Ha Richard, Mutasa Simukayi, Sant Eduardo Pascual Van, Karcich Jenika, Chin Christine, Liu Michael Z, Jambawalikar Sachin
Breast Imaging Section, Department of Radiology, Columbia University Medical Center, 622 W 168th St, PB-1-301, New York, NY 10032.
Department of Radiology, Columbia University Medical Center, New York, NY.
AJR Am J Roentgenol. 2019 May;212(5):1166-1171. doi: 10.2214/AJR.18.20250. Epub 2019 Mar 12.
The purpose of this study was to test the hypothesis that convolutional neural networks can be used to predict which patients with pure atypical ductal hyperplasia (ADH) may be safely monitored rather than undergo surgery. A total of 298 unique images from 149 patients were used for our convolutional neural network algorithm. A total of 134 images from 67 patients with ADH that had been diagnosed by stereotactic-guided biopsy of calcifications but had not been upgraded to ductal carcinoma in situ or invasive cancer at the time of surgical excision. A total of 164 images from 82 patients with mammographic calcifications indicated that ductal carcinoma in situ was the final diagnosis. Two standard mammographic magnification views of the calcifications (a craniocaudal view and a mediolateral or lateromedial view) were used for analysis. Calcifications were segmented using an open-source software platform and images were resized to fit a bounding box of 128 × 128 pixels. A topology with 15 hidden layers was used to implement the convolutional neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Patients were randomly separated into a training-and-validation set (80% of patients) and a test set (20% of patients). Code was implemented using open-source software on a workstation with an open-source operating system and a graphics card. The AUC value was 0.86 (95% CI, ± 0.03) for the test set. Aggregate sensitivity and specificity were 84.6% (95% CI, ± 4.0%) and 88.2% (95% CI, ± 3.0%), respectively. Diagnostic accuracy was 86.7% (95% CI, ± 2.9). It is feasible to apply convolutional neural networks to distinguish pure atypical ductal hyperplasia from ductal carcinoma in situ with the use of mammographic images. A larger dataset will likely result in further improvement of our prediction model.
卷积神经网络可用于预测哪些单纯非典型导管增生（ADH）患者可安全监测而非接受手术。我们的卷积神经网络算法使用了来自149名患者的总共298张独特图像。其中，67例经立体定向引导下钙化活检诊断为ADH但手术切除时未升级为导管原位癌或浸润性癌的患者，共有134张图像。82例乳腺钼靶钙化患者的总共164张图像显示最终诊断为导管原位癌。使用钙化的两个标准乳腺钼靶放大视图（头尾位视图和内外侧或外内侧视图）进行分析。使用开源软件平台对钙化进行分割，并将图像调整大小以适合128×128像素的边界框。使用具有15个隐藏层的拓扑结构来实现卷积神经网络。网络架构包含五个残差层，每次卷积后随机失活率为0.25。患者被随机分为训练和验证集（80%的患者）和测试集（20%的患者）。代码在具有开源操作系统和图形卡的工作站上使用开源软件实现。测试集的AUC值为0.86（95%CI，±0.03）。总体敏感性和特异性分别为84.6%（95%CI，±4.0%）和88.2%（95%CI，±3.0%）。诊断准确率为86.7%（95%CI，±2.9）。应用卷积神经网络通过乳腺钼靶图像区分单纯非典型导管增生和导管原位癌是可行的。更大的数据集可能会进一步改进我们的预测模型。
