Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN
This method offers a solution for radiologists to obtain different CT kernel images post-hoc without additional patient exposure, which is an incremental improvement for medical imaging workflows.
This paper addresses the problem of converting CT images between different filter kernels without requiring new patient scans. They propose a CycleGAN-based method with AdaIN that can translate images between two kernels and generate intermediate kernel images, achieving quality comparable to supervised methods.
X-ray computed tomography (CT) uses different filter kernels to highlight different structures. Since the raw sinogram data is usually removed after the reconstruction, in case there are additional need for other types of kernel images that were not previously generated, the patient may need to be scanned again. Accordingly, there exists increasing demand for post-hoc image domain conversion from one kernel to another without sacrificing the image quality. In this paper, we propose a novel unsupervised continuous kernel conversion method using cycle-consistent generative adversarial network (cycleGAN) with adaptive instance normalization (AdaIN). Even without paired training data, not only can our network translate the images between two different kernels, but it can also convert images along the interpolation path between the two kernel domains. We also show that the quality of generated images can be further improved if intermediate kernel domain images are available. Experimental results confirm that our method not only enables accurate kernel conversion that is comparable to supervised learning methods, but also generates intermediate kernel images in the unseen domain that are useful for hypopharyngeal cancer diagnosis.