46 Deep MR to CT synthesis using paired data in the pelvic area

Introduction. The establishment of a MRI-only workflow in radiotherapy depends on the ability to generate an accurate synthetic-CT (sCT) for dose calculation. Previously proposed methods have used a Generative Adversarial Network (GAN) to generate a fast sCT in order to simplify the clinical workflow and reduce uncertainties. We used a conditional Generative Adversarial Network (cGAN) framework called pix2pixHD [1] which addresses the two main issues of a GAN: the difficulty of generating high-resolution images and the lack of details in the previous high-resolution results.

Source: Physica Medica: European Journal of Medical Physics - November 30, 2019 Category: General Medicine Authors: K.N.D. Brou Boni, L. Vanquin, A. Wagner, J. Klein, D. Pasquier, N. Reynaert Source Type: research