We propose a method for synthesizing cardiac MR images with plausible heart shapes and realistic appearances for the purpose of generating labeled data for deep-learning (DL) training. It breaks down the image synthesis into label deformation and label-to-image translation tasks. The former is achieved via latent space interpolation in a VAE model, while the latter is accomplished via a conditional GAN model. We devise an approach for label manipulation in the latent space of the trained VAE model, namely pathology synthesis, aiming to synthesize a series of pseudo-pathological synthetic subjects with characteristics of a desired heart disease. Furthermore, we propose to model the relationship between 2D slices in the latent space of the VAE via estimating the correlation coefficient matrix between the latent vectors and utilizing it to correlate elements of randomly drawn samples before decoding to image space. This simple yet effective approach results in generating 3D consistent subjects from 2D slice-by-slice generations. Such an approach could provide a solution to diversify and enrich the available database of cardiac MR images and to pave the way for the development of generalizable DL-based image analysis algorithms. The code will be available at https://github.com/sinaamirrajab/CardiacPathologySynthesis.
翻译:我们提出一种方法,将心脏MR图象与合理的心脏形状和现实外观结合起来,以生成标签数据,供深造(DL)培训使用,将图像合成分为标签变形和标签到图像翻译任务,前者是通过VAE模型的潜在空间内插而实现的,而后者则通过有条件的GAN模型实现。我们在经过培训的VAE模型的潜在空间,即病理合成中设计了一种标签操作方法,目的是合成一系列具有理想心脏病特征的假病合成主题。此外,我们提议通过估计潜载矢量之间的相关系数矩阵并利用它来将随机抽取样本的相关要素解密到图像空间,来模拟VAE潜在空间中的2D切片之间的关系。这一简单而有效的方法可以产生2D切切切切除/阴性世代的3D一致主题。这种方法可以提供一种解决办法,使现有的心脏ML图像数据库多样化和丰富,并为开发基于通用的DL-MR/Carmabasimes的图像分析铺平道路。