Department of Radiology, Peking University People's Hospital, Beijing, P R China; Department of Radiology, Yantai Yuhuangding Hospital, Yantai, Shandong, P R China.
Department of Radiology, Peking University People's Hospital, Beijing, P R China.
J Am Coll Radiol. 2019 Apr;16(4 Pt A):485-491. doi: 10.1016/j.jacr.2018.09.041. Epub 2018 Dec 4.
This study aimed to evaluate whether radiomics can improve the diagnostic performance of mammography compared with that obtained by experienced radiologists.
This retrospective study included 173 patients (with 74 benign and 99 malignant lesions) who underwent mammography examination before neoadjuvant chemotherapy. Radiomic features were extracted from the mammography image of each patient. Several preprocessing methods, including centering and normalization, were used along with statistical analysis to reduce and select radiomic features. Four machine learning algorithms, namely, support vector machine, logistic regression, K-nearest neighbor, and Bayes classification, were applied to construct a predictive model. An independent testing data set was used to validate the prediction ability of the model. The classification performance was compared with the diagnostic predictions of two breast radiologists who had access to the same mammography cases.
A total of 51 radiomic features remained after the preprocessing. Logistic regression classification presented the best differentiation ability among the four regression models. The diagnostic accuracy, specificity, and sensitivity of the logistic regression model for the training data set were 0.978, 0.975, and 0.983, respectively. The diagnostic accuracy, specificity, and sensitivity for the testing data set were 0.886, 0.900, and 0.867, respectively. The accuracy, specificity, and sensitivity of the combined reading of the two radiologists were 0.772, 0.710, 0.862 in the training data set and 0.769, 0.695, 0.858 in the testing data set, respectively.
Mammography images could be captured and quantified by radiomics, which offers a good diagnostic ability for benign and malignant breast tumors and provides complementary information to radiologists.
本研究旨在评估与经验丰富的放射科医生相比，放射组学是否可以提高乳房 X 线摄影的诊断性能。
本回顾性研究纳入了 173 名患者（74 例良性病变和 99 例恶性病变），这些患者在新辅助化疗前接受了乳房 X 线摄影检查。从每位患者的乳房 X 线摄影图像中提取放射组学特征。使用了几种预处理方法，包括中心化和归一化，以及统计分析来减少和选择放射组学特征。应用了四种机器学习算法，即支持向量机、逻辑回归、K 最近邻和贝叶斯分类，来构建预测模型。使用独立的测试数据集来验证模型的预测能力。将分类性能与具有相同乳房 X 线摄影病例访问权限的两位乳腺放射科医生的诊断预测进行比较。
预处理后共保留了 51 个放射组学特征。在四个回归模型中，逻辑回归分类表现出最好的区分能力。逻辑回归模型对训练数据集的诊断准确性、特异性和敏感性分别为 0.978、0.975 和 0.983。对测试数据集的诊断准确性、特异性和敏感性分别为 0.886、0.900 和 0.867。两位放射科医生联合阅读的准确性、特异性和敏感性在训练数据集中分别为 0.772、0.710 和 0.862，在测试数据集中分别为 0.769、0.695 和 0.858。
放射组学可以捕获和量化乳房 X 线摄影图像，为良性和恶性乳腺肿瘤提供了良好的诊断能力，并为放射科医生提供了补充信息。
