Ambient-Pix2PixGAN for Translating Medical Images from Noisy Data
This addresses the challenge of applying deep learning methods to noisy medical images, which is an incremental improvement for medical imaging applications.
The paper tackled the problem of medical image-to-image translation from noisy data by proposing Ambient-Pix2PixGAN, a conditional GAN architecture that can be trained on noisy measurements to produce high-quality translated images, as demonstrated in MRI-to-PET translation studies.
Image-to-image translation is a common task in computer vision and has been rapidly increasing the impact on the field of medical imaging. Deep learning-based methods that employ conditional generative adversarial networks (cGANs), such as Pix2PixGAN, have been extensively explored to perform image-to-image translation tasks. However, when noisy medical image data are considered, such methods cannot be directly applied to produce clean images. Recently, an augmented GAN architecture named AmbientGAN has been proposed that can be trained on noisy measurement data to synthesize high-quality clean medical images. Inspired by AmbientGAN, in this work, we propose a new cGAN architecture, Ambient-Pix2PixGAN, for performing medical image-to-image translation tasks by use of noisy measurement data. Numerical studies that consider MRI-to-PET translation are conducted. Both traditional image quality metrics and task-based image quality metrics are employed to assess the proposed Ambient-Pix2PixGAN. It is demonstrated that our proposed Ambient-Pix2PixGAN can be successfully trained on noisy measurement data to produce high-quality translated images in target imaging modality.