Faculty Bibliography

Magnetic resonance imaging (MRI) is a leading image modality for the assessment of musculoskeletal (MSK) injuries and disorders. A significant drawback, however, is the lengthy data acquisition. This issue has motivated the development of methods to improve the speed of MRI. The field of artificial intelligence (AI) for accelerated MRI, although in its infancy, has seen tremendous progress over the past 3 years. Promising approaches include deep learning methods for reconstructing undersampled MRI data and generating high-resolution from low-resolution data. Preliminary studies show the promise of the variational network, a state-of-the-art technique, to generalize to many different anatomical regions and achieve comparable diagnostic accuracy as conventional methods. This article discusses the state-of-the-art methods, considerations for clinical applicability, followed by future perspectives for the field.

A publicly available dataset containing k-space data as well as Digital Imaging and Communications in Medicine image data of knee images for accelerated MR image reconstruction using machine learning is presented.

H MRI maps brain anatomy and pathology non-invasively through contrasts generated by exploiting inhomogeneities in tissue micro-environments. Inferring histopathological information from MRI findings, however, remains challenging due to the absence of direct links between MRI signals and specific tissue compartments. Here, we show that convolutional neural networks, developed using co-registered multi-contrast MRI and histological data of the mouse brain, can generate virtual histology from MRI results. Our networks provide maps that mirror histological stains for axons and myelin with enhanced specificity compared to existing MRI markers. Furthermore, by introducing random perturbations to the inputs, the relative contribution of each MRI contrast within the networks can be estimated and guide the optimization of MRI acquisition. We anticipate our method to be a starting point for translation of MRI results into easy-to-understand virtual histology for neurobiologists and provide resources for developing novel MRI contrasts

The slow acquisition speed of magnetic resonance imaging (MRI) has led to the development of two complementary methods: acquiring multiple views of the anatomy simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). While the combination of these methods has the potential to allow much faster scan times, reconstruction from such undersampled multi-coil data has remained an open problem. In this paper, we present a new approach to this problem that extends previously proposed variational methods by learning fully end-to-end. Our method obtains new state-of-the-art results on the fastMRI dataset for both brain and knee MRIs

Low-dose X-ray CT is a major research area with high clinical impact. Compressed sensing using view-based sparse sampling and sparsity-promoting regularization has shown promise in simulations, but these methods can be difficult to implement on diagnostic clinical CT scanners since the X-ray beam cannot be switched on and off rapidly enough. An alternative to view-based sparse sampling is interrupted-beam sparse sampling. SparseCT is a recently-proposed interrupted-beam scheme that achieves sparse sampling by blocking a portion of the beam using a multislit collimator. The use of a multislit collimator necessitates a number of modifications to the standard compressed sensing reconstruction pipeline. In particular, we find that SparseCT reconstruction is feasible within a model-based image reconstruction framework that incorporates data fidelity weighting to consider penumbra effects and source jittering to consider the effect of partial source obstruction. Here, we present these modifications and demonstrate their application in simulations and real-world prototype scans. In simulations compared to conventional low-dose acquisitions, SparseCT is able to achieve smaller normalized root-mean square differences than tube-current reduction at larger dose reduction levels. In prototype experiments, we successfully apply our reconstruction modifications and maintain image resolution at the quarter-dose reduction level. The SparseCT design requires only small hardware modifications to current diagnostic clinical scanners, opening up new possibilities for CT dose reduction.

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.

PURPOSE/OBJECTIVE:Although deep learning has shown great promise for MR image reconstruction, an open question regarding the success of this approach is the robustness in the case of deviations between training and test data. The goal of this study is to assess the influence of image contrast, SNR, and image content on the generalization of learned image reconstruction, and to demonstrate the potential for transfer learning. METHODS:Reconstructions were trained from undersampled data using data sets with varying SNR, sampling pattern, image contrast, and synthetic data generated from a public image database. The performance of the trained reconstructions was evaluated on 10 in vivo patient knee MRI acquisitions from 2 different pulse sequences that were not used during training. Transfer learning was evaluated by fine-tuning baseline trainings from synthetic data with a small subset of in vivo MR training data. RESULTS:Deviations in SNR between training and testing led to substantial decreases in reconstruction image quality, whereas image contrast was less relevant. Trainings from heterogeneous training data generalized well toward the test data with a range of acquisition parameters. Trainings from synthetic, non-MR image data showed residual aliasing artifacts, which could be removed by transfer learning-inspired fine-tuning. CONCLUSION/CONCLUSIONS:This study presents insights into the generalization ability of learned image reconstruction with respect to deviations in the acquisition settings between training and testing. It also provides an outlook for the potential of transfer learning to fine-tune trainings to a particular target application using only a small number of training cases.

Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive. We introduce the fastMRI dataset, a large-scale collection of both raw MR measurements and clinical MR images, that can be used for training and evaluation of machine-learning approaches to MR image reconstruction. By introducing standardized evaluation criteria and a freely-accessible dataset, our goal is to help the community make rapid advances in the state of the art for MR image reconstruction. We also provide a self-contained introduction to MRI for machine learning researchers with no medical imaging background