Abstract
Typically, deep learning architectures are handcrafted for their respective learning problem. As an alternative, neural architecture search (NAS) has been proposed where the architecture's structure is learned in an additional optimization step. For the medical imaging domain, this approach is very promising as there are diverse problems and imaging modalities that require architecture design. However, NAS is very time-consuming and medical learning problems often involve high-dimensional data with high computational requirements. We propose an efficient approach for NAS in the context of medical, image-based deep learning problems by searching for architectures on low-dimensional data which are subsequently transferred to high-dimensional data. For OCT-based layer segmentation, we demonstrate that a search on 1D data reduces search time by 87.5% compared to a search on 2D data while the final 2D models achieve similar performance.
Abstract (translated)
通常，深度学习体系结构是针对各自的学习问题手工构建的。作为替代方案，神经架构搜索（NAS）已经被提出，其中架构的结构是在一个额外的优化步骤中学习的。对于医学成像领域，这种方法是非常有前途的，因为有各种各样的问题和成像方式需要架构设计。然而，NAS非常耗时，医学学习问题通常涉及高维数据和高计算要求。我们提出了一种有效的方法，在医学，基于图像的深度学习问题的背景下，通过寻找低维数据的架构，然后转移到高维数据。对于基于OCT的层分割，我们证明在一维数据上搜索与在二维数据上搜索相比减少了87.5%的搜索时间，而最终的二维模型实现了类似的性能。
URL
https://arxiv.org/abs/1905.02590
