It is the intent of the National Library of Medicine (NLM) to procure professional services from Texas Tech University, Lubbock, Texas (Dr. Hamed Sari-Sarraf) on a sole source basis. Period of Performance: September 1, 2005 - August 31, 2006. Professional services are required over a 12-month period for the creation of a system for the segmentation of objects in biomedical images by shape. As part of NLM R&D work to create a Content-Based Image Retrieval System for biomedical images, several segmentation algorithms for spine x-rays have been previously developed, using different segmentation methodologies. These algorithms have been valuable testbeds for understanding the interaction among algorithmic approaches and parameters, vertebral shape modeling, and statistical pixel characteristics of an important national collection of spine x-ray images collected in the second National Health and Nutrition Examination Survey (NHANES II). However NLM now intends to build upon these previous efforts by removing some of the limitations of these initial systems, adding additional capability, and integrating all of the methods into a "shape segmentation system" that will afford the user a menu of shape segmentation methods available under a common interface. It is the intent of NLM to use this shape segmentation system as a component in a future CBIR system. In addition, this system, or one or more of its segmentation methods, will be used as a tool for segmenting a large collection of spine x-ray images. Task description: Subtask 1: Review government-provided concepts for integrated shape segmentation system and production level segmentation system, and provide expert feedback and recommendations. Review initial set of new vertebrae shape models provided by the government and provide technical critique of the feasibility of supporting these models in the TT Group. Provide technical feedback on any Standard Interface Requirements (SIR) and Standard Segmentation Format (SSF) requirements provided by the government. Create initial design concepts for the integrated segmentation system. Conduct research into further improving segmentation performance for the spine x-ray images. Subtask 2: Implement integrated segmentation system at first level capability (possibly partial functionality). Review refined vertebrae shape models, and SIR/SSF requirements and provide technical analysis and feedback. Provide initial test results using one or more of the TT Group methods and using refined vertebrae shape models. Continue research into further improving segmentation performance for the spine x-ray images, including implementation of optimized segmentation. Subtask 3: Implement integrated segmentation system at initial version of full functional capability, although possibly without optimized spine x-ray segmentation. Continue research into further improving segmentation performance for the spine x-ray images, including implementation of this optimized segmentation. Provide test results for multiple spine x-ray images, including both cervical and lumbar spines, for all of the TT Group methods. Identify a method or methods most suitable for incorporation into the production level segmentation system and implement any required changes to make this method operate efficiently in the production system. Subtask 4: Incorporate new optimized spine x-ray segmentation into the integrated segmentation system. Test all methods in the integrated system on spine x-rays, other non-spine grayscale images, and color images. Test the optimized spine x-ray segmentation on a significant number of spine x-ray images, including both cervical and lumbar spine images. For subtasks 1-4, the Contractor will use digitized x-ray images made available by the government. 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 area of 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 Computer Vision and Image Analysis Laboratory (CVIAL). 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. 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. 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) business days from the publication date of this notice. Proposals must include pricing information. NLM Synopsis No. NLM 05-141/CYC. Inquires regarding this procurement may be made to Cara Y. Calimano, Contract Specialist, NLM on (301) 496-6127.

Bid Protests Not Available