Unified cross-modality feature disentangler for unsupervised multi-domain MRI abdomen organs segmentation

TL;DR

This paper introduces a unified cross-modality feature disentangling method that enables unsupervised multi-domain MRI abdomen organ segmentation using labeled CT data, achieving high accuracy comparable to supervised methods.

Contribution

A novel variational auto-encoder based approach for disentangling content and style in multi-modal images, facilitating unsupervised segmentation across MRI modalities.

Findings

Achieved lowest average multi-domain image reconstruction error of 1.34±0.04.

Attained Dice scores of 0.85 for T1w and 0.90 for T2w MRI in segmentation.

Performed comparably to fully supervised segmentation methods.

Abstract

Our contribution is a unified cross-modality feature disentagling approach for multi-domain image translation and multiple organ segmentation. Using CT as the labeled source domain, our approach learns to segment multi-modal (T1-weighted and T2-weighted) MRI having no labeled data. Our approach uses a variational auto-encoder (VAE) to disentangle the image content from style. The VAE constrains the style feature encoding to match a universal prior (Gaussian) that is assumed to span the styles of all the source and target modalities. The extracted image style is converted into a latent style scaling code, which modulates the generator to produce multi-modality images according to the target domain code from the image content features. Finally, we introduce a joint distribution matching discriminator that combines the translated images with task-relevant segmentation probability maps to further constrain and regularize image-to-image (I2I) translations. We performed extensive comparisons to multiple state-of-the-art I2I translation and segmentation methods. Our approach resulted in the lowest average multi-domain image reconstruction error of 1.34$\pm$0.04. Our approach produced an average Dice similarity coefficient (DSC) of 0.85 for T1w and 0.90 for T2w MRI for multi-organ segmentation, which was highly comparable to a fully supervised MRI multi-organ segmentation network (DSC of 0.86 for T1w and 0.90 for T2w MRI).