ABSTRACT
Recently, unsupervised deep learning methods have shown great potential in image processing. Compared with a large-amount demand for paired training data of supervised methods with a specific task, unsupervised methods can learn a universal and explicit prior information on data distribution and integrate it into the reconstruction process. Therefore, it can be used in various image reconstruction environments without showing degraded performance. The importance of unsupervised learning in MRI reconstruction appears to be growing. Nevertheless, the establishment of prior formulation in unsupervised deep learning varies a lot depending on mathematical approximation and network architectures. In this work, we summarized basic concepts of unsupervised deep learning comprehensively and compared performances of several state-of-the-art unsupervised learning methods for MRI reconstruction.
ABSTRACT
Recently, unsupervised deep learning methods have shown great potential in image processing. Compared with a large-amount demand for paired training data of supervised methods with a specific task, unsupervised methods can learn a universal and explicit prior information on data distribution and integrate it into the reconstruction process. Therefore, it can be used in various image reconstruction environments without showing degraded performance. The importance of unsupervised learning in MRI reconstruction appears to be growing. Nevertheless, the establishment of prior formulation in unsupervised deep learning varies a lot depending on mathematical approximation and network architectures. In this work, we summarized basic concepts of unsupervised deep learning comprehensively and compared performances of several state-of-the-art unsupervised learning methods for MRI reconstruction.
ABSTRACT
Objective To investigate the value of post processing technique of MSCT in the diagnosis of bile duct stones.Methods 89 cases with high density bile stones were collected.All of the images were reconstructed by using surface reconstruction(CPR),multiplanar reconstruction(MPR),volume reconstruction(VR), to clearly show the location, size, number and shape of bile duct stones, and provide accurate image information for clinic.Results 396 cases of bile duct stones were detected in all of the 89 patients,after treatment,the reconstructed image of could accurately show the location,size,number and shape of stones.Conclusion Post-processing technique of MSCT can provide accurate image information for the diagnosis of the the biliary stone,and improve the effectiveness and safety of the operation.