End-to-End Adversarial Retinal Image Synthesis
End-to-End Adversarial Retinal Image Synthesis
复制标题
DOI：
10.1109/tmi.2017.2759102
复制
发表时间：
2018-03-01
影响因子：
10.6
通讯作者：
Campilho, Aurelio
中科院分区：
文献类型：
--
作者：
Costa, Pedro;Galdran, Adrian;Campilho, Aurelio
在医学图像分析应用中，大量注释数据的可用性变得越来越重要。然而，带注释的医疗数据往往稀缺且获取成本高昂。在本文中，我们通过应用基于对抗性学习的最新技术来解决合成视网膜彩色图像的问题。在这种情况下，训练生成模型以最大化第二个模型提供的损失函数，试图将其输出分类为真实的或合成的。特别是，我们建议为视网膜血管网络合成任务实现一个对抗性自动编码器。我们使用生成的血管树作为生成彩色视网膜图像的中间阶段，这是通过生成对抗网络完成的。这两种模型都需要优化几乎处处可微的损失函数，这使得我们能够联合训练它们。由此产生的模型提供了一个端到端的视网膜图像合成系统，能够通过从我们施加到相关潜在空间的简单概率分布中进行采样，生成用户需要的尽可能多的视网膜图像及其相应的血管网络。我们表明，学习到的潜在空间包含明确定义的语义结构，这意味着我们可以在视网膜图像空间中执行计算，例如，在两个视网膜图像之间平滑地插入新数据点。视觉和定量结果表明，合成图像与训练集中的图像有很大不同，同时在解剖学上也保持一致并显示出合理的视觉质量。
In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.