期刊
MEDICAL IMAGE ANALYSIS
卷 49, 期 -, 页码 14-26出版社
ELSEVIER
DOI: 10.1016/j.media.2018.07.001
关键词
Data-driven image synthesis; Retinal fundus image synthesis; Deep learning; Neuronal image synthesis
类别
资金
- CSC Chinese Government Scholarship
- A*STAR JCO grants
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. (C) 2018 The Authors. Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据