Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density
Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density
复制标题
DOI：
10.1038/s41523-019-0134-6
复制
发表时间：
2019-11-19
影响因子：
5.9
通讯作者：
Gierach, Gretchen L.
中科院分区：
文献类型：
--
作者：
Mullooly, Maeve;Bejnordi, Babak Ehteshami;Gierach, Gretchen L.
乳房密度是乳腺癌的危险因素，是反映相对于乳房面积或体积的纤维腺组织含量的放射学特征。其组织学特征尚不完全明确。在这里，我们使用深度学习方法来确定放射引导活检中的组织学相关性，这可能是乳房密度的基础，并区分高密度和低密度妇女中的癌症。我们评估了来自影像引导的乳腺活检(n=852例)的苏木精-伊红(H&E)染色的数字化图像。乳房密度评估为整体和局部纤维腺体积(%)。表征H&E成分的卷积神经网络。总共从网络输出中提取了37个特征，描述了组织数量和形态结构。训练随机森林回归模型以确定预测纤维腺体积最大的相关因素(n=588)。在264名独立患者中，评估了预测的纤维腺体积与放射学量化的纤维腺体积之间的相关性。训练第二个随机森林分类器以预测诊断(侵袭性与良性)；使用受试者工作特征曲线下面积(AUC)来评估性能。利用提取的特征，回归模型预测了纤维腺的整体(r=0.94)和局部(r=0.93)体积，其中脂肪和非脂肪间质含量的相关性最强，其次是上皮组织，而不是数量。对于高纤维腺体体积和低纤维腺体体积的癌症的预测，该分类器的AUC值分别为0.92和0.84，其中上皮组织特征最重要。这些结果提示非脂肪间质、脂肪组织数量和上皮区组织可以预测纤维腺的体积。该模型有望识别高密度和低密度患者癌症风险的组织学相关性，并值得进一步评估。
Breast density, a breast cancer risk factor, is a radiologic feature that reflects fibroglandular tissue content relative to breast area or volume. Its histology is incompletely characterized. Here we use deep learning approaches to identify histologic correlates in radiologically-guided biopsies that may underlie breast density and distinguish cancer among women with elevated and low density. We evaluated hematoxylin and eosin (H&E)-stained digitized images from image-guided breast biopsies (n = 852 patients). Breast density was assessed as global and localized fibroglandular volume (%). A convolutional neural network characterized H&E composition. In total 37 features were extracted from the network output, describing tissue quantities and morphological structure. A random forest regression model was trained to identify correlates most predictive of fibroglandular volume (n = 588). Correlations between predicted and radiologically quantified fibroglandular volume were assessed in 264 independent patients. A second random forest classifier was trained to predict diagnosis (invasive vs. benign); performance was assessed using area under receiver-operating characteristics curves (AUC). Using extracted features, regression models predicted global (r = 0.94) and localized (r = 0.93) fibroglandular volume, with fat and non-fatty stromal content representing the strongest correlates, followed by epithelial organization rather than quantity. For predicting cancer among high and low fibroglandular volume, the classifier achieved AUCs of 0.92 and 0.84, respectively, with epithelial organizational features ranking most important. These results suggest non-fatty stroma, fat tissue quantities and epithelial region organization predict fibroglandular volume. The model holds promise for identifying histological correlates of cancer risk in patients with high and low density and warrants further evaluation.