Improving style transfer in dynamic contrast enhanced MRI using a spatio-temporal approach

TL;DR

This paper introduces a novel spatio-temporal approach for style transfer in DCE-MRI that effectively handles contrast variations and motion, outperforming existing methods through a combination of autoencoders, convolutional LSTMs, and adaptive convolutions.

Contribution

The paper presents a new method integrating autoencoders, convolutional LSTMs, and adaptive convolutions for improved style transfer in dynamic contrast-enhanced MRI.

Findings

Outperforms state-of-the-art methods on two datasets

Introduces a new metric considering contrast enhancement

Effectively models temporal and local contrast variations

Abstract

Style transfer in DCE-MRI is a challenging task due to large variations in contrast enhancements across different tissues and time. Current unsupervised methods fail due to the wide variety of contrast enhancement and motion between the images in the series. We propose a new method that combines autoencoders to disentangle content and style with convolutional LSTMs to model predicted latent spaces along time and adaptive convolutions to tackle the localised nature of contrast enhancement. To evaluate our method, we propose a new metric that takes into account the contrast enhancement. Qualitative and quantitative analyses show that the proposed method outperforms the state of the art on two different datasets.