Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis
Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis
复制标题
DOI：
10.1016/j.media.2020.101759
复制
发表时间：
2020-10-01
影响因子：
10.9
通讯作者：
Gholipour, Ali
中科院分区：
文献类型：
--
作者：
Karimi, Davood;Dou, Haoran;Gholipour, Ali
深度学习模型的监督训练需要大型标记数据集。越来越多的人对获得用于医学图像分析应用的这样的数据集感兴趣。然而，标签噪声的影响尚未得到足够的重视。最近的研究表明，标签噪声可以显著影响许多机器学习和计算机视觉应用中深度学习模型的性能。这对于医疗应用尤其重要，因为数据集通常很小，标记需要领域专业知识，并且观察者之间和观察者内部的差异很大，错误的预测可能会影响直接影响人类健康的决策。在本文中，我们首先回顾了深度学习中处理标签噪声的最新技术。然后，我们回顾了在医学图像分析的深度学习中处理标签噪声的研究。我们的综述表明，最近在深度学习中处理标签噪声的进展在很大程度上没有被医学图像分析界所注意。为了帮助更好地了解问题的严重程度及其潜在的补救措施，我们对三个具有不同类型标签噪声的医学成像数据集进行了实验，研究了几种现有的策略，并开发了新的方法来对抗标签噪声的负面影响。根据这些实验的结果和我们对文献的回顾，我们提出了一些建议，可以用来减轻不同类型的标签噪声对医学图像分析训练的深度模型的影响。我们希望本文能够帮助医学图像分析研究人员和开发人员选择和设计新技术，有效地处理深度学习中的标签噪声。(c)2020 Elsevier B.V.保留所有权利。
Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high interand intra-observer variability, and erroneous predictions may influence decisions that directly impact human health. In this paper, we first review the state-of-theart in handling label noise in deep learning. Then, we review studies that have dealt with label noise in deep learning for medical image analysis. Our review shows that recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image analysis community. To help achieve a better understanding of the extent of the problem and its potential remedies, we conducted experiments with three medical imaging datasets with different types of label noise, where we investigated several existing strategies and developed new methods to combat the negative effect of label noise. Based on the results of these experiments and our review of the literature, we have made recommendations on methods that can be used to alleviate the effects of different types of label noise on deep models trained for medical image analysis. We hope that this article helps the medical image analysis researchers and developers in choosing and devising new techniques that effectively handle label noise in deep learning. (c) 2020 Elsevier B.V. All rights reserved.