Department of Software and IT Engineering, École de technologie supérieure., 1100 Notre-Dame W., Montreal, Canada.
Taras Shevchenko National University of Kyiv, Volodymyrska St, 60, Kyiv, Ukraine.
Int J Comput Assist Radiol Surg. 2019 Oct;14(10):1785-1794. doi: 10.1007/s11548-019-02022-z. Epub 2019 Jul 8.
We aim to perform generation of angiograms for various vascular structures as a mean of data augmentation in learning tasks. The task is to enhance the realism of vessels images generated from an anatomically realistic cardiorespiratory simulator to make them look like real angiographies.
The enhancement is performed by applying the CycleGAN deep network for transferring the style of real angiograms acquired during percutaneous interventions into a data set composed of realistically simulated arteries.
The cycle consistency was evaluated by comparing an input simulated image with the one obtained after two cycles of image translation. An average structural similarity (SSIM) of 0.948 on our data sets has been obtained. The vessel preservation was measured by comparing segmentations of an input image and its corresponding enhanced image using Dice coefficient.
We proposed an application of the CycleGAN deep network for enhancing the artificial data as an alternative to classical data augmentation techniques for medical applications, particularly focused on angiogram generation. We discussed success and failure cases, explaining conditions for the realistic data augmentation which respects both the complex physiology of arteries and the various patterns and textures generated by X-ray angiography.
我们旨在通过生成各种血管结构的血管造影图像来实现学习任务的数据增强。任务是增强从解剖学逼真的心肺模拟器生成的血管图像的逼真度，使其看起来像真实的血管造影。
通过应用 CycleGAN 深度网络来实现增强，该网络将在经皮介入过程中获得的真实血管造影的风格转移到由真实模拟动脉组成的数据集。
通过比较输入的模拟图像和经过两次图像翻译循环后的图像，评估循环一致性。在我们的数据集上获得了平均结构相似性 (SSIM) 为 0.948。通过使用 Dice 系数比较输入图像及其对应的增强图像的分割，评估血管保留。
我们提出了一种应用 CycleGAN 深度网络来增强人工数据的方法，作为医学应用中经典数据增强技术的替代方法，特别是专注于血管造影生成。我们讨论了成功和失败的案例，解释了在尊重动脉的复杂生理学以及 X 射线血管造影生成的各种模式和纹理的条件下进行真实数据增强的条件。
