Elizabeth K. Cole

PURPOSE: Deep learning has had success with MRI reconstruction, but previously published works use real-valued networks. The few works which have tried complex-valued networks have not fully assessed their impact on phase. Therefore, the purpose of this work is to fully investigate end-to-end complex-valued convolutional neural networks (CNNs) for accelerated MRI reconstruction and in several phase-based applications in comparison to 2-channel real-valued networks. METHODS: Several complex-valued activation functions for MRI reconstruction were implemented, and their performance was compared. Complex-valued convolution was implemented and tested on an unrolled network architecture and a U-Net-based architecture over a wide range of network widths and depths with knee, body, and phase-contrast datasets. RESULTS: Quantitative and qualitative results demonstrated that complex-valued CNNs with complex-valued convolutions provided superior reconstructions compared to real-valued convolutions with the same number of trainable parameters for both an unrolled network architecture and a U-Net-based architecture, and for 3 different datasets. Complex-valued CNNs consistently had superior normalized RMS error, structural similarity index, and peak SNR compared to real-valued CNNs. CONCLUSION: Complex-valued CNNs can enable superior accelerated MRI reconstruction and phase-based applications such as fat-water separation, and flow quantification compared to real-valued convolutional neural networks.

Artificial intelligence algorithms based on principles of deep learning (DL) have made a large impact on the acquisition, reconstruction, and interpretation of MRI data. Despite the large number of retrospective studies using DL, there are fewer applications of DL in the clinic on a routine basis. To address this large translational gap, we review the recent publications to determine three major use cases that DL can have in MRI, namely, that of model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. For each of these three areas, we provide a framework for important considerations that consist of appropriate model training paradigms, evaluation of model robustness, downstream clinical utility, opportunities for future advances, as well recommendations for best current practices. We draw inspiration for this framework from advances in computer vision in natural imaging as well as additional healthcare fields. We further emphasize the need for reproducibility of research studies through the sharing of datasets and software. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2.

Deep learning-based image reconstruction methods have achieved promising results across multiple MRI applications. However, most approaches require large-scale fully-sampled ground truth data for supervised training. Acquiring fully-sampled data is often either difficult or impossible, particularly for dynamic contrast enhancement (DCE), 3D cardiac cine, and 4D flow. We present a deep learning framework for MRI reconstruction without any fully-sampled data using generative adversarial networks. We test the proposed method in two scenarios: retrospectively undersampled fast spin echo knee exams and prospectively undersampled abdominal DCE. The method recovers more anatomical structure compared to conventional methods.

Most deep learning (DL) magnetic resonance imaging (MRI) reconstruction approaches rely on supervised training algorithms, which require access to high-quality, fully-sampled ground truth datasets. In MRI, acquiring fully-sampled data is time-consuming, expensive, and, in some cases, impossible due to limitations on data acquisition speed. We present a DL framework for MRI reconstruction that does not require any fully-sampled data using unsupervised generative adversarial networks. We test our proposed method on 2D knee MRI data and 2D+time abdominal dynamic contrast enhanced (DCE) MRI data. In the DCE-MRI dataset, as is the case with many dynamic MRI sequences, ground truth was not possible to acquire and therefore, supervised DL reconstruction was not feasible. We show that our unsupervised method produces reconstructions which are better than compressed sensing in terms of image metrics and the recovery of anatomical structure, with faster inference time. In contrast to most deep learning reconstruction techniques, which are supervised, this method does not need any fully-sampled data. With the proposed method, accelerated imaging and accurate reconstruction can be performed in applications in cases where fully-sampled datasets are difficult to obtain or unavailable.