24-010521 SOW- final.docx

STATEMENT OF WORK(SOW)

SERVICES

GENERAL INFORMATIONTitle of Project:

Development of a Neural Network for Prediction of Macromolecular Composition in Hyperspectral Imaging Data Sets Statement of Need and Purpose:

The purpose of this acquisition is to purchase service of Development of a Neural Network for Prediction of Macromolecular Composition in Hyperspectral Imaging Data Sets

Background Information and Objective:

The MRI Section of the National Institute on Aging (NIA) Intramural Research Program (IRP) in studies of tissue response to aging and age-related pathology. Although the Section’s main current interest is applications within the central nervous system, the methodology developed is more wide-ranging and has potential utility across a broad range of problems in biomedical tissue characterization. The MRI Section has a strong interest in extending the Section’s methodology to other areas. In particular, the lab’s now propose to build on our published work on neural network analysis of biomedical signals to address the difficult problem of macromolecular quantification in near-infrared (NIR) hyperspectral imaging of cartilage and other tissues. NIR experiments are central to minimally invasive assessment of cartilage and other tissues at the molecular level and have been investigated by several groups in recent years. However, unique expertise is required to obtain hyperspectral images that span both the NIR and mid-infrared (MIR) region. The ability to obtain this data from individual pixels at high resolution in one scan enables the NIR hyperspectral data to serve as input to a neural network where the MIR data, arising from a gold-standard approach for obtaining macromolecular composition information, can serve as the outcome data.

The considerations above lead to a very natural formulation of a neural-network approach using hyperspectral images of cartilage that span both the NIR and MIR ranges. Using a wide-bandwidth spectrometer, NIR and MIR spectra will be jointly acquired at high pixel resolution (micron-level). The latter can then be quantified for component sizes of collagen and proteoglycan (PG). This will be performed in an imaging modality, where, in effect, each pixel will serve as a training sample of paired data of the form (NIR spectra; [collagen] and [PG]). After training, the NN can be applied to quantification of the NIR-only spectra obtained from animal studies, human subjects and patients; The NN can also serve as a template for similar approaches in other tissues. Application to newly acquired human data is outside of the scope of the present proposal but serves as the motivation and goal.

Period of Performance:

Base Period – 9/15/2024 – 6/30/2025

SCOPE OF WORKGeneral Requirements:

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:

Specific Requirements:

1) Develop a masking scheme based on a Euclidean distance metric or otherwise to define distance from a fiducial cartilage spectrum in order to segment and mask non-cartilage pixels in NIR and MIR imaging spectroscopy. Perform subsequent analyses only on the cartilage-like pixels.

2) Develop a neural network architecture for relating input NIR spectra to collagen and PG concentrations as defined by MIR.

3) Perform hyperparameter optimization for the constructed neural network to ensure quantification accuracy.

4) Test the NN on a testing set of NIR and MIR spectra with associated MIR quantification

LEVEL OF EFFORT:

(1) NIA estimates the level of effort for this requirement shall be 20 hours per week for one graduate student.

GOVERNMENT RESPONSIBILITIES

The government shall provide suitable background from the MRI Section’s previous work and expertise in neural network development and machine learning.

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 National Institute on Aging (NIA) researchers can reproduce the 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 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 including updates on the code, algorithms, and methods produced at each of the stages described above.

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 CONSIDERATIONSKey Personnel:

NIA requires the contractor to provide key personnel that have a background in both NIR and MIR spectroscopy, and background in machine learning.

Data Rights:

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.”

Publications and Publicity:

NA

Confidentiality of Information:

Data generated are from in vitro studies and no confidential data is involved.

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