arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.04798cs.CV
收藏

Hydranet:回归神经网络的数据增强

Hydranet: Data Augmentation for Regression Neural Networks

Erasmus MC - University Medical Center Rotterdam(伊拉斯姆斯医学中心——鹿特丹大学医学中心);Erasmus MC(伊拉斯姆斯医学中心);TU Delft(代尔夫特理工大学);University of Copenhagen(哥本哈根大学)

Florian Dubost, Gerda Bortsova, Hieab Adams, M. Arfan Ikram, Wiro Niessen, Meike Vernooij, Marleen de Bruijne

摘要:

深度学习技术经常被批评为严重依赖于大量的标记数据。这个问题在医学图像分析中更具挑战性,因为注释者的专业知识通常很稀缺。我们提出了一种新的数据增强方法来正则化神经网络回归器,该回归器从每个图像的单个全局标签中学习。该方法的原理是通过重组现有样本来创建新样本。我们证明了我们的算法在两个任务上的性能:估计基底神经节中血管周围空间扩大的数量,以及估计白质高信号体积。我们表明,所提出的方法提高了更基本的数据增强的性能。所提出的方法在第一个任务上达到了0.73的地面实况和网络预测之间的组内相关系数,在第二个任务上达到了0.84,只使用了25到30次扫描,每次扫描使用一个全局标签进行训练。在相同的训练扫描次数下,更传统的数据增强方法在第一个任务上只能达到0.68的组内相关系数,在第二个任务上只能达到0.79。

英文摘要:

Deep learning techniques are often criticized to heavily depend on a large quantity of labeled data. This problem is even more challenging in medical image analysis where the annotator expertise is often scarce. We propose a novel data-augmentation method to regularize neural network regressors that learn from a single global label per image. The principle of the method is to create new samples by recombining existing ones. We demonstrate the performance of our algorithm on two tasks: estimation of the number of enlarged perivascular spaces in the basal ganglia, and estimation of white matter hyperintensities volume. We show that the proposed method improves the performance over more basic data augmentation. The proposed method reached an intraclass correlation coefficient between ground truth and network predictions of 0.73 on the first task and 0.84 on the second task, only using between 25 and 30 scans with a single global label per scan for training. With the same number of training scans, more conventional data augmentation methods could only reach intraclass correlation coefficients of 0.68 on the first task, and 0.79 on the second task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑