Systems and methods for rapidly determining one or more metabolite measurements from MR spectroscopy data

1. A method for determining a concentration of one or more metabolites within a region of interest comprising:

processing magnetic resonance (MR) spectroscopy data of a region of interest, the magnetic resonance spectroscopy data including a plurality of spectra of one or more metabolites, through a series of neural networks, the processing including:

determining baseline components of each spectrum using a first neural network of the series, the baseline components defining a baseline model;

generating baseline-corrected components for each spectrum using the baseline components; and

determining one or more peak components of each spectrum using a second neural network of the series and the baseline-corrected components; and

determining one or more metabolite measurements of the one or more metabolites in the region of interest using the one or more peak components.

2. The method of claim 1 , further comprising:

determining one or more spectral features of each peak region using the one or more peak components;

wherein the one or more metabolite measurements are determined using the one or more spectral features.

3. The method of claim 2 , wherein the one or more metabolite measurements includes a quantification of concentration of the one more metabolites, a concentration ratio between at least two metabolites, a chemical exchange rate between at least two metabolites, among others, or a combination thereof.

4. The method of claim 1 , wherein:

the region of interest is a portion of a brain; and

the one or more metabolites includes choline (Cho) and N-acetylaspartate (NAA); and

the one or more metabolite measurements includes a Cho/NAA ratio.

5. The method of claim 1 , wherein:

the first neural network includes a trained encoder and a decoder;

the trained encoder determines a plurality of baseline parameters; and

the decoder defined by wavelet reconstruction equations determines the baseline components for each spectrum using the baseline parameters.

6. The method of claim 5 , wherein:

the second neural network includes a trained encoder and a decoder; and

the trained encoder determines a plurality of peak parameters; and

the decoder defined by a Lorentzian-Gaussian lineshape model determines the peak components for each spectrum using the plurality of peak parameters.

7. The method of claim 6 , wherein the one or more peak parameters includes one or more spectral features for each metabolite, zero-order phase, first-order phase, gaussian decay constant and Lorentzian decay constant.

8. The method of claim 1 , further comprising:

generating one or more maps of the region of interest using the one or more metabolites and/or one or more metabolite measurements and corresponding anatomical MR data.

9. The method of claim 8 , further comprising:

registering the one or more metabolites and/or the one or more metabolite measurements with the corresponding anatomical MR data.

10. The method of claim 1 , wherein:

the MR spectroscopy data is processed and provided in a first matrix, the matrix including a plurality of datapoints for each spectrum; the plurality of datapoints representing an entire model for each spectrum;

the determining the baseline components includes generating a second matrix, the second matrix including the baseline components for each spectrum;

the determining the baseline-corrected components includes generating a third matrix, the third matrix including the baseline corrected datapoints for each spectrum; and

the determining the one or more peak components includes generating a fourth matrix, the fourth matrix including the one or more peak components for each spectrum.

11. A system for determining a concentration of one or more metabolites within a region of interest comprising:

one or more processors; and

one or more hardware storage devices having stored thereon computer-executable instructions which are executable by the one or more processors to cause the computing system to perform at least the following:

processing magnetic resonance (MR) spectroscopy data of a region of interest, the magnetic resonance spectroscopy data including a plurality of spectra of one or more metabolites, through a series of neural networks, the processing including:

determining baseline components of each spectrum using a first neural network of the series, the baseline components defining a baseline model;

generating baseline-corrected components for each spectrum using the baseline components; and

determining one or more peak components of each spectrum using a second neural network of the series and the baseline-corrected components; and

determining one or more metabolite measurements of the one or more metabolites in the region of interest using the one or more peak components.

12. The system of claim 11 , wherein the one or more processors are further configured to cause the computing system to perform at least the following:

determining one or more spectral features of each peak region using the one or more peak components;

wherein the one or more metabolite measurements are determined using the one or more spectral features.

13. The system of claim 12 , wherein the one or more metabolite measurements includes a quantification of concentration of the one more metabolites, a concentration ratio between at least two metabolites, a chemical exchange rate between at least two metabolites, among others, or a combination thereof.

14. The system of claim 11 , wherein:

the region of interest is a portion of a brain; and

the one or more metabolites includes choline (Cho) and N-acetylaspartate (NAA); and

the one or more metabolite measurements includes a Cho/NAA ratio.

15. The system of claim 11 , wherein:

the first neural network includes a trained encoder and a decoder;

the trained encoder determines a plurality of baseline parameters; and

the decoder defined by wavelet reconstruction equations determines the baseline components for each spectrum using the baseline parameters.

16. The system of claim 15 , wherein:

the second neural network includes a trained encoder and a decoder; and

the trained encoder determines a plurality of peak parameters; and

the decoder defined by a Lorentzian-Gaussian lineshape model determines the peak components for each spectrum using the plurality of peak parameters.

17. The system of claim 16 , wherein the one or more peak parameters includes one or more spectral features for each metabolite, zero-order phase, first-order phase, gaussian decay constant and Lorentzian decay constant.

18. The system of claim 11 , wherein the one or more processors are further configured to cause the computing system to perform at least the following:

generating one or more maps of the region of interest using the one or more metabolites and/or one or more metabolite measurements and corresponding anatomical MR data.

19. The system of claim 18 , wherein the one or more processors are further configured to cause the computing system to perform at least the following:

registering the one or more metabolites and/or the one or more metabolite measurements with the corresponding anatomical MR data.

20. The system of claim 11 , wherein:

the MR spectroscopy data is processed and provided in a first matrix, the matrix including a plurality of datapoints for each spectrum; the plurality of datapoints representing an entire model for each spectrum;

the determining the baseline components includes generating a second matrix, the second matrix including the baseline components for each spectrum;

the determining the baseline-corrected components includes generating a third matrix, the third matrix including the baseline-corrected datapoints for each spectrum; and

the determining the one or more peak components includes generating a fourth matrix, the fourth matrix including the one or more peak components for each spectrum.