3；（2）HER2+与 HER2-；（3）HR+与 HR-；（4）非管腔型与管腔 A 或 HR+/HER2-和管腔 B 或 HR+/HER2+。对于多变量分析，考虑了特征选择、平衡技术和模式识别方法。
单变量分析结果表明，每种结果的诊断性能均较低，而多变量分析结果表明，可以获得更好的性能。在 HER2+检测中，使用 MLO 视图提取的 12 个特征的线性回归模型（LRM）获得了最佳性能（准确率为 73%，AUC=0.77）。在 HR+检测中，使用 MLO 视图提取的 14 个特征的 LRM 获得了最佳性能（准确率为 77%，AUC=0.80）。在分级分类中，使用 MLO 视图提取的三个预测因子训练的决策树在验证集上达到了 82%的准确率，获得了最佳性能。在管腔与非管腔组织学类型分类中，使用 CC 视图提取的 15 个预测因子训练的袋装树在验证集上达到了 94%的准确率，获得了最佳性能。
结果表明，放射组学分析可有效地应用于设计一种工具，以支持医生在乳腺癌分类中的决策。特别是，管腔与非管腔组织学类型的分类可以达到很高的准确性。
