Gadolinium dose reduction for brain MRI using conditional deep learning

TL;DR

This paper introduces a deep learning method that predicts contrast enhancement signals from low-dose MRI subtraction images, enabling reduced gadolinium doses while maintaining diagnostic quality across diverse datasets.

Contribution

The work presents a novel deep learning approach that isolates contrast signals from low-dose images and incorporates physical parameters for improved contrast prediction.

Findings

Effective contrast enhancement prediction across multiple datasets

Ability to synthesize images beyond standard gadolinium doses

Robust performance on various scanners and contrast agents

Abstract

Recently, deep learning (DL)-based methods have been proposed for the computational reduction of gadolinium-based contrast agents (GBCAs) to mitigate adverse side effects while preserving diagnostic value. Currently, the two main challenges for these approaches are the accurate prediction of contrast enhancement and the synthesis of realistic images. In this work, we address both challenges by utilizing the contrast signal encoded in the subtraction images of pre-contrast and post-contrast image pairs. To avoid the synthesis of any noise or artifacts and solely focus on contrast signal extraction and enhancement from low-dose subtraction images, we train our DL model using noise-free standard-dose subtraction images as targets. As a result, our model predicts the contrast enhancement signal only; thereby enabling synthesization of images beyond the standard dose. Furthermore, we adapt the embedding idea of recent diffusion-based models to condition our model on physical parameters affecting the contrast enhancement behavior. We demonstrate the effectiveness of our approach on synthetic and real datasets using various scanners, field strengths, and contrast agents.