Digital mammographic tumor classification using transfer learning from deep convolutional neural networks
Digital mammographic tumor classification using transfer learning from deep convolutional neural networks
复制标题
DOI：
10.1117/1.jmi.3.3.034501
复制
发表时间：
2016-07-01
影响因子：
2.4
通讯作者：
Giger, Maryellen L.
中科院分区：
文献类型：
--
作者：
Huynh, Benjamin Q.;Li, Hui;Giger, Maryellen L.
卷积神经网络(CNN)通过直接从图像数据中学习特征而不是使用解析提取的特征，显示了计算机辅助诊断(CADx)的潜力。然而，由于样本大小和肿瘤表现的差异，CNN很难从零开始训练用于医学图像。相反，转移学习可以用来通过最初为非医疗任务预先训练的CNN从医学图像中提取肿瘤信息，从而减少了对大型数据集的需求。我们的数据库包括219个乳腺病变(607张全视野数字化乳房X光摄影图像)。我们比较了基于CNN提取的图像特征和我们先前计算机提取的肿瘤特征的支持向量机分类器在区分乳腺良恶性病变的任务中的作用。以受试者工作特征(ROC)曲线下的面积为性能指标进行五重交叉验证(按病变)。结果表明，基于CNN提取的特征的分类器(使用转移学习)与使用分析性提取的特征的分类器的性能相当[ROC曲线下的面积(AUC)=0.81]。此外，基于这两种类型的集成分类器的性能明显好于单独使用任何一种类型的分类器(Auc=0.86vs.0.81，p=0.022)。我们的结论是，转移学习可以改进当前的CADx方法，同时还可以提供不需要大数据集的独立分类器，从而促进放射组学和精确医学中的机器学习方法。(C)2016年光学仪器工程师学会(SPIE)
Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve (AUC) = 0.81]. Further, the performance of ensemble classifiers based on both types was significantly better than that of either classifier type alone (AUC = 0.86 versus 0.81, p = 0.022). We conclude that transfer learning can improve current CADx methods while also providing standalone classifiers without large datasets, facilitating machine-learning methods in radiomics and precision medicine. (C) 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)