Faithful Synthesis of Low-dose Contrast-enhanced Brain MRI Scans using Noise-preserving Conditional GANs

TL;DR

This paper introduces a conditional GAN model that synthesizes brain MRI images at various contrast agent doses, enabling dose reduction while maintaining diagnostic quality, and demonstrates its effectiveness on multiple datasets.

Contribution

The paper proposes a novel noise-preserving loss function for conditional GANs to accurately synthesize MRI images at fractional contrast doses, addressing a key challenge in dose reduction.

Findings

Conditional GANs effectively generate MRI images at different contrast doses.

The proposed model preserves noise characteristics crucial for diagnosis.

The approach can be transferred to other datasets lacking non-standard dose images.

Abstract

Today Gadolinium-based contrast agents (GBCA) are indispensable in Magnetic Resonance Imaging (MRI) for diagnosing various diseases. However, GBCAs are expensive and may accumulate in patients with potential side effects, thus dose-reduction is recommended. Still, it is unclear to which extent the GBCA dose can be reduced while preserving the diagnostic value -- especially in pathological regions. To address this issue, we collected brain MRI scans at numerous non-standard GBCA dosages and developed a conditional GAN model for synthesizing corresponding images at fractional dose levels. Along with the adversarial loss, we advocate a novel content loss function based on the Wasserstein distance of locally paired patch statistics for the faithful preservation of noise. Our numerical experiments show that conditional GANs are suitable for generating images at different GBCA dose levels and can be used to augment datasets for virtual contrast models. Moreover, our model can be transferred to openly available datasets such as BraTS, where non-standard GBCA dosage images do not exist.