Deep convolutional neural network (DCNN), now popularly called artificial intelligence (AI), has shown the potential to improve over previous computer-assisted tools in medical imaging developed in the past decades. A DCNN has millions of free parameters that need to be trained, but the training sample set is limited in size for most medical imaging tasks so that transfer learning is typically used. Automatic data mining may be an efficient way to enlarge the collected data set but the data can be noisy such as incorrect labels or even a wrong type of image. In this work we studied the generalization error of DCNN with transfer learning in medical imaging for the task of classifying malignant and benign masses on mammograms. With a finite available data set, we simulated a training set containing corrupted data or noisy labels. The balance between learning and memorization of the DCNN was manipulated by varying the proportion of corrupted data in the training set. The generalization error of DCNN was analyzed by the area under the receiver operating characteristic curve for the training and test sets and the weight changes after transfer learning. The study demonstrates that the transfer learning strategy of DCNN for such tasks needs to be designed properly, taking into consideration the constraints of the available training set having limited size and quality for the classification task at hand, to minimize memorization and improve generalizability.

中文翻译：

---

带转移学习的深度卷积神经网络广义误差分析在乳腺癌诊断中的应用

深度卷积神经网络（DCNN）现在被普遍称为人工智能（AI），它显示出有可能超越过去几十年来开发的医学成像中的计算机辅助工具。DCNN具有数百万个需要训练的自由参数，但是对于大多数医学成像任务而言，训练样本集的大小受到限制，因此通常使用转移学习。自动数据挖掘可能是扩大收集到的数据集的有效方法，但是数据可能很杂乱，例如标签不正确，甚至图像类型错误。在这项工作中，我们研究了在医学成像中采用转移学习的DCNN泛化误差，以对乳腺X线照片上的恶性和良性肿块进行分类。利用有限的可用数据集，我们模拟了包含损坏的数据或嘈杂标签的训练集。通过更改训练集中损坏数据的比例，可以控制DCNN的学习与记忆之间的平衡。通过训练和测试集的接收器工作特性曲线下的面积以及传递学习后的权重变化，分析了DCNN的泛化误差。研究表明，针对此类任务的DCNN转移学习策略需要适当设计，要考虑到现有训练集的局限性，因为现有训练集的规模和质量有限，可以最大程度地减少记忆并提高通用性。通过训练和测试集的接收器工作特性曲线下的面积以及传递学习后的权重变化，分析了DCNN的泛化误差。研究表明，针对此类任务的DCNN转移学习策略需要适当设计，要考虑到现有训练集的局限性，因为现有训练集的规模和质量有限，可以最大程度地减少记忆并提高通用性。通过训练和测试集的接收器工作特性曲线下的面积以及传递学习后的权重变化，分析了DCNN的泛化误差。研究表明，针对此类任务的DCNN转移学习策略需要适当设计，要考虑到现有训练集的局限性，因为现有训练集的规模和质量有限，可以最大程度地减少记忆并提高通用性。