D-Attachment SOW Development of harmonic analysis and machine learning.pdf

Version 11-30-2016-1 FAR Part 11—Describing Agency Needs

STATEMENT OF WORK (SERVICES)

(SOW)

GENERAL INFORMATION

Development of harmonic analysis and machine learning-based approaches for magnetic resonance parameter estimation and for data fusion in MRI

The MRI Section of the NIA/IRP (National Institute on Aging/Intramural Research Program) specializes in studies of tissue response to aging, and age-related pathology.

As part of our program in brain mapping in particular, NIA has a need to work with emerging methods in harmonic analysis, machine learning, and data fusion. These will become central elements in our work on non-invasive diagnosis of brain tissue pathology and understanding microstructural changes that occur with aging.

One of the major open questions in aging research is how the brain and brain stem change with age, and what differentiates between healthy and non-healthy aging. This incorporates the development of age-related pathology and disease, including Alzheimer’s disease. The MRI Section has made major advances over the past several years using data stabilization methods. However, new, even more specialized approaches are being developed in the applied mathematics area for signal analysis.

These highly mathematical methods are in the realm of novel neural network architectures and implementations and what may be called “data un-compression”, along with data fusion. We wish to apply these emerging methods to our brain MRI work at the NIA IRP after testing on simulated data.

Base Period – 8/15/2023 – 12/31/2023 Option Period 1 – 1/1/2024 – 8/15/2024 Option Period 2 – 8/16/2024 – 12/31/2024 Option Period 3 – 1/1/2025 – 8/15/2025

SCOPE OF WORK

Independently and not as an agent of the Government, the Contractor shall furnish all the necessary services, qualified personnel, material, equipment, and facilities, not otherwise provided by the Government as needed to perform the Statement of Work below:

1) Develop mathematical models of how neural network architecture and hyperparameter settings contribute to the efficiency of input-layer-regularized neural networks.

Title of Project:

Statement of Need and Purpose:

Background Information and Objective:

Period of Performance:

General Requirements:

Specific Requirements:

2) Based on (1), develop self-regularizing networks for parameter estimation in MR relaxometry and MRI data fusion.

3) Construct graph-matching schemes for heterogeneous data fusion in Magnetic

Resonance Imaging and other NMR applications, taking advantage of Laplacian embeddings as efficient feature extractors.

4) Apply the machine learning methods developed in (1-3) to simulated MR relaxometry and imaging data based on input parameters from published brain, muscle and cartilage studies to compare the accuracy and precision of these methods with the state of the art.

LEVEL OF EFFORT:

(2) graduate students, 100% effort, 4 months/8 months

GOVERNMENT RESPONSIBILITIES

The government shall provide simulated MR relaxometry and MRI data for analysis using the machine learning methods developed by the contractor. The project officer will evaluate code produced by the contractor and provide feedback at each of the four stages described above.

DELIVERY OR DELIVERABLES

The contractor shall deliver code (e.g. Python and MATLAB scripts) generated in steps

(1) through (4) above.

The contractor shall provide detailed instructions on using this code so that the National Institute on Aging (NIA) researchers can reproduce their work and apply the analytical techniques developed to new data. These instructions will include both annotations within the code and separate documents providing step-by-step instructions.

The contractor shall provide the results of applying the analytical techniques developed to the simulated MR relaxometry and MRI data provided by the Government.

The timely submission of deliverables is essential to successfully completing this requirement. Deliverables are to be submitted in electronic copy.

REPORTING REQUIREMENTS

The contractor is required to provide status updates during the period of performance.

This shall cover all work completed during the specified period and shall present the work to be accomplished during the subsequent period. The status updates shall also identify any problems that arose and a statement explaining how the problem was resolved. The status updates shall also identify any problems that have arisen but have not been completely resolved and provide an explanation. No formal written report is required.

OTHER CONSIDERATIONS

Mathematics graduate students with experience in advanced machine learning and their application to image processing problems.

The National Institute on Aging shall have unlimited rights under this contract including in reports, recommendations, briefings, work plans and all other deliverables in accordance with FAR 52.227-14 Rights in Data-General ALT IV. This includes the deliverables provided under the basic contract and any optional task deliverables exercised by the contracting officer. In addition, it includes any additional deliverables required by contract change. The definition of “unlimited rights” is contained in Federal Acquisition Regulation (FAR) 27.401, “Definitions.”

In collaboration with NIA investigators, the contractor may write and publish articles of data produced as a result of the requirements of the SOW.

This is not applicable because only simulated data will be analyzed in this project.

Key Personnel:

Data Rights:

Publications and Publicity:

Confidentiality of Information: