Improving style transfer in dynamic contrast enhanced MRI using a spatio-temporal approach
This work solves a domain-specific problem in medical imaging for MRI analysis, with incremental improvements over existing methods.
The paper tackles the challenge of style transfer in dynamic contrast enhanced MRI by addressing variations in contrast enhancements and motion, proposing a method that combines autoencoders, convolutional LSTMs, and adaptive convolutions, and shows it outperforms state-of-the-art methods on two datasets.
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.