Delineation of gliomas using radial metabolite indexing

A Visual Analytics Approach for Comparing Cohorts in Single-Voxel Magnetic Resonance Spectroscopy Data

Single-voxel proton magnetic resonance spectroscopy (¹H-MRS) is a non-invasive in-vivo technology to measure metabolic concentrations in selected regions of interest in a tissue, e.g., the brain. ¹H-MRS generates spectra of signals with different frequencies and specific intensities which can be assigned to respective metabolites in the investigated tissue and quantified. In studies designed to detect biomarkers of a specific disorder or dysfunction, the overall goal is not just to analyze a single ¹H-MRS data set, but to compare patient cohorts against healthy controls. We propose a visual analytics tool for the comparative analyses of cohorts, i.e., sets of data sets. Each data set can be regarded as a multivariate data sample, in which each variable represents the concentration of a metabolite. While a standard workflow for comparative analyses of two cohorts is routinely deployed by analyzing metabolites individually, our tool allows for comparative cohort analysis in a multivariate setting. Our top-down analysis strategy uses multidimensional data visualization methods combined with statistical plots and statistical analyses. We document and evaluate the effectiveness of our approach for the interactive analysis of metabolite concentrations in three brain regions for a comparative study of an alcohol-dependent patient cohort and a healthy control group.

(2 + 1)D-CAIPIRINHA accelerated MR spectroscopic imaging of the brain at 7T

Purpose

To compare a new parallel imaging (PI) method for multislice proton magnetic resonance spectroscopic imaging (¹H‐MRSI), termed (2 + 1)D‐CAIPIRINHA, with two standard PI methods: 2D‐GRAPPA and 2D‐CAIPIRINHA at 7 Tesla (T).

Methods

(2 + 1)D‐CAIPIRINHA is a combination of 2D‐CAIPIRINHA and slice‐CAIPIRINHA. Eight healthy volunteers were measured on a 7T MR scanner using a 32‐channel head coil. The best undersampling patterns were estimated for all three PI methods. The artifact powers, g‐factors, Cramér–Rao lower bounds (CRLB), and root mean square errors (RMSE) were compared quantitatively among the three PI methods. Metabolic maps and spectra were compared qualitatively.

Results

(2 + 1)D‐CAIPIRINHA allows acceleration in three spatial dimensions in contrast to 2D‐GRAPPA and 2D‐CAIPIRINHA. Thus, this sequence significantly decreased the RMSE of the metabolic maps by 12.1 and 6.9%, on average, for 4 < R < 11, compared with 2D‐GRAPPA and 2D‐CAIPIRINHA, respectively. The artifact power was 22.6 and 8.4% lower, and the CRLB were 3.4 and 0.6% lower, respectively.

Conclusion

(2 + 1)‐CAIPIRINHA can be implemented for multislice MRSI in the brain, enabling higher accelerations than possible with two‐dimensional (2D) parallel imaging methods. An eight‐fold acceleration was still feasible in vivo with negligible PI artifacts with lipid decontamination, thus decreasing the measurement time from 120 to 15 min for a 64 × 64 × 4 matrix. Magn Reson Med 78:429–440, 2017. © 2016 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine.