We developed a novel 3D electronic cleansing (EC) method for CT colonography (CTC) based on a generativeadversarial network (GAN). GANs are machine-learning algorithms that can be trained to translate an input imagedirectly into a desired output image without using explicit manual annotations. A 3D-GAN EC scheme was developedby extending a 2D-pix2pix GAN model to volumetric CTC datasets based on 3D-convolutional kernels. To overcomethe usual need for paired input-output training data, the 3D-GAN model was trained by use of a self-supervised learningscheme where the training data were constructed iteratively as a combination of volumes of interest (VOIs) from pairedanthropomorphic colon phantom CTC datasets and input VOIs from the unseen clinical input CTC dataset where thevirtually cleansed output sample pairs were self-generated by use of a progressive cleansing method. Our preliminaryevaluation with a clinical fecal-tagging CTC case showed that the 3D-GAN EC scheme can substantially reduce theprocessing time and EC image artifacts in comparison to our previous deep-learning EC scheme.
展开▼