SOLICITATION NOTICE
R -- Clinical Decision Support in Evidence-Based Practice and Content-Based Image Retrieval
- Notice Date
- 9/12/2007
- Notice Type
- Solicitation Notice
- NAICS
- 541990
— All Other Professional, Scientific, and Technical Services
- Contracting Office
- Department of Health and Human Services, National Institutes of Health, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, UNITED STATES
- ZIP Code
- 00000
- Solicitation Number
- 07-190-CYC
- Response Due
- 9/27/2007
- Archive Date
- 10/12/2007
- Description
- It is the intent of the National Library of Medicine (NLM) to procure professional services from the University of Missouri- Rolla, Dr. R. Joe Stanley, on a sole source basis Proposed Work Professional services are required over a 12-month period for the analysis, design and development of techniques for (1) classifying figure images extracted from biomedical journal articles into categories suitable for Clinical Decision Support (CDS) in Evidence-Based Practice (EBP); and (2) classifying these and other medical images by modality and anatomy in support of Multiscale Content-Based Image Retrieval (CBIR). The Communications Engineering Branch (CEB) of the National Library of Medicine conducts research and development into the archiving and retrieval of biomedical multimedia information using technology such as CBIR, which allows the retrieval of images by features such as shape, color, and texture of regions of interest within the images. NLM maintains digitized spine x-ray images from second National Health and Nutrition Examination Survey (NHANES II), and uterine cervix images (cervigrams) from a multi-year longitudinal study conducted by the National Cancer Institute (NCI) for early detection of human papilloma virus (HPV) and progression to pre-cancer. The branch also supports research and development in Repository for Informed Decision Making (RiDEM) which explores methods for extraction of information for clinical journals and other NLM resources for decision support in EBP. The project is now exploring value added through use of automatically annotated images extracted from these resources to enhance the quality of the information presented. The investigator shall obtain a collection of images from the Government or sources identified by the Government. The investigator shall develop techniques for classifying the images on the criteria described above. In addition, the investigator shall develop techniques to further classify images within each class identified above into subclasses with images of uniform appearance, e.g. lung images in coronal view, lung images in sagittal view, hand images, histopathology images, tissues images etc. All methods shall be developed in MATLAB and Java. The investigator is encouraged to use open source classification tools, such as YALE/RapidMiner (http://www.rapid-i.com) over libraries found in MATLAB, if feasible. The investigator shall explore and improve upon techniques published in the literature from evaluation forums, such as ImageCLEF. No GUI need be developed in this effort. The investigator shall, however, develop command-line routines as proof-of-concept. All development shall be done as negotiated with the Government. The investigator shall provide bi-monthly progress updates in addition to semi-annual and annual reports. The Government shall keep the investigator updated with results obtained from intramural research efforts, if available. Required Tasks The following tasks are to be completed. Full detail is given in the Proposed Work section of this Statement of Work. All image analysis and annotation software delivered shall be written in Java and/or MATLAB (base version R2007a) computer languages. Open source tools such as YALE classification toolbox should be used as negotiated with the Government. Task Description Task 1: Techniques for automatic annotation of biomedical images by modality.The investigator shall conduct R&D for automatic classification of biomedical images found in biomedical journal article figures according to criteria identified in Table 1 and Table 2, described above. Task 2: Techniques for automatic annotation of biomedical images.The investigator shall conduct R&D for classification of biomedical images on visual similarity within particular image classes annotated from Task 1. For this, the investigator shall explore and evaluate techniques found in the literature, such as those reported in Image CLEF forum. 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: 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. Evaluation Criteria 1.The investigator shall have at least 8 years experience as a researcher in advanced technical applications for biomedical processing, and shall have demonstrable expertise (by conference and technical journal publications) in the areas of pattern recognition and machine learning, advanced image processing, including biomedical image segmentation; artificial neural networks, and the application of such methods to the classification of biomedical pathology in human subjects; and hands-on software skills in MATLAB and Java. 2.The investigator shall have demonstrable expertise in the application of advanced image segmentation and classification techniques to biomedical images. The University of Missouri-Rolla is uniquely qualified for this work because of the expertise and experience of the principal investigator below (Dr. Joe Stanley) in the specific area of feature classification of digitized spine x-rays and prior published work in color normalization for medical images, combined with his extensive educational background and experience in advanced image processing. Citations of published articles in these areas are available upon request. The proposed acquisition will be procured under FAR Part 13 - Acquisitions of Non- Commercial Items. This is not a Request for Quotations (RFQ), nor is an RFQ available. 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) (September 2006). However, all responsive sources may submit a capabilities statement in a timely manner that will be considered by the Government. Proposals must include pricing information. Responses must be in writing and must be received in the office within fifteen (15) business days from the publication date of this notice. EMAIL OR FAXED PROPOSALS WILL NOT BE ACCEPTED. NLM Synopsis No. NLM 07-190/CYC. Inquires regarding this procurement may be made to Cara Y. Calimano, Contract Specialist, NLM on (301) 496-6127.
- Place of Performance
- Address: 8600 Rockville Pike, Bethesda, MD
- Zip Code: 20894
- Country: UNITED STATES
- Zip Code: 20894
- Record
- SN01403809-W 20070914/070913072108 (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 |