Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images
This work addresses the problem of reducing radiation exposure in CT scans for patients by enhancing image quality through denoising, representing an incremental improvement in medical imaging methods.
The paper tackles CT image denoising by proposing a multi-cycle-consistent adversarial network (MCCAN) that uses intermediate domains and enforces local and global cycle-consistency, resulting in improved denoising quality over CCADN with slightly less computation.
As one of the most commonly ordered imaging tests, computed tomography (CT) scan comes with inevitable radiation exposure that increases the cancer risk to patients. However, CT image quality is directly related to radiation dose, thus it is desirable to obtain high-quality CT images with as little dose as possible. CT image denoising tries to obtain high dose like high-quality CT images (domain X) from low dose low-quality CTimages (domain Y), which can be treated as an image-to-image translation task where the goal is to learn the transform between a source domain X (noisy images) and a target domain Y (clean images). In this paper, we propose a multi-cycle-consistent adversarial network (MCCAN) that builds intermediate domains and enforces both local and global cycle-consistency for edge denoising of CT images. The global cycle-consistency couples all generators together to model the whole denoising process, while the local cycle-consistency imposes effective supervision on the process between adjacent domains. Experiments show that both local and global cycle-consistency are important for the success of MCCAN, which outperformsCCADN in terms of denoising quality with slightly less computation resource consumption.