SOLICITATION NOTICE
R -- Interactive Segmentation System with Consumer-Level Graphics Processing Unit
- Notice Date
- 8/7/2008
- Notice Type
- Presolicitation
- NAICS
- 611310
— Colleges, Universities, and Professional Schools
- Contracting Office
- Department of Health and Human Services, National Institutes of Health, National Library of Medicine, 8600 Rockville Pike, Bethesda, Maryland, 20894
- ZIP Code
- 20894
- Solicitation Number
- 08-175-CYC
- Archive Date
- 9/6/2008
- Point of Contact
- Cara Y Calimano,, Phone: 301 496-6127
- E-Mail Address
-
CalimaC@mail.nlm.nih.gov
- Small Business Set-Aside
- N/A
- Description
- This is a synopsis being conducted under Simplified Acquisition Procedures in accordance with FAR Part 13. This solicitation document incorporates provisions and clauses that are in effect through the June 2008 Federal Acquisition Regulation revision, which includes the consolidation of all Federal Acquisition Circulars through 2005-26. This acquisition is NOT a small business set-aside and the NAICS code is 611310. It is the intent of the National Library of Medicine (NLM) to procure professional services from Dr. Sari-Sarraf with Texas Tech University on a sole source basis. Professional services are required over a 12-month period to develop algorithms and create open source implementations of these algorithms for creation of an interactive segmentation system for the efficient, computer-assisted segmentation of biomedical images, using image processing support from a consumer-grade Graphics Processing Unit (GPU) and commercial workstation-level computing platform. This system will support image indexing work for Content-Based Image Retrieval (CBIR) projects at the National Library of Medicine (NLM). Proposed Work: The specific work required is as follows: (1) conduct research and development into the implementation of image indexing algorithms on consumer-level graphics processing units (GPUs) by building on previous NLM algorithm development in this area; (2) create an interactive texture segmentation tool, generalizing concepts implemented in Mortensen’s intelligent scissors approach, which uses image processing functions that have been implemented on a GPU. In more detail: (1) Conduct research and development into the implementation of image indexing algorithms on consumer-level graphics processing units (GPUs). The contractor shall study the architecture and design of the nVidia video card, which hosts a 768 MB GeForce 8800 GTX GPU, and shall report on latest technological reports from the technical literature in the use of the card for medical or general image processing, and in the use of software development and implementation tools for use with the video card; the contractor shall implement an up-to-date development environment on a workstation that hosts the card; (2) Implement an interactive segmentation system which exploits use of the GPU for segmentation speed, multiple simultaneous segmentation with varying input parameters, or other enhancements recommended by the contractor, and negotiated with the government, that have the potential to significantly enhance user segmentation throughput and/or quality. A goal of the system is to allow the rapid and accurate segmentation of significant objects in a biomedical image by a technician who has been trained in the likely visual characteristics of the objects to be segmented.The system shall be evaluated on region segmentation in images provided by NLM, including color uterine cervix images. Initial approaches that should be studied include Mortensen’s intelligent scissors concepts and active contour modeling. The techniques may be specially “tuned” to the uterine cervix images by parameter settings, but should also be fully functional on general images, independent of factors such as image size, color, grayscale, or modality of acquisition, as long as the required texture characteristics are present in the images. This system will be evaluated on a test set of images supplied by NLM. The test set will include color uterine cervix images; the contractor will use the segmentation system to interactively segment regions on these images and evaluate these segmentations against those marked by experts. The tissue types/anatomy/visual phenomena segmented may include any or all of the following: cervix region, os, cysts, squamous epithelium, columnar epithelium, squamous metaplasia, blood, mucous, invasive cancer. (3) For image processing functions, which are implemented on the GPU to support the interactive segmentation, provide a callable interface so that the functions are usable outside of the segmentation system. A list of example image processing functions which are of interest to the government for GPU implementation is given below. The actual image processing functions implemented on the GPU will be determined by the contractor, in cooperation with the government, in the course of the R&D for the interactive segmentation system. Example functions: Gabor filters, Gray-level coocurrence matrices, Hu moments, Color space transforms: RGB/Lab, RGB/Luv, RGB/HSV, Graylevel and color histogram computation, Discrete Wavelet Transform, Gradient images and other quantities useful for image pre-processing for Intelligent Scissors interactive segmentation, Generalized Hough Transform, Mathematical morphology operations (opening, closing, erosion, dilation, watershed), Graylevel and color histogram computation. REQUIRED TASKS: The work described in the Proposed Work section shall be completed. Below, that work is divided into two required subtasks and presented in summary form. Software for GPU image processing shall be coded in C++/C, consistently with the requirements of the GPU development system. The segmentation system, and all user interfaces shall be coded in MATLAB, except as negotiated with the government. All software delivered shall include source code and documentation. Task description: Subtask 1: Provide updated analysis of feasibility of image processing on consumer level graphics processor units (GPUs), including report on state-of-the-art achievements from the technical literature for general image processing and medical image processing. Develop design and initial implementation for an interactive segmentation system that exploits GPU processing. All parts of this subtask should be accomplished according to the requirements in the Proposed Work. Subtask 2: Provide final implementation of an interactive segmentation tool that exploits GPU processing for enhancements to user throughput, quality of segmentations, or other significant enhancements to the interactive segmentation process. Evaluate on images provided by NLM, which will include uterine cervix images with labeled regions which may be used as reference or “truth” segmentations. All parts of this subtask should be accomplished according to the requirements in the Proposed Work. For subtasks 1-2, the Contractor will use image data provided made available by the government. Notice of Government Unlimited Rights to Work First Produced Under This Contract: Government rights to work first produced under this contract are established by Federal law including, but not limited to, this specific reference: FAR 42.227-14, Rights in Data – General, (b) (1). Requirement to Notify Government of Proprietary Work Dependencies: All algorithms and code developed under this contract are U.S. government property and are for public use and benefit, including, but not limited to, internal use by government institutions, use by researchers or other parties collaborating in government work, and public domain release, at the option of the government. Offerors are required to notify the Government in writing of any dependencies of the deliverables under this contract on proprietary, copyrighted, or patented work that potentially inhibits, restricts, or requires permission for the dissemination of the deliverables to the public, other governmental agencies or research groups, or to any other parties whatsoever. Texas Tech University is uniquely qualified for this work because of the expertise and experience of the principal investigator below (Dr. Sari-Sarraf) in the specific areas of image segmentation and the use of Graphics Processing Units (GPUs) for image processing, specifically image segmentation, combined, with his extensive educational background and research experience in advanced image processing and numerous other technical publications, and the support of the facilities and staff of the Texas Tech Applied Vision Laboratory (AVL). Dr. Sari-Sarraf has been the principal investigator for all of the segmentation methods that are the focus of research and development for the proposed contract work. This notice of intent is not a request for competitive quotations however, all responses received, within 15 days from the date of publication of this synopsis will be considered by NLM. EMAILED OR FAXED PROPOSALS WILL NOT BE ACCEPTED. The quoter shall include all information which documents and/or supports the qualification criteria in one clearly marked section of its quotation. The contractor shall comply with all applicable Federal, State, and local laws, executive orders, rules and regulations applicable to its performance under this order. Full text of clauses and provisions are available at Federal Acquisition Regulation (FAR): http://www.arnet.gov/far/index.html. The following clauses and provisions apply to this acquisition and may be obtained from the web site: FAR 52.213-4, Terms and Conditions—Simplified Acquisitions (Other Than Commercial Items) (February 2008).
- Web Link
-
FedBizOpps Complete View
(https://www.fbo.gov/?s=opportunity&mode=form&id=9db746cd4608037898114e5f91026503&tab=core&_cview=1)
- Place of Performance
- Address: 6707 Democracy Blvd, Suite 105, Bethesda, Maryland, 20892, United States
- Zip Code: 20892
- Zip Code: 20892
- Record
- SN01633762-W 20080809/080807222410-9db746cd4608037898114e5f91026503 (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |