Visual Attention Network for Low Dose CT
This work addresses image quality issues in low-dose CT for medical imaging applications, representing an incremental improvement by integrating visual attention into an existing GAN framework.
The paper tackles noise and artifacts in low-dose CT imaging by applying a generative adversarial network (GAN) with a visual attention mechanism, resulting in improved image quality as demonstrated qualitatively and quantitatively on clinical CT images.
Noise and artifacts are intrinsic to low dose CT (LDCT) data acquisition, and will significantly affect the imaging performance. Perfect noise removal and image restoration is intractable in the context of LDCT due to the statistical and technical uncertainties. In this paper, we apply the generative adversarial network (GAN) framework with a visual attention mechanism to deal with this problem in a data-driven/machine learning fashion. Our main idea is to inject visual attention knowledge into the learning process of GAN to provide a powerful prior of the noise distribution. By doing this, both the generator and discriminator networks are empowered with visual attention information so they will not only pay special attention to noisy regions and surrounding structures but also explicitly assess the local consistency of the recovered regions. Our experiments qualitatively and quantitatively demonstrate the effectiveness of the proposed method with clinic CT images.