Prior-Guided Image Reconstruction for Accelerated Multi-Contrast MRI via Generative Adversarial Networks

Abstract

Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of information available for diagnosis. Yet, excessive scan times associated with additional contrasts may be a limiting factor. Two mainstream frameworks for enhanced scan efficiency are reconstruction of undersampled acquisitions and synthesis of missing acquisitions. Recently, deep learning methods have enabled significant performance improvements in both frameworks. Yet, reconstruction performance decreases towards higher acceleration factors with diminished sampling density at high-spatial-frequencies, whereas synthesis can manifest artefactual sensitivity or insensitivity to image features due to the absence of data samples from the target contrast. Here we propose a new approach for synergistic recovery of undersampled multi-contrast acquisitions based on conditional generative adversarial networks. The proposed method mitigates the limitations of pure learning-based reconstruction or synthesis by utilizing three priors: shared high-frequency prior available in the source contrast to preserve high-spatial-frequency details, low-frequency prior available in the undersampled target contrast to prevent feature leakage/loss, and perceptual prior to improve recovery of high-level features. Demonstrations on brain MRI datasets from healthy subjects and patients indicate the superior performance of the proposed method compared to pure reconstruction and synthesis methods. The proposed method can help improve the quality and scan efficiency of multi-contrast MRI exams.

Optimizing multicontrast MRI reconstruction with shareable feature aggregation and selection

“…Recently, research has shown that MC brain images from the same patient contain redundant information, which means that a previously scanned contrast can be used as prior knowledge to reconstruct the images of subsequent contrast scans, consequently further accelerating the MC‐MRI protocols 17–20 . Leveraging shareable information among MC images for fast MRI has been studied using compressed sensing (CS), 20–23 patch‐based operators 7 and dictionary learning 24 methods.…”

“…More recently, deep neural networks have been exploited for fast MC images synthesis 25–27 and reconstruction 28–37 . Rather than using fixed, handcrafted extractors, the networks learn the parameters of convolutional kernels for the shareable feature representations.…”

“…Rather than using fixed, handcrafted extractors, the networks learn the parameters of convolutional kernels for the shareable feature representations. For example, networks in 28–34 directly concatenate MC images of the original resolution in the input layer, followed by the convolutional layers for feature extraction. The features are extracted by the shallow layer, which represents the sharing structure of the original images.…”

Generative adversarial network for glioblastoma ensures morphologic variations and improves diagnostic model for isocitrate dehydrogenase mutant type

“…GAN learns data distribution from training samples and can generate realistic imaging data that are similar in distribution, but nevertheless differ from the original data; this may constitute an attractive solution of overfitting for small datasets 13 , 14 . GAN has been applied for reconstructing multi-contrast MR images 16 – 18 , reducing noise 19 , detecting 20 , 21 , and tumor grading 22 , but assessment of the morphologic characteristics of GAN-based synthetic data and their ability to classify molecular subtype in a diagnostic models have not been tested. If GAN-generated imaging data reflect the morphologic characteristics of glioblastomas with mutant IDH, while varying in morphologic distribution, then these GAN-generated data can be used for training on future deep learning tasks.…”

Improving Signal to Noise Ratio in Ultra High Field Magnetic Resonance Imaging

“…It is noteworthy that Mardani suggests the discriminator outputs can be used to focus on sensitive anatomies. Dar et al [100] also used perceptual priors in their multi-contrast reconstruction GAN. The above mentioned studies using GANs have demonstrated enhanced performance compared to state of the art compressed sensing and other parallel imaging reconstruction techniques.…”