Cross-Domain Medical Image Translation by Shared Latent Gaussian Mixture Model
This addresses the challenge of poor generalization in medical image segmentation models between domains, particularly for preserving small structures like calcified plaques, though it appears incremental as an enhancement to existing translation methods.
The paper tackles the problem of preserving fine structures during cross-domain medical image translation, which is important for clinical applications like segmenting small calcified plaques. Their proposed patch-based model using shared latent variables from a Gaussian mixture model shows superior performance in preserving fine structures compared to state-of-the-art methods, as verified through detection and segmentation tasks.
Current deep learning based segmentation models often generalize poorly between domains due to insufficient training data. In real-world clinical applications, cross-domain image analysis tools are in high demand since medical images from different domains are often needed to achieve a precise diagnosis. An important example in radiology is generalizing from non-contrast CT to contrast enhanced CTs. Contrast enhanced CT scans at different phases are used to enhance certain pathologies or organs. Many existing cross-domain image-to-image translation models have been shown to improve cross-domain segmentation of large organs. However, such models lack the ability to preserve fine structures during the translation process, which is significant for many clinical applications, such as segmenting small calcified plaques in the aorta and pelvic arteries. In order to preserve fine structures during medical image translation, we propose a patch-based model using shared latent variables from a Gaussian mixture model. We compare our image translation framework to several state-of-the-art methods on cross-domain image translation and show our model does a better job preserving fine structures. The superior performance of our model is verified by performing two tasks with the translated images - detection and segmentation of aortic plaques and pancreas segmentation. We expect the utility of our framework will extend to other problems beyond segmentation due to the improved quality of the generated images and enhanced ability to preserve small structures.