摘要 :
Image-to-image translation (I2I) has broad application prospects for assisting physicians in diagnosis of medical image missing scenarios. Considering that there is no medical I2I model constructed from a geometric view of simulta...
展开
Image-to-image translation (I2I) has broad application prospects for assisting physicians in diagnosis of medical image missing scenarios. Considering that there is no medical I2I model constructed from a geometric view of simultaneously preserving local manifold-value and global manifold structure, we propose an I2I model based on manifold-value correction and manifold matching (MMNet) to translate one modal image to another in a paired and unpaired fashion and preserve the texture details of the target model image. For local manifold-value preservation, each manifold-value of the generated image is aligned with the corresponding real image as much as possible by jointly optimizing the distribution corrector and the distribution generator. For global manifold structure preservation, three distance metrics are defined to globally reduce the difference between the manifold of the generated images and the manifold of the real images through optimizing the manifold matching loss. Experimental results demonstrate that the proposed MMNet outperforms multiple state-of-the-art GANs-based methods for MR image translation in both qualitative and quantitative measures.
收起