SA-GAN: Structure-Aware GAN for Organ-Preserving Synthetic CT Generation
This addresses the problem of MR-only treatment planning for medical professionals in disease sites with internal organ changes, but it is an incremental improvement over existing GAN-based methods.
The paper tackles the challenge of generating synthetic CT images from MRI in medical imaging, where inconsistencies due to organ changes between modalities hinder training, by proposing SA-GAN, which preserves organ shapes and locations, resulting in clinically acceptable accuracy for synthetic CTs and organ segmentation on a pelvic dataset.
In medical image synthesis, model training could be challenging due to the inconsistencies between images of different modalities even with the same patient, typically caused by internal status/tissue changes as different modalities are usually obtained at a different time. This paper proposes a novel deep learning method, Structure-aware Generative Adversarial Network (SA-GAN), that preserves the shapes and locations of in-consistent structures when generating medical images. SA-GAN is employed to generate synthetic computed tomography (synCT) images from magnetic resonance imaging (MRI) with two parallel streams: the global stream translates the input from the MRI to the CT domain while the local stream automatically segments the inconsistent organs, maintains their locations and shapes in MRI, and translates the organ intensities to CT. Through extensive experiments on a pelvic dataset, we demonstrate that SA-GAN provides clinically acceptable accuracy on both synCTs and organ segmentation and supports MR-only treatment planning in disease sites with internal organ status changes.