Department of Biostatistics, Key Laboratory on Public Health Safety of the Ministry of Education, School of Public Health, Fudan University, Shanghai, 200032, China.
Department of Radiology, Fudan University Shanghai Cancer Center, No. 270 Dongan Road, Shanghai, 200032, China.
Cancer Imaging. 2022 May 12;22(1):22. doi: 10.1186/s40644-022-00460-8.
Radiomics plays an important role in the field of oncology. Few studies have focused on the identification of factors that may influence the classification performance of radiomics models. The goal of this study was to use contrast-enhanced mammography (CEM) images to identify factors that may potentially influence the performance of radiomics models in diagnosing breast lesions.
A total of 157 women with 161 breast lesions were included. Least absolute shrinkage and selection operator (LASSO) regression and the random forest (RF) algorithm were employed to construct radiomics models. The classification result for each lesion was obtained by using 100 rounds of five-fold cross-validation. The image features interpreted by the radiologists were used in the exploratory factor analyses. Univariate and multivariate analyses were performed to determine the association between the image features and misclassification. Additional exploratory analyses were performed to examine the findings.
Among the lesions misclassified by both LASSO and RF ≥ 20% of the iterations in the cross-validation and those misclassified by both algorithms ≤5% of the iterations, univariate analysis showed that larger lesion size and the presence of rim artifacts and/or ripple artifacts were associated with more misclassifications among benign lesions, and smaller lesion size was associated with more misclassifications among malignant lesions (all p < 0.050). Multivariate analysis showed that smaller lesion size (odds ratio [OR] = 0.699, p = 0.002) and the presence of air trapping artifacts (OR = 35.568, p = 0.025) were factors that may lead to misclassification among malignant lesions. Additional exploratory analyses showed that benign lesions with rim artifacts and small malignant lesions (< 20 mm) with air trapping artifacts were misclassified by approximately 50% more in rate compared with benign and malignant lesions without these factors.
Lesion size and artifacts in CEM images may affect the diagnostic performance of radiomics models. The classification results for lesions presenting with certain factors may be less reliable.
放射组学在肿瘤学领域发挥着重要作用。目前，很少有研究关注可能影响放射组学模型分类性能的因素。本研究旨在使用增强型乳腺 X 线摄影术（CEM）图像来确定可能影响乳腺病变诊断中放射组学模型性能的因素。
共纳入 157 例 161 个乳腺病变患者。采用最小绝对收缩和选择算子（LASSO）回归和随机森林（RF）算法构建放射组学模型。使用 100 次五重交叉验证获得每个病变的分类结果。由放射科医生解释的图像特征用于探索性因素分析。进行单变量和多变量分析，以确定图像特征与错误分类之间的关联。进行额外的探索性分析以检验研究结果。
在 LASSO 和 RF 均将交叉验证中迭代次数≥20%的病变和迭代次数≤5%的病变分类错误的情况下，单变量分析显示，良性病变中，病变较大、存在边缘伪影和/或波纹伪影与更多的误诊相关，而恶性病变中，病变较小与更多的误诊相关（均 P＜0.050）。多变量分析显示，病变较小（比值比 [OR]＝0.699，P＝0.002）和存在空气捕获伪影（OR＝35.568，P＝0.025）是导致恶性病变误诊的因素。进一步的探索性分析表明，存在边缘伪影的良性病变和较小的恶性病变（＜20 mm）伴有空气捕获伪影，其误诊率比无这些因素的良性和恶性病变高约 50%。
CEM 图像中的病变大小和伪影可能会影响放射组学模型的诊断性能。具有某些特征的病变的分类结果可能不太可靠。
