SOURCES SOUGHT
A -- Generative Adversarial Networks for Automatic Whole Slide Imaging Dataset Expansion and Analysis - Draft SOW
- Notice Date
- 7/24/2018
- Notice Type
- Sources Sought
- NAICS
- 5417
— Scientific Research and Development ServicesT
- 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
- NIHLM201800083
- Archive Date
- 8/15/2018
- Point of Contact
- Keturah D. Busey, Phone: 3014966546
- E-Mail Address
-
buseyk@mail.nlm.nih.gov
(buseyk@mail.nlm.nih.gov)
- Small Business Set-Aside
- N/A
- Description
- Draft SOW This is a Small Business Sources Sought Notice. This is NOT a solicitation for proposals, proposal abstracts, or quotations. The purpose of this notice is to obtain information regarding: (1) the availability and capability of qualified small business sources; (2) whether they are small businesses; HUBZone small businesses; service- disabled, veteran-owned small businesses; 8(a) small businesses; veteran-owned small businesses; woman-owned small businesses; or small disadvantaged businesses; and (3) their size classification relative to the North American Industry Classification System (NAICS) code for the proposed acquisition. Your responses to the information requested will assist the Government in determining the appropriate acquisition method, including whether a set-aside is possible. An organization that is not considered a small business under the applicable NAICS code should not submit a response to this notice. The National Institutes of Health (NIH), National Library of Medicine (NLM) is conducting a market survey to help determine the availability and technical capability of qualified small businesses, veteran-owned small businesses and/or HUBZone small businesses capable of serving the needs identified below. This Sources Sought Notice is for informational and planning purposes only and shall not be construed as a solicitation or as an obligation or commitment by the Government. This notice is intended strictly for market research. BACKGROUND Cervical cancer remains a leading cause of cancer mortality and morbidity worldwide. It occurs earlier than most other female cancers, leading to a disproportionate loss of years of life compared with other cancers. Approximately 90% of the quarter million deaths per year occur in low- and middle-income countries, where prevention programs are limited. In some low-resource countries, cervical cancer is the leading female malignancy, with lifetime cumulative incidence exceeding 5%. Unless we are able to alter current trends, the number of new cases is projected to increase in the decades ahead as the global population ages and grows. The cancer arises from persistent infection of the cervix with approximately a dozen carcinogenic types of human papillomavirus (HPV). Routinely, expert pathologists visually examine histology slides for cervix tissue abnormality assessment. They classify squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN). Automating this classification requires manual markup of training data by an expert pathologist that is used for supervised machine learning. The process is tedious, prone to error, and often not exhaustively complete. There is a need to enhance automation capability by developing robust classifiers but that needs large samples of training data. Recently, GANs have been used to artificially generate training data for deep learning and other machine learning algorithms. However, much of recent work has focused creating new whole images for training. This work requires the contractor to develop novel GAN techniques for replicating CIN patterns within digitized whole slide histology images that reflect statistical reality in the training data and are sufficiently real to train a deep learning classifier which will then be used to detect and localize these patterns on a large previously unannotated image data set. These automatically detected segments must be evaluated by an expert pathologist and the end-to-end algorithm suitably refined to achieve optimal performance. State of the art in automatic classification of uterine cervix histology images has used manually marked strips of relevant classes of intraepithelial neoplasia within a small number of images. Because of the tedious nature of marking up these strips, the deep learning classifier is trained on and heavily augmented data set, limiting its value in real world applications. There is a need for a robust deep learning classifier for classifying CIN status of whole slide cervical biopsy tissues with predictable performance. This requires a large training data set which could be generated using a novel implementation of GANs. OBJECTIVE Professional services are required to (i) develop and evaluate novel automatic techniques for medical data set expansion using generative adversarial network (GAN) technology with a goal toward generating training data for deep learning / artificial intelligence (AI) applications. PROJECT REQUIREMENTS See attached draft statement of work. Anticipated Period of Performance The period of performance will be for base period from September 24, 2018 through September 23, 2019 with one (1) one-year option period. Other Important Considerations: This Sources Sought Notice is not a Request for Quotes (RFQ), nor is an RFQ available. All responsible sources may submit a capability statement which will be considered by the National Library of Medicine. Interested firms responding to this Sources Sought Notice must adhere to the following: (a) Provide a capability statement demonstrating relevant experience, skills and ability to fulfill the Government's requirements for the above. The capability statement should contain enough sufficient detail for the Government to make an informed decision regarding your capabilities; however, the statement should not exceed 10 pages. (b) The capability statement must identify the responder's: small business type and size; DUNS number; NAICS code; and technical and administrative points of contact, including names, titles, addresses, telephone and fax numbers, and e-mail addresses. (c) All capability statements must be submitted electronically no later than 12:00 p.m. local prevailing time on Tuesday, July 31, 2018. NLM requires capability statements to be submitted electronically through the NLM Electronic Contract Proposal System (eCPS) using the following link: https://ecps.nih.gov All capability statements received via eCPS by Tuesday, July 31, 2018 at 12:00 p.m. local prevailing time will be considered by NLM. For directions on using eCPS, go to https://ecps.nih.gov and click on "How to Submit." NOTE: To submit your electronic capability statement using eCPS, all offerors must have a valid NIH External Directory Account, which provides authentication and serves as a vehicle for secure transmission of documents and communication with the NLM. The NIH External Directory Account registration process may take up to 24 hours to become active. Submission of proposals by facsimile or e-mail is not accepted. Firms interested in responding to this notice must be able to provide the professional services required by NLM outlined in the attached Statement of Work. The offeror shall include all information necessary to document and/or support the qualification criteria in one clearly marked section of its proposal. All responses from responsible sources will be considered. Disclaimer and Important Notes: This notice does not obligate the Government to award a contract or otherwise pay for the information provided in response. The Government reserves the right to use information provided by respondents for any purpose deemed necessary and legally appropriate. Any organization responding to this notice should ensure that its response is complete and sufficiently detailed to allow the Government to determine the organization's qualifications to perform the work. Respondents are advised that the Government is under no obligation to acknowledge receipt of the information received or provide feedback to respondents with respect to any information submitted. After a review of the responses received, a pre-solicitation synopsis and solicitation may be published in Federal Business Opportunities. However, responses to this notice will not be considered adequate responses to a solicitation. Confidentiality: No proprietary, classified, confidential, or sensitive information should be included in your response. The Government reserves the right to use any non-proprietary technical information in any resultant solicitation(s).
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/HHS/NIH/OAM/NIHLM201800083/listing.html)
- Record
- SN05004722-W 20180726/180724231047-bdbf001621de502417ed500a9d947114 (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 |