Recently, both supervised and unsupervised deep learning methods have been widely applied on the CT metal artifact reduction (MAR) task. Supervised methods such as Dual Domain Network (Du-DoNet) work well on simulation data; however, their performance on clinical data is limited due to domain gap. Unsupervised methods are more generalized, but do not eliminate artifacts completely through the sole processing on the image domain. To combine the advantages of both MAR methods, we propose an unpaired dual-domain network (U-DuDoNet) trained using unpaired data. Unlike the artifact disentanglement network (ADN) that utilizes multiple encoders and decoders for disentangling content from artifact, our U-DuDoNet directly models the artifact generation process through additions in both sinogram and image domains, which is theoretically justified by an additive property associated with metal artifact. Our design includes a self-learned sinogram prior net, which provides guidance for restoring the information in the sinogram domain, and cyclic constraints for artifact reduction and addition on unpaired data. Extensive experiments on simulation data and clinical images demonstrate that our novel framework outperforms the state-of-the-art unpaired approaches.
翻译:最近,在CT金属工艺品减少(MAR)任务中,广泛应用了监督和不受监督的深层学习方法。在模拟数据方面,双域网(Du-DoNet)等受监督方法对模拟数据效果良好;然而,其临床数据的性能因域差而受到限制。不受监督的方法较为普遍,但并不完全通过图像域的唯一处理来消除文物。为了结合这两种MAR方法的优势,我们提议使用未受保护的数据培训的未受监督的双域网(U-DuDoNet)。不同于利用多种编码器和解密器将内容与文物脱钩的文物分解网络(ADN),我们的U-DuDoNet直接通过在螺旋图和图像域中的添加来模拟工艺品生成过程,这在理论上是由与金属工艺品相关的添加属性所证明的。我们的设计包括一个自学的罪理图前网,为恢复罪理学领域信息提供指导,以及用于减少和添加未受委托数据的周期限制。关于模拟和临床图面图面框架的大规模模拟和临床图像实验,展示了我们新的模型和临床图状。