SOLICITATION NOTICE
70 -- Visual content analysis of biomedical images for clinical decision support
- Notice Date
- 8/30/2011
- 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, 6707 Democracy Blvd., Suite 105, Bethesda, Maryland, 20894, United States
- ZIP Code
- 20894
- Solicitation Number
- NLM-11-157-SVU
- Archive Date
- 9/14/2011
- Point of Contact
- Suet Vu, Phone: 301-496-6546
- E-Mail Address
-
vus@mail.nih.gov
(vus@mail.nih.gov)
- Small Business Set-Aside
- N/A
- Description
- This is synopsis prepared in accordance with the format under Simplified Acquisition Procedures at Federal Acquisition Regulation (FAR) Subpart 13. This solicitation document incorporates provisions and clauses that are in effect in the June 2010 Federal Acquisition Regulation (FAR) Revision, including all FAR Circulars issued as of the date of this synopsis. This acquisition is NOT a small business set-aside and the North American Industry Classification System (NAICS) code is 611310 - Colleges, Universities, and Professional Schools. It is the intent of the National Library of Medicine (NLM) to procure professional services from Dr. R. Joe Stanley with Missouri University on a sole source basis. Professional services are required over a 12-month period to carrying out all required research and development for selected topics in: (i) graphical biomedical figure content analysis; and, (ii) uterine cervical cancer histology image classification, toward improving the state of art in clinical decision support. Specifically, graphical figure content analysis shall improve existing graphical image classification that separates statistical figures (pie charts, bar charts, line charts) from diagrams (drawings, illustrations), and flowcharts to also separate statistical figure subtypes: pie charts, bar charts, and line charts. It is desirable to see significant increases in overall classification accuracy while maintaining robustness against variety of image types seen in the biomedical literature. Further, the offeror shall develop methods to extract content from bar charts (axes labels, tick mark values, bar values, and associate multiple bars with appropriate legend items). For histology classification task the offeror shall design, implement, and test an algorithm for classification of epithelium tissue of the uterine cervix as Normal, CIN1, CIN2, or CIN3, in digitized, histology images in which the epithelium tissue has been segmented. All software for task: (i) shall be developed in Java unless otherwise negotiated with the government. For task (ii), the development is preferred in Java or C/C++, however prototype development may be done in MATLAB®. The vendor shall perform the following activities in conducting an analysis of the workflows in acquisitions and cataloging in Technical Services and cataloging in History of Medicine: The contractor will: Part I: Biomedical Graphical Figure Content Analysis: (a) Improve existing graphical image classification performance to separate statistical figures (pie charts, bar charts, line charts) from diagrams (drawings, illustrations), and flowcharts; (b) Develop methods to separate pie charts, bar charts, and line charts; (c) Develop methods to extract content from bar charts (axes labels, tick mark values, bar values, and associate multiple bars with appropriate legend items). Specifically, graphical figure content analysis shall improve existing graphical image classification that separates statistical figures (pie charts, bar charts, line charts) from diagrams (drawings, illustrations), and flowcharts to also separate statistical figure subtypes: pie charts, bar charts, and line charts. It is desirable to see significant increases in overall classification accuracy while maintaining robustness against variety of image types seen in the biomedical literature. The government will provide an image data set or direct the offeror to suitable online image data repositories. Part II: Histology Image Classification: Design, implement, and test an algorithm for classification of epithelium tissue of the uterine cervix as Normal, CIN1, CIN2, or CIN3, in digitized, histology images in which the epithelium tissue has been segmented. Design, implement, and test algorithms for classification of epithelium tissue of the uterine cervix as Normal, CIN1, CIN2, or CIN3, in digitized, histology images in which the epithelium tissue has been segmented. Use standard visual classification criteria for guidance in developing the classification criteria. One commonly used feature to determine the CIN grade is the nuclear-cytoplasmic ratio: a larger ratio corresponds to a more severe CIN degree. For example, atypical cells are seen mostly in the lower third of the epithelium for CIN 1, lower half or two thirds of the epithelium for CIN 2, and full thickness of the epithelium for CIN 3. Segments of epithelium may be long and may have varying levels of pathology in subregions. It is necessary to develop a concept of classifying multiple subregions within one large, connected region of epithelium. The government will provide a set of segmented cervix histology images with epithelium classifications made by expert pathologists. 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. The purchase order period of performance will be for a 12-month Base Period of approximately September 19, 2011 through September 18, 2012. Evaluation criteria for contract award 1. The investigator shall have at least 10 years experience at a senior research level in the fields of medical image processing, pattern recognition, machine learning and computational intelligence with recent specific experience in analysis of cancerous cell and tissue images. 2. The investigator shall have specific recent background in analysis of biomedical images from literature for detecting content relevant to biomedical content-based indexing and retrieval of these images for clinical decision support. An award will be made to the offeror who represents the best value to the Government whereby each of the two evaluation criteria when combined, are more important than price. Offerors must submit a completed copy of the provision at FAR 52.212-3, Offeror Representations and Certifications - Commercial Items (August 2009), with their offers. The clause at FAR 52.212-5, Contract Terms and Conditions Required to Implement Statutes or Executive Orders - Commercial Items (June 2010), and the attached Statement of Work (SOW) apply to this acquisition, as well as the following clauses cited therein: FAR 52.232-33, Payment by Electronic Funds Transfer - Central Contractor Registration (October 2003). 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 quote 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 application 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 obtain from the web site: FAR 52.213-4, Terms and Conditions-Simplified Acquisitions (Other Than Commercial Items). Any questions can be submitted to Suet Vu, Contract Specialist, at 301-496-6546. All information received will be considered as part of a competitive acquisition. RESPONSES ARE DUE BY 1:00 PM LOCAL PREVAILING TIME ON September 13, 2011. This requirement is being processed by the National Library of Medicine (NLM), NIH.
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/HHS/NIH/OAM/NLM-11-157-SVU/listing.html)
- Place of Performance
- Address: Bethesda, Maryland, 20894, United States
- Zip Code: 20894
- Zip Code: 20894
- Record
- SN02556257-W 20110901/110831000730-9be8c5f5c80a9e699e8b7ad57a59cb59 (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 |