Generalization error analysis for deep convolutional neural network with transfer learning in breast cancer diagnosis.
Generalization error analysis for deep convolutional neural network with transfer learning in breast cancer diagnosis.
复制标题
DOI：
10.1088/1361-6560/ab82e8
复制
发表时间：
2020-05-11
影响因子：
3.5
通讯作者：
Richter CD
中科院分区：
文献类型：
--
作者：
Samala RK;Chan HP;Hadjiiski LM;Helvie MA;Richter CD
深度卷积神经网络（DCNN），现在通常被称为人工智能（AI），已经显示出在过去几十年中开发的医学成像中改进以前计算机辅助工具的潜力。DCNN有数百万个需要训练的自由参数，但对于大多数医学成像任务来说，训练样本集的大小有限，因此通常使用迁移学习。自动数据挖掘可能是扩大收集的数据集的有效方法，但数据可能是嘈杂的，例如不正确的标签甚至错误的图像类型。在这项工作中，我们研究了在医学成像中使用迁移学习的DCNN的泛化误差，用于对乳房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数据或噪声标签的训练集。DCNN的学习和记忆之间的平衡是通过改变训练集中损坏数据的比例来控制的。通过训练集和测试集的受试者工作特征曲线下的面积以及迁移学习后的权重变化来分析DCNN的泛化误差。该研究表明，DCNN用于此类任务的迁移学习策略需要适当设计，考虑到现有训练集的限制，这些训练集对于手头的分类任务具有有限的大小和质量，以最大限度地减少记忆并提高泛化能力。
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 images. 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.
登录
查看更多内容
影响因子：
3.8
作者：
Samala, Ravi K.;Chan, Heang-Ping;Cha, Kenny
通讯作者：
Cha, Kenny
影响因子：
9.8
作者：
Lee RS;Gimenez F;Hoogi A;Miyake KK;Gorovoy M;Rubin DL
通讯作者：
Rubin DL
影响因子：
19.7
作者：
Lakhani, Paras;Sundaram, Baskaran
通讯作者：
Sundaram, Baskaran
一种用于分类乳房乳房密度类别的深度学习方法。
影响因子：
3.8
作者：
Mohamed AA;Berg WA;Peng H;Luo Y;Jankowitz RC;Wu S
通讯作者：
Wu S
DOI：
10.1007/s11548-018-1843-2
发表时间：
2018-12
影响因子：
3
作者：
Byra M;Styczynski G;Szmigielski C;Kalinowski P;Michałowski Ł;Paluszkiewicz R;Ziarkiewicz-Wróblewska B;Zieniewicz K;Sobieraj P;Nowicki A
通讯作者：
Nowicki A