Loren Data's SAM Daily™

FBO DAILY ISSUE OF AUGUST 18, 2004 FBO #0996
SOLICITATION NOTICE

R -- Live Wire Segmentation, Collection of Reference Data, and Biomedical Classification

Notice Date

8/16/2004
 

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
 

ZIP Code

20894
 

Solicitation Number

04-210-CYC
 

Response Due

8/31/2004
 

Archive Date

9/15/2004
 

Point of Contact

Cara Calimano, Office Automation Assistance, Phone 301 496-6127, Fax 301 402-8169, - Karen Riggs, Contracting Officer, Phone 301 496-6546, Fax 301 402-0642,
 

E-Mail Address

CalimaC@mail.nlm.nih.gov, kr33v@nih.gov
 

Description

It is the intent of the National Library of Medicine (NLM) to procure professional services on a sole source basis The Curators of the University of Missouri, Rolla, Missouri for a continuation of existing services.. The overall objective of this procurement is procure professional services over a 12-month period for the analysis, design and development of techniques for advanced segmentation algorithms that will incorporate the live wire method for digitized x-ray images. The following task are to be completed. All software delivered will be in the MATLAB language, except as negotiated by the government. Subtask 1) Implement an extended capability live wire segmentation algorithm. This capability will include (1) extending the algorithm capability to accommodate segmentation of the uterine cervix images; (2) incorporating user editing capability, including the capability to sequentially ?undo? and ?redo? previous control points and the associated segments of the segmentation; and (3) incorporating interactive user capability to rain the live wire segment to adhere to the specific type of edge currently being followed, rather that the strongest edge in the neighborhood. Subtask 2) Collect spine x-ray reference segmentations. The work will build an extended reference set of segmented vertebrae from the digitized images by collecting from at least two medical experts? segmentations of vertebrae for approximately 1250 images of the digitized spine, according to specifications and methodology negotiated with the government, including both cervical and lumbar spine images for the NHANES II data set. Subtask 3) Implement classification algorithm for uterine cervix images. The implementation will automatically classify uterine cervix images for the presence of acetowhitened regions of size above a specified threshold. This work will incorporate the use of artificial neural networks or other advanced classification methods in a manner similar to the classification work that has been done for the digitized x-rays. Subtask 4) Evaluate the uterine cervix classification algorithm. The performance of the algorithm for classification of uterine cervix images for presence of acetowhitened regions will be evaluated against a set of classifications by a medical expert, and supplied by the government. For subtasks 3 and 4, the contractor will use digitized x-ray images made available by the government. Evaluation Criteria: (1) The investigator shall have at least 5 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 advanced image processing, including biomedical image segmentation; artificial neural networks and classification methods, and the application of such methods to the classification of biomedical pathology in human subjects; and hands-on software skills in MATLAB and C/C++. (2) The investigator shall have demonstrable expertise in the application of advanced image segmentation and classification techniques to the NHANES II digitized x-rays. The University of Missouri-Rolla is uniquely qualified for this work because of the expertise and experience of the principal investigator below ( Joe Stanley) in the specific area of feature classification of digitized spine x-rays, combined with his extensive educational background and experience in advanced image processing. Dr. R. Joe Stanley is on the faculty of the Department of Electrical and Computer Engineering at the University of Missouri-Rolla. Based on his professional training and over 5 years experience in both academia and the private sector, Dr. Stanley is uniquely qualified for this work. The proposed acquisition will be procured under FAR Part 13 - Simplified Acquisition of Non-Commercial Items. This is not a Request for Quotations (RFQ), nor is an RFQ available. However, all responsive sources may submit a capabilities statement in a timely manner that will be considered by the Government. Sources interested in responding to this notice must be able to provide convincing evidence that they possess the requisite expertise and experience to successfully perform the services as specified above. Responses must be in writing and must be received in the office within fifteen (15) calendar days from the publication date of this notice. Proposal must include pricing information. NLM Synopsis No. NLM 04-210/CYC. Inquires regarding this procurement may be made to Cara Y. Calimano, Office Automation Technician, NLM on (301) 496 6127.
 

Place of Performance

Address: 8600 Rockville Pike, Bethesda, Maryland

Zip Code: 20894

Country: US
 

Record

SN00644476-W 20040818/040816211826 (fbodaily.com)
 

Source

FedBizOpps.gov Link to This Notice
(may not be valid after Archive Date)

---

| FSG Index  |  This Issue's Index  |  Today's FBO Daily Index Page |