arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.12296eess.IVcs.CV
收藏

一种用于高分辨率视网膜图像生成和分割的两级GAN算法

A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

University of Siena(锡耶纳大学);University of Florence(佛罗伦萨大学)

Paolo Andreini, Simone Bonechi, Monica Bianchini, Alessandro Mecocci, Franco Scarselli, Andrea Sodi

摘要:

近年来,深度学习在计算机视觉中的应用越来越普遍。然而,深度架构的有效训练通常依赖于大量带注释的数据集。这在医学领域中是至关重要的,在医学领域中,获得注释图像是困难且昂贵的。在本文中,我们使用生成对抗网络(GANs)来合成高质量的视网膜图像,以及相应的语义标签映射,以在训练过程中代替真实图像。与其他先前的提议不同,我们提出了两步方法:首先,训练逐渐增长的GAN以生成描述血管结构(即脉管系统)的语义标签图;其次,使用图像到图像转换方法从生成的脉管系统获得逼真的视网膜图像。通过只使用少量的训练样本,我们的方法生成逼真的高分辨率图像,可以有效地用于扩大小的可用数据集。在训练过程中,使用生成的图像代替真实数据获得了可比的结果。所提出的方法的实际可行性已被证明,通过将其应用于两个良好建立的基准集视网膜血管分割,都包含一个非常小的训练样本。我们的方法相对于最先进的技术获得了更好的性能。

英文摘要:

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where it is difficult and expensive to obtain annotated images. In this paper, we use Generative Adversarial Networks (GANs) for synthesizing high quality retinal images, along with the corresponding semantic label-maps, to be used instead of real images during the training process. Differently from other previous proposals, we suggest a two step approach: first, a progressively growing GAN is trained to generate the semantic label-maps, which describe the blood vessel structure (i.e. vasculature); second, an image-to-image translation approach is used to obtain realistic retinal images from the generated vasculature. By using only a handful of training samples, our approach generates realistic high resolution images, that can be effectively used to enlarge small available datasets. Comparable results have been obtained employing the generated images in place of real data during training. The practical viability of the proposed approach has been demonstrated by applying it on two well established benchmark sets for retinal vessel segmentation, both containing a very small number of training samples. Our method obtained better performances with respect to state-of-the-art techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑