Transfer Learning Improves Supervised Image Segmentation Across Imaging Protocols
Transfer Learning Improves Supervised Image Segmentation Across Imaging Protocols
复制标题
DOI：
10.1109/tmi.2014.2366792
复制
发表时间：
2015-05-01
影响因子：
10.6
通讯作者：
de Bruijne, Marleen
中科院分区：
文献类型：
--
作者：
van Opbroek, Annegreet;Ikram, M. Arfan;de Bruijne, Marleen
不同扫描仪或不同成像方案获得的图像之间的差异是生物医学图像自动分割的主要挑战。这种变化尤其阻碍了其他成功的监督学习技术的应用，监督学习技术为了表现良好，通常需要大量精确代表目标数据的标记训练数据。因此，我们建议将迁移学习用于图像分割。迁移学习技术可以处理训练数据和目标数据之间分布的差异，因此可以提高跨扫描仪和扫描协议分割的监督学习性能。我们提出了四个迁移分类器，它们可以只使用少量具有代表性的训练数据，以及大量其他特征略有不同的训练数据来训练分类方案。将四种转移分类器与标准监督分类器在两个多位点数据的磁共振成像脑分割任务（白质、灰质和脑脊液分割）上的性能进行了比较；白质/质谱分割。实验表明，当只有少量具有代表性的训练数据可用时，迁移学习可以大大优于常见的监督学习方法，将分类误差降低高达60%。
The variation between images obtained with different scanners or different imaging protocols presents a major challenge in automatic segmentation of biomedical images. This variation especially hampers the application of otherwise successful supervised-learning techniques which, in order to perform well, often require a large amount of labeled training data that is exactly representative of the target data. We therefore propose to use transfer learning for image segmentation. Transfer-learning techniques can cope with differences in distributions between training and target data, and therefore may improve performance over supervised learning for segmentation across scanners and scan protocols. We present four transfer classifiers that can train a classification scheme with only a small amount of representative training data, in addition to a larger amount of other training data with slightly different characteristics. The performance of the four transfer classifiers was compared to that of standard supervised classification on two magnetic resonance imaging brain-segmentation tasks with multi-site data: white matter, gray matter, and cerebrospinal fluid segmentation; and white-matter-/MS-lesion segmentation. The experiments showed that when there is only a small amount of representative training data available, transfer learning can greatly outperform common supervised-learning approaches, minimizing classification errors by up to 60%.