Beijing Institute of Technology, China; Bioinformatics Institute, A*STAR, Singapore.
Beijing Institute of Technology, China.
Med Image Anal. 2018 Oct;49:14-26. doi: 10.1016/j.media.2018.07.001. Epub 2018 Jul 4.
This paper aims at synthesizing multiple realistic-looking retinal (or neuronal) images from an unseen tubular structured annotation that contains the binary vessel (or neuronal) morphology. The generated phantoms are expected to preserve the same tubular structure, and resemble the visual appearance of the training images. Inspired by the recent progresses in generative adversarial nets (GANs) as well as image style transfer, our approach enjoys several advantages. It works well with a small training set with as few as 10 training examples, which is a common scenario in medical image analysis. Besides, it is capable of synthesizing diverse images from the same tubular structured annotation. Extensive experimental evaluations on various retinal fundus and neuronal imaging applications demonstrate the merits of the proposed approach.
本文旨在从未见的管状结构注释中综合多个逼真的视网膜（或神经元）图像，该注释包含二进制血管（或神经元）形态。生成的幻象应保留相同的管状结构，并类似于训练图像的视觉外观。受最近在生成对抗网络（GAN）以及图像样式转换方面的进展的启发，我们的方法具有多个优点。它可以在仅有 10 个训练示例的小训练集中很好地工作，这在医学图像分析中是常见的情况。此外，它能够从相同的管状结构注释中合成多种图像。在各种视网膜眼底和神经元成像应用中的广泛实验评估证明了所提出方法的优势。
