Perception consistency ultrasound image super-resolution via self-supervised CycleGAN
Perception consistency ultrasound image super-resolution via self-supervised CycleGAN
复制标题
DOI：
10.1007/s00521-020-05687-9
复制
发表时间：
2021-01-16
影响因子：
6
通讯作者：
Han, Jungong
中科院分区：
文献类型：
--
作者：
Liu, Heng;Liu, Jianyong;Han, Jungong
由于传感器、传输介质和超声固有特性的限制，超声成像质量一直不理想，尤其是其空间分辨率较低。为了弥补这种情况，最近开发了深度学习网络用于超声图像超分辨率（SR），因为它具有强大的近似能力。然而，目前大多数监督SR方法不适用于超声医学图像，因为医学图像样本总是稀少的，通常，在现实中，没有低分辨率（LR）和高分辨率（HR）的训练对。本文基于自监督和循环生成对抗网络，提出了一种新的感知一致性超声图像SR方法，该方法只需要LR超声数据，并且能够保证生成的SR图像的再退化图像与原始LR图像一致，反之亦然。首先通过图像增强生成测试超声LR图像的HR父子，然后充分利用LR-SR-LR和HR-LR-SR的周期损失和伪随机序列的对抗特性，促使生成器产生更好的感知一致性SR结果。在CCA-US和CCA-US数据集上的PSNR/IFC/SSIM、推理效率和视觉效果的测试结果表明，该方法是有效的，并且优于其他现有方法的上级性能。
Due to the limitations of sensors, the transmission medium, and the intrinsic properties of ultrasound, the quality of ultrasound imaging is always not ideal, especially its low spatial resolution. To remedy this situation, deep learning networks have been recently developed for ultrasound image super-resolution (SR) because of the powerful approximation capability. However, most current supervised SR methods are not suitable for ultrasound medical images because the medical image samples are always rare, and usually, there are no low-resolution (LR) and high-resolution (HR) training pairs in reality. In this work, based on self-supervision and cycle generative adversarial network, we propose a new perception consistency ultrasound image SR method, which only requires the LR ultrasound data and can ensure the re-degenerated image of the generated SR one to be consistent with the original LR image, and vice versa. We first generate the HR fathers and the LR sons of the test ultrasound LR image through image enhancement, and then make full use of the cycle loss of LR-SR-LR and HR-LR-SR and the adversarial characteristics of the discriminator to promote the generator to produce better perceptually consistent SR results. The evaluation of PSNR/IFC/SSIM, inference efficiency and visual effects under the benchmark CCA-US and CCA-US datasets illustrate our proposed approach is effective and superior to other state-of-the-art methods.