Bio Imaging and Signal Processing Laboratory, Department of Bio and Brain Engineering, KAIST, Daejeon, Republic of Korea.
Department of Radiology, University of Ulsan College of Medicine, Seoul, Republic of Korea.
Med Phys. 2019 Feb;46(2):550-562. doi: 10.1002/mp.13284. Epub 2018 Dec 26.
In multiphase coronary CT angiography (CTA), a series of CT images are taken at different levels of radiation dose during the examination. Although this reduces the total radiation dose, the image quality during the low-dose phases is significantly degraded. Recently, deep neural network approaches based on supervised learning technique have demonstrated impressive performance improvement over conventional model-based iterative methods for low-dose CT. However, matched low- and routine-dose CT image pairs are difficult to obtain in multiphase CT. To address this problem, we aim at developing a new deep learning framework.
We propose an unsupervised learning technique that can remove the noise of the CT images in the low-dose phases by learning from the CT images in the routine dose phases. Although a supervised learning approach is not applicable due to the differences in the underlying heart structure in two phases, the images are closely related in two phases, so we propose a cycle-consistent adversarial denoising network to learn the mapping between the low- and high-dose cardiac phases.
Experimental results showed that the proposed method effectively reduces the noise in the low-dose CT image while preserving detailed texture and edge information. Moreover, thanks to the cyclic consistency and identity loss, the proposed network does not create any artificial features that are not present in the input images. Visual grading and quality evaluation also confirm that the proposed method provides significant improvement in diagnostic quality.
The proposed network can learn the image distributions from the routine-dose cardiac phases, which is a big advantage over the existing supervised learning networks that need exactly matched low- and routine-dose CT images. Considering the effectiveness and practicability of the proposed method, we believe that the proposed can be applied for many other CT acquisition protocols.
在多期冠状动脉 CT 血管造影（CTA）中，在检查过程中会在不同辐射剂量水平下拍摄一系列 CT 图像。虽然这降低了总辐射剂量，但低剂量阶段的图像质量会显著降低。最近，基于监督学习技术的深度神经网络方法在低剂量 CT 方面的表现优于传统的基于模型的迭代方法。然而，在多期 CT 中，很难获得匹配的低剂量和常规剂量 CT 图像对。为了解决这个问题，我们旨在开发一种新的深度学习框架。
我们提出了一种无监督学习技术，通过从常规剂量阶段的 CT 图像中学习，可以去除低剂量阶段 CT 图像的噪声。尽管由于两个阶段中心脏结构的差异，监督学习方法不适用，但两个阶段的图像密切相关，因此我们提出了一种循环一致的对抗去噪网络，以学习低剂量和高剂量心脏阶段之间的映射。
实验结果表明，该方法有效地降低了低剂量 CT 图像的噪声，同时保留了详细的纹理和边缘信息。此外，由于循环一致性和身份损失，所提出的网络不会创建任何在输入图像中不存在的人为特征。视觉分级和质量评估也证实，该方法在诊断质量方面有显著提高。
所提出的网络可以从常规剂量心脏阶段学习图像分布，这是现有需要完全匹配的低剂量和常规剂量 CT 图像的监督学习网络的一个很大优势。考虑到所提出方法的有效性和实用性，我们相信该方法可以应用于许多其他 CT 采集协议。
