Accelerated MRI using intelligent protocolling and subject-specific denoising applied to Alzheimer's disease imaging.

Magnetic Resonance Imaging (MR Imaging) is routinely employed in diagnosing Alzheimer's Disease (AD), which accounts for up to 60-80% of dementia cases. However, it is time-consuming, and protocol optimization to accelerate MR Imaging requires local expertise since each pulse sequence involves multiple configurable parameters that need optimization for contrast, acquisition time, and signal-to-noise ratio (SNR). The lack of this expertise contributes to the highly inefficient utilization of MRI services diminishing their clinical value. In this work, we extend our previous effort and demonstrate accelerated MRI via intelligent protocolling of the modified brain screen protocol, referred to as the Gold Standard (GS) protocol. We leverage deep learning-based contrast-specific image-denoising to improve the image quality of data acquired using the accelerated protocol. Since the SNR of MR acquisitions depends on the volume of the object being imaged, we demonstrate subject-specific (SS) image-denoising. The accelerated protocol resulted in a 1.94 × gain in imaging throughput. This translated to a 72.51% increase in MR Value-defined in this work as the ratio of the sum of median object-masked local SNR values across all contrasts to the protocol's acquisition duration. We also computed PSNR, local SNR, MS-SSIM, and variance of the Laplacian values for image quality evaluation on 25 retrospective datasets. The minimum/maximum PSNR gains (measured in dB) were 1.18/11.68 and 1.04/13.15, from the baseline and SS image-denoising models, respectively. MS-SSIM gains were: 0.003/0.065 and 0.01/0.066; variance of the Laplacian (lower is better): 0.104/-0.135 and 0.13/-0.143. The GS protocol constitutes 44.44% of the comprehensive AD imaging protocol defined by the European Prevention of Alzheimer's Disease project. Therefore, we also demonstrate the potential for AD-imaging via automated volumetry of relevant brain anatomies. We performed statistical analysis on these volumetric measurements of the hippocampus and amygdala from the GS and accelerated protocols, and found that 27 locations were in excellent agreement. In conclusion, accelerated brain imaging with the potential for AD imaging was demonstrated, and image quality was recovered post-acquisition using DL-based image denoising models.

Developing and deploying deep learning models in brain magnetic resonance imaging: A review.

Magnetic resonance imaging (MRI) of the brain has benefited from deep learning (DL) to alleviate the burden on radiologists and MR technologists, and improve throughput. The easy accessibility of DL tools has resulted in a rapid increase of DL models and subsequent peer-reviewed publications. However, the rate of deployment in clinical settings is low. Therefore, this review attempts to bring together the ideas from data collection to deployment in the clinic, building on the guidelines and principles that accreditation agencies have espoused. We introduce the need for and the role of DL to deliver accessible MRI. This is followed by a brief review of DL examples in the context of neuropathologies. Based on these studies and others, we collate the prerequisites to develop and deploy DL models for brain MRI. We then delve into the guiding principles to develop good machine learning practices in the context of neuroimaging, with a focus on explainability. A checklist based on the United States Food and Drug Administration's good machine learning practices is provided as a summary of these guidelines. Finally, we review the current challenges and future opportunities in DL for brain MRI.

Open-source magnetic resonance imaging acquisition: Data and documentation for two validated pulse sequences.

Raw data, simulated and acquired phantom images, and quantitative longitudinal and transverse relaxation times (T1/T2) maps from two open-source Magnetic Resonance Imaging (MRI) pulse sequences are presented in this dataset along with corresponding ".seq" files, sequence implementation scripts, and reconstruction/analysis scripts [1]. Real MRI data were collected from a 3T Siemens Prisma Fit and a 1.5T Siemens Aera via the Pulseq open-source MR sequence platform, and corresponding in silico data were generated using the simulation module of Virtual Scanner [2]. This dataset and its associated code can be used to validate the pipeline for using the same pulse sequences at other research sites using Pulseq, to provide guidelines for documenting and sharing open-source pulse sequences in general, and to demonstrate practical, customizable acquisition scripts using the PyPulseq library.

ArtifactID: Identifying artifacts in low-field MRI of the brain using deep learning.

Low-field MR scanners are more accessible in resource-constrained settings where skilled personnel are scarce. Images acquired in such scenarios are prone to artifacts such as wrap-around and Gibbs ringing. Such artifacts negatively affect the diagnostic quality and may be confused with pathology or reduce the region of interest visibility. As a first step solution, ArtifactID identifies wrap-around and Gibbs ringing in low-field brain MRI. We utilized two datasets: 179 T1-weighted pathological brain images from a 0.36 T scanner and 581 publicly available T1-weighted brain images. Individual binary classification models were trained to identify through-plane wrap-around, in-plane wrap-around, and Gibbs ringing. Visual explanations obtained via the GradCAM method helped develop trust in the wrap-around model. The mean precision and recall metrics across the four implemented models were 97.6% and 92.83% respectively. Agreement analysis of the models and the radiologists' labels returned Cohen's kappa values of 0.768 ± 0.062, 1.00 ± 0.000, 0.89 ± 0.085, and 0.878 ± 0.103 for the through-plane wrap-around, in-plane wrap-around, and Gibbs ringing models, respectively.

A framework for validating open-source pulse sequences.

Open-source pulse sequence programs offer an accessible and transparent approach to sequence development and deployment. However, a common framework for testing, documenting, and sharing open-source sequences is still needed to ensure sequence usability and repeatability. We propose and demonstrate such a framework by implementing two sequences, Inversion Recovery Spin Echo (IRSE) and Turbo Spin Echo (TSE), with PyPulseq, and testing them on a commercial 3 T scanner. We used the ACR and ISMRM/NIST phantoms for qualitative imaging and T1/T2 mapping, respectively. The qualitative sequences show good agreement with vendor-provided counterparts (mean Structural Similarity Index Measure (SSIM) = 0.810 for IRSE and 0.826 for TSE). Both sequences passed five out of the seven standard ACR tests, performing at similar levels to vendor counterparts. Compared to reference values, the coefficient of determination R2 was 0.9946 for IRSE T1 mapping and 0.9331 for TSE T2 mapping. All sequences passed the scanner safety check for a 70 kg, 175 cm subject. The framework was demonstrated by packaging the sequences and sharing them on GitHub with data and documentation on the file generation, acquisition, reconstruction, and post-processing steps. The same sequences were tested at a second site using a 1.5 T scanner with the information shared. PDF templates for both sequence developers and users were created and filled.

Autonomous magnetic resonance imaging.

Access to Magnetic Resonance Imaging (MRI) across developing countries ranges from being prohibitive to scarcely available. For example, eleven countries in Africa have no scanners. One critical limitation is the absence of skilled manpower required for MRI usage. Some of these challenges can be mitigated using autonomous MRI (AMRI) operation. In this work, we demonstrate AMRI to simplify MRI workflow by separating the required intelligence and user interaction from the acquisition hardware. AMRI consists of three components: user node, cloud and scanner. The user node voice interacts with the user and presents the image reconstructions at the end of the AMRI exam. The cloud generates pulse sequences and performs image reconstructions while the scanner acquires the raw data. An AMRI exam is a custom brain screen protocol comprising of one T1-, T2- and T2*-weighted exams. A neural network is trained to incorporate Intelligent Slice Planning (ISP) at the start of the AMRI exam. A Look Up Table was designed to perform intelligent protocolling by optimizing for contrast value while satisfying signal to noise ratio and acquisition time constraints. Data were acquired from four healthy volunteers for three experiments with different acquisition time constraints to demonstrate standard and self-administered AMRI. The source code is available online. AMRI achieved an average SNR of 22.86 ± 0.89 dB across all experiments with similar contrast. Experiment #3 (33.66% shorter table time than experiment #1) yielded a SNR of 21.84 ± 6.36 dB compared to 23.48 ± 7.95 dB for experiment #1. AMRI can potentially enable multiple scenarios to facilitate rapid prototyping and research and streamline radiological workflow. We believe we have demonstrated the first Autonomous MRI of the brain.

Pulseq-Graphical Programming Interface: Open source visual environment for prototyping pulse sequences and integrated magnetic resonance imaging algorithm development.

PURPOSE: To provide a single open-source platform for comprehensive MR algorithm development inclusive of simulations, pulse sequence design and deployment, reconstruction, and image analysis. METHODS: We integrated the "Pulseq" platform for vendor-independent pulse programming with Graphical Programming Interface (GPI), a scientific development environment based on Python. Our integrated platform, Pulseq-GPI, permits sequences to be defined visually and exported to the Pulseq file format for execution on an MR scanner. For comparison, Pulseq files using either MATLAB only ("MATLAB-Pulseq") or Python only ("Python-Pulseq") were generated. We demonstrated three fundamental sequences on a 1.5 T scanner. Execution times of the three variants of implementation were compared on two operating systems. RESULTS: In vitro phantom images indicate equivalence with the vendor supplied implementations and MATLAB-Pulseq. The examples demonstrated in this work illustrate the unifying capability of Pulseq-GPI. The execution times of all the three implementations were fast (a few seconds). The software is capable of user-interface based development and/or command line programming. CONCLUSION: The tool demonstrated here, Pulseq-GPI, integrates the open-source simulation, reconstruction and analysis capabilities of GPI Lab with the pulse sequence design and deployment features of Pulseq. Current and future work includes providing an ISMRMRD interface and incorporating Specific Absorption Ratio and Peripheral Nerve Stimulation computations.