OBJECTIVE:To develop and validate a radiomics model based on contrast-enhanced spectral mammography (CESM), and preoperatively discriminate low-grade (grade I/II) and high-grade (grade III) invasive breast cancer. METHOD:A total of 205 patients with CESM examination and pathologically confirmed invasive breast cancer were retrospectively enrolled. We randomly divided patients into two independent sets namely, training set (164 patients) and test set (41 patients) with a ratio of 8:2. Radiomics features were extracted from the low-energy and subtracted images. The least absolute shrinkage and selection operator (LASSO) logistic regression were established for feature selection, which were then utilized to construct three classification models namely, low energy, subtracted images and their combined model to discriminate high- and low-grade invasive breast cancer. Receiver operator characteristic (ROC) curves were used to confirm performance of three models in training set. The clinical usefulness was evaluated by using decision curve analysis (DCA). An independent test set was used to confirm the discriminatory power of the models. To test robustness of the result, we used 100 times LGOCV (leave group out cross validation) to validate three models. RESULTS:From initial radiomics feature pool, 17 and 11 features were selected for low-energy image and subtracted image, respectively. The combined model using 28 features showed the best performance for preoperatively evaluating the histologic grade of invasive breast cancer, with an area under the curve, AUC = 0.88, and 95%confidence interval [CI] 0.85 to 0.92 in the training set and AUC = 0.80 (95%CI 0.67 to 0.92) in the test set. The mean AUC of LGOCV is 0.82. CONCLUSIONS:CESM-based radiomics model is a non-invasive predictive tool that demonstrates good application prospects in preoperatively predicting histological grade of invasive breast cancer.

中文翻译：

---

使用基于对比增强光谱乳房 X 线摄影的放射组学术前预测浸润性乳腺癌的组织学分级

目的：开发和验证基于对比增强光谱乳房X线摄影（CESM）的放射组学模型，并在术前区分低级别（I/II级）和高级别（III级）浸润性乳腺癌。方法：回顾性纳入经CESM检查并经病理证实为浸润性乳腺癌的205例患者。我们将患者随机分为两个独立的集合，即训练集（164 名患者）和测试集（41 名患者），比例为 8:2。从低能量和减影图像中提取放射组学特征。建立最小绝对收缩和选择算子（LASSO）逻辑回归进行特征选择，然后将其用于构建三个分类模型，即低能量、减影图像及其组合模型来区分高级别和低级别浸润性乳腺癌。接收操作者特征 (ROC) 曲线用于确认三个模型在训练集中的性能。通过使用决策曲线分析（DCA）评估临床有用性。使用独立的测试集来确认模型的区分能力。为了测试结果的稳健性，我们使用了 100 次 LGOCV（排除组交叉验证）来验证三个模型。结果：从初始放射组学特征库中，分别选择了17个和11个特征用于低能图像和减影图像。使用 28 个特征的组合模型在术前评估浸润性乳腺癌的组织学分级方面表现出最佳性能，曲线下面积 AUC = 0.88，95% 置信区间 [CI] 0.85 至 0。训练集中 92，测试集中 AUC = 0.80 (95%CI 0.67 to 0.92)。LGOCV 的平均 AUC 为 0.82。结论：基于CESM的影像组学模型是一种无创预测工具，在术前预测浸润性乳腺癌组织学分级方面具有良好的应用前景。