Semi-supervised task-driven data augmentation for medical image segmentation
Semi-supervised task-driven data augmentation for medical image segmentation
复制标题
DOI：
10.1016/j.media.2020.101934
复制
发表时间：
2021-02-01
影响因子：
10.9
通讯作者：
Konukoglu, Ender
中科院分区：
文献类型：
--
作者：
Chaitanya, Krishna;Karani, Neerav;Konukoglu, Ender
基于监督学习的分割方法通常需要大量带注释的训练数据才能在测试时很好地泛化。在医学应用中，管理这样的数据集并不是一个有利的选择，因为从专家那里获取大量带注释的样本既耗时又昂贵。因此，在文献中已经提出了许多方法，用于使用有限的注释示例进行学习。不幸的是，在文献中提出的方法还没有产生显着的收益超过随机数据增强图像分割，随机增强本身不产生高精度。在这项工作中，我们提出了一种新的任务驱动的数据增强方法，用于使用有限的标记数据进行学习，其中合成数据生成器针对分割任务进行了优化。所提出的方法的生成器模型的强度和形状的变化，使用两组变换，作为添加剂的强度变换和变形场。这两种变换都使用半监督框架中的标记和未标记示例进行优化。我们在三个医学数据集，即心脏，前列腺和胰腺上的实验表明，所提出的方法在有限的注释设置中显着优于标准增强和半监督图像分割方法。(C)2020年，任作家。由爱思唯尔公司出版
Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large number of annotated samples from experts is time-consuming and expensive. Consequently, numerous methods have been proposed in the literature for learning with limited annotated examples. Unfortunately, the proposed approaches in the literature have not yet yielded significant gains over random data augmentation for image segmentation, where random augmentations themselves do not yield high accuracy. In this work, we propose a novel task-driven data augmentation method for learning with limited labeled data where the synthetic data generator, is optimized for the segmentation task. The generator of the proposed method models intensity and shape variations using two sets of transformations, as additive intensity transformations and deformation fields. Both transformations are optimized using labeled as well as unlabeled examples in a semi-supervised framework. Our experiments on three medical datasets, namely cardiac, prostate and pancreas, show that the proposed approach significantly outperforms standard augmentation and semi-supervised approaches for image segmentation in the limited annotation setting. (C) 2020 The Authors. Published by Elsevier B.V.